{ "cells": [ { "cell_type": "markdown", "id": "4a867836", "metadata": {}, "source": [ "Bayesian Neural Network model traning and prediction data generation." ] }, { "cell_type": "code", "execution_count": 1, "id": "210da263", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "\n", "from sklearn.preprocessing import StandardScaler\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.neural_network import MLPRegressor\n", "import matplotlib.pyplot as plt\n", "from sklearn.metrics import r2_score\n", "\n", "import pickle" ] }, { "cell_type": "code", "execution_count": 2, "id": "edbf3b27", "metadata": {}, "outputs": [], "source": [ "import numpy as np\n", "import tensorflow as tf\n", "from tensorflow import keras\n", "from tensorflow.keras import layers\n", "import tensorflow_datasets as tfds\n", "import tensorflow_probability as tfp\n", "\n", "tfk = tf.keras\n", "tf.keras.backend.set_floatx(\"float32\")\n", "import tensorflow_probability as tfp\n", "tfd = tfp.distributions\n", "from sklearn.preprocessing import StandardScaler\n", "from sklearn.ensemble import IsolationForest\n", "\n", "from scipy.stats import norm" ] }, { "cell_type": "markdown", "id": "9dadf6ec", "metadata": {}, "source": [ "Load the training databases, generated in player_match_database_creation" ] }, { "cell_type": "code", "execution_count": 3, "id": "fa098fa4", "metadata": {}, "outputs": [], "source": [ "db1 = pd.read_excel('mid_outputs/database_entries.xlsx', index_col = 0) \n", "db2 = pd.read_excel('mid_outputs/season2021/database_entries.xlsx', index_col = 0) \n", "db3 = pd.read_excel('mid_outputs/season2122/database_entries.xlsx', index_col = 0) " ] }, { "cell_type": "code", "execution_count": 4, "id": "f71fa9a4", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
matchdayplayerteamoppteamhomevotegoalsassistscards_malusfantavote...miscontrolsdispossessedfoulsfouledaerials_wonaerials_lostcarriesprogressive_carriescarries_into_final_thirdcarries_into_penalty_area
01ToloiAtalantaSampdoria07.0100.010.0...0.0073640.0014730.0066270.0058910.0139910.0110460.3652430.0081000.0162000.000000
11DjimsitiAtalantaSampdoria06.0000.06.0...0.0018760.0075050.0056290.0056290.0225140.0150090.4878050.0037520.0037520.000000
21HateboerAtalantaSampdoria06.0000.55.5...0.0059930.0052430.0134830.0014980.0164790.0104870.2838950.0119850.0097380.000749
31OkoliAtalantaSampdoria05.5000.55.0...0.0130180.0035500.0153850.0082840.0473370.0272190.2698220.0023670.0047340.000000
41ZorteaAtalantaSampdoria06.0000.55.5...0.0000000.0000000.0222220.0000000.0111110.0222220.5333330.0666670.0666670.000000
..................................................................
2455138TamezeVeronaLazio05.5000.05.5...0.0198140.0101010.0128210.0132090.0236990.0213680.3372180.0213680.0128210.003885
2455238HonglaVeronaLazio07.0100.59.5...0.0184330.0122890.0230410.0076800.0230410.0261140.3410140.0092170.0153610.003072
2455338LasagnaVeronaLazio07.0100.59.5...0.0464530.0228040.0160470.0084460.0261820.0413850.1908780.0219590.0109800.005912
2455438CaprariVeronaLazio06.0000.06.0...0.0339540.0197150.0153340.0270170.0029210.0098580.3913840.0427160.0277470.018620
2455538SimeoneVeronaLazio07.0100.010.0...0.0512630.0301550.0211080.0218620.0226160.0407090.2461360.0150770.0128160.006031
\n", "

24556 rows × 122 columns

\n", "
" ], "text/plain": [ " matchday player team oppteam home vote goals assists \\\n", "0 1 Toloi Atalanta Sampdoria 0 7.0 1 0 \n", "1 1 Djimsiti Atalanta Sampdoria 0 6.0 0 0 \n", "2 1 Hateboer Atalanta Sampdoria 0 6.0 0 0 \n", "3 1 Okoli Atalanta Sampdoria 0 5.5 0 0 \n", "4 1 Zortea Atalanta Sampdoria 0 6.0 0 0 \n", "... ... ... ... ... ... ... ... ... \n", "24551 38 Tameze Verona Lazio 0 5.5 0 0 \n", "24552 38 Hongla Verona Lazio 0 7.0 1 0 \n", "24553 38 Lasagna Verona Lazio 0 7.0 1 0 \n", "24554 38 Caprari Verona Lazio 0 6.0 0 0 \n", "24555 38 Simeone Verona Lazio 0 7.0 1 0 \n", "\n", " cards_malus fantavote ... miscontrols dispossessed fouls \\\n", "0 0.0 10.0 ... 0.007364 0.001473 0.006627 \n", "1 0.0 6.0 ... 0.001876 0.007505 0.005629 \n", "2 0.5 5.5 ... 0.005993 0.005243 0.013483 \n", "3 0.5 5.0 ... 0.013018 0.003550 0.015385 \n", "4 0.5 5.5 ... 0.000000 0.000000 0.022222 \n", "... ... ... ... ... ... ... \n", "24551 0.0 5.5 ... 0.019814 0.010101 0.012821 \n", "24552 0.5 9.5 ... 0.018433 0.012289 0.023041 \n", "24553 0.5 9.5 ... 0.046453 0.022804 0.016047 \n", "24554 0.0 6.0 ... 0.033954 0.019715 0.015334 \n", "24555 0.0 10.0 ... 0.051263 0.030155 0.021108 \n", "\n", " fouled aerials_won aerials_lost carries progressive_carries \\\n", "0 0.005891 0.013991 0.011046 0.365243 0.008100 \n", "1 0.005629 0.022514 0.015009 0.487805 0.003752 \n", "2 0.001498 0.016479 0.010487 0.283895 0.011985 \n", "3 0.008284 0.047337 0.027219 0.269822 0.002367 \n", "4 0.000000 0.011111 0.022222 0.533333 0.066667 \n", "... ... ... ... ... ... \n", "24551 0.013209 0.023699 0.021368 0.337218 0.021368 \n", "24552 0.007680 0.023041 0.026114 0.341014 0.009217 \n", "24553 0.008446 0.026182 0.041385 0.190878 0.021959 \n", "24554 0.027017 0.002921 0.009858 0.391384 0.042716 \n", "24555 0.021862 0.022616 0.040709 0.246136 0.015077 \n", "\n", " carries_into_final_third carries_into_penalty_area \n", "0 0.016200 0.000000 \n", "1 0.003752 0.000000 \n", "2 0.009738 0.000749 \n", "3 0.004734 0.000000 \n", "4 0.066667 0.000000 \n", "... ... ... \n", "24551 0.012821 0.003885 \n", "24552 0.015361 0.003072 \n", "24553 0.010980 0.005912 \n", "24554 0.027747 0.018620 \n", "24555 0.012816 0.006031 \n", "\n", "[24556 rows x 122 columns]" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "db = pd.concat([db1, db2, db3], ignore_index = True) \n", "\n", "db" ] }, { "cell_type": "code", "execution_count": 5, "id": "1d024554", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
matchdayplayerteamoppteamhomevotegoalsassistscards_malusfantavote...gk_psxggk_psnpxg_per_shot_on_target_againstgk_psxg_netgk_passes_completed_launchedgk_passes_launchedgk_passesgk_passes_throwsgk_goal_kicksgk_crossesgk_crosses_stopped
01MussoAtalantaSampdoria06.0000.55.5...12.700.21-1.3081.0185.0372.0107.098.0174.010.0
11SkorupskiBolognaLazio06.5-200.04.5...30.800.281.8099.0240.0563.0117.0153.0299.018.0
21VicarioEmpoliSpezia05.5-100.04.5...26.400.270.40102.0310.0766.0113.0108.0426.025.0
31GolliniFiorentinaCremonese15.0-200.03.0...9.350.240.8524.068.0291.547.069.5122.53.5
41HandanovicInterLecce06.5-100.05.5...10.600.30-1.4027.052.0266.046.045.079.02.0
..................................................................
124021ConsigliSassuoloAtalanta16.0000.06.0...23.300.35-4.70112.0269.0686.099.0172.0255.016.0
124121DragowskiSpeziaNapoli15.0-300.02.0...28.100.27-3.9085.0268.0503.092.0109.0251.09.0
124221Milinkovic-Savic V.TorinoUdinese16.5000.06.5...21.900.23-0.10148.0524.0788.095.0155.0263.018.0
124321SilvestriUdineseTorino06.5-100.05.5...23.900.311.9090.0225.0450.076.0164.0275.05.0
124421Montipo'VeronaLazio16.0-100.05.0...27.600.25-4.40206.0413.0497.065.0168.0294.015.0
\n", "

1245 rows × 102 columns

\n", "
" ], "text/plain": [ " matchday player team oppteam home vote goals \\\n", "0 1 Musso Atalanta Sampdoria 0 6.0 0 \n", "1 1 Skorupski Bologna Lazio 0 6.5 -2 \n", "2 1 Vicario Empoli Spezia 0 5.5 -1 \n", "3 1 Gollini Fiorentina Cremonese 1 5.0 -2 \n", "4 1 Handanovic Inter Lecce 0 6.5 -1 \n", "... ... ... ... ... ... ... ... \n", "1240 21 Consigli Sassuolo Atalanta 1 6.0 0 \n", "1241 21 Dragowski Spezia Napoli 1 5.0 -3 \n", "1242 21 Milinkovic-Savic V. Torino Udinese 1 6.5 0 \n", "1243 21 Silvestri Udinese Torino 0 6.5 -1 \n", "1244 21 Montipo' Verona Lazio 1 6.0 -1 \n", "\n", " assists cards_malus fantavote ... gk_psxg \\\n", "0 0 0.5 5.5 ... 12.70 \n", "1 0 0.0 4.5 ... 30.80 \n", "2 0 0.0 4.5 ... 26.40 \n", "3 0 0.0 3.0 ... 9.35 \n", "4 0 0.0 5.5 ... 10.60 \n", "... ... ... ... ... ... \n", "1240 0 0.0 6.0 ... 23.30 \n", "1241 0 0.0 2.0 ... 28.10 \n", "1242 0 0.0 6.5 ... 21.90 \n", "1243 0 0.0 5.5 ... 23.90 \n", "1244 0 0.0 5.0 ... 27.60 \n", "\n", " gk_psnpxg_per_shot_on_target_against gk_psxg_net \\\n", "0 0.21 -1.30 \n", "1 0.28 1.80 \n", "2 0.27 0.40 \n", "3 0.24 0.85 \n", "4 0.30 -1.40 \n", "... ... ... \n", "1240 0.35 -4.70 \n", "1241 0.27 -3.90 \n", "1242 0.23 -0.10 \n", "1243 0.31 1.90 \n", "1244 0.25 -4.40 \n", "\n", " gk_passes_completed_launched gk_passes_launched gk_passes \\\n", "0 81.0 185.0 372.0 \n", "1 99.0 240.0 563.0 \n", "2 102.0 310.0 766.0 \n", "3 24.0 68.0 291.5 \n", "4 27.0 52.0 266.0 \n", "... ... ... ... \n", "1240 112.0 269.0 686.0 \n", "1241 85.0 268.0 503.0 \n", "1242 148.0 524.0 788.0 \n", "1243 90.0 225.0 450.0 \n", "1244 206.0 413.0 497.0 \n", "\n", " gk_passes_throws gk_goal_kicks gk_crosses gk_crosses_stopped \n", "0 107.0 98.0 174.0 10.0 \n", "1 117.0 153.0 299.0 18.0 \n", "2 113.0 108.0 426.0 25.0 \n", "3 47.0 69.5 122.5 3.5 \n", "4 46.0 45.0 79.0 2.0 \n", "... ... ... ... ... \n", "1240 99.0 172.0 255.0 16.0 \n", "1241 92.0 109.0 251.0 9.0 \n", "1242 95.0 155.0 263.0 18.0 \n", "1243 76.0 164.0 275.0 5.0 \n", "1244 65.0 168.0 294.0 15.0 \n", "\n", "[1245 rows x 102 columns]" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "db_gk1 = pd.read_excel('mid_outputs/database_entries_gk.xlsx', index_col = 0) \n", "db_gk2 = pd.read_excel('mid_outputs/season2021/database_entries_gk.xlsx', index_col = 0) \n", "db_gk3 = pd.read_excel('mid_outputs/season2122/database_entries_gk.xlsx', index_col = 0) \n", "\n", "db_gk = pd.concat([db_gk1, db_gk1, db_gk1], ignore_index = True) \n", "\n", "db_gk" ] }, { "cell_type": "markdown", "id": "04df0936", "metadata": {}, "source": [ "Load player stats from current season and past seasons" ] }, { "cell_type": "code", "execution_count": 6, "id": "bc9dae87", "metadata": {}, "outputs": [], "source": [ "players_orig = pd.read_excel('mid_outputs/players_stats.xlsx', index_col = 3)\n", "#players = pd.read_excel('mid_outputs/players_stats_rwk.xlsx', index_col = 3) # reworked stats to account for past season\n", "\n", "players_old = pd.read_excel('mid_outputs/season2122/players_stats.xlsx', index_col = 3)\n", "players_old_2 = pd.read_excel('mid_outputs/season2021/players_stats.xlsx', index_col = 3)\n", "\n", "players = players_orig" ] }, { "cell_type": "markdown", "id": "397babf2", "metadata": {}, "source": [ "Load team data from current season and add an average Serie A team row" ] }, { "cell_type": "code", "execution_count": 7, "id": "493b0495", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_11840\\661405348.py:3: FutureWarning: Dropping of nuisance columns in DataFrame reductions (with 'numeric_only=None') is deprecated; in a future version this will raise TypeError. Select only valid columns before calling the reduction.\n", " avg_row = pd.DataFrame(index = ['Avg'], data = [team_data.mean()], columns = team_data.columns)\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
teamteam_players_usedteam_possessionteam_gamesteam_games_startsteam_minutesteam_goalsteam_assiststeam_pens_madeteam_pens_att...vs_team_foulsvs_team_fouledvs_team_offsidesvs_team_pens_wonvs_team_pens_concededvs_team_own_goalsvs_team_ball_recoveriesvs_team_aerials_wonvs_team_aerials_lostvs_team_aerials_won_pct
AtalantaAtalanta24.0049.0021.0231.01890.038.027.06.008.0...232.0244.026.001.08.001.01261.0260.0317.045.10
BolognaBologna25.0051.9021.0231.01890.027.020.04.004.0...262.0254.036.003.04.001.01145.0239.0193.055.30
CremoneseCremonese30.0044.2021.0231.01890.015.07.02.004.0...232.0264.033.003.04.000.01168.0388.0296.056.70
EmpoliEmpoli27.0046.8021.0231.01890.019.011.00.000.0...270.0244.035.002.00.000.01104.0242.0211.053.40
FiorentinaFiorentina28.0057.3021.0231.01890.023.018.02.004.0...296.0252.054.001.04.000.01061.0274.0317.046.40
VeronaHellas Verona34.0043.1021.0231.01890.017.014.00.000.0...213.0302.024.001.00.002.01173.0385.0422.047.70
InterInter23.0054.0021.0231.01890.040.027.02.002.0...263.0237.019.002.02.001.0960.0221.0266.045.40
JuventusJuventus26.0049.2021.0231.01890.033.025.03.004.0...229.0232.027.000.04.000.01064.0247.0257.049.00
LazioLazio21.0051.4021.0231.01890.036.026.03.004.0...294.0206.044.001.04.001.01157.0207.0216.048.90
LecceLecce26.0042.4021.0231.01890.020.014.01.002.0...275.0279.045.003.02.001.01141.0396.0316.055.60
MilanMilan27.0053.9021.0231.01890.035.030.02.002.0...255.0251.025.004.02.002.01059.0249.0305.044.90
MonzaMonza29.0055.9021.0231.01890.026.016.04.004.0...303.0263.037.000.04.001.01075.0226.0241.048.40
NapoliNapoli24.0061.4021.0231.01890.051.040.05.006.0...291.0192.028.001.05.000.01049.0214.0259.045.20
RomaRoma26.0048.9021.0231.01890.028.019.03.005.0...292.0238.010.000.05.000.01095.0205.0245.045.60
SalernitanaSalernitana28.0045.1021.0231.01890.024.016.01.001.0...238.0242.052.008.01.001.01143.0268.0247.052.00
SampdoriaSampdoria31.0047.9021.0231.01890.010.08.00.000.0...328.0288.056.004.00.000.01126.0340.0339.050.10
SassuoloSassuolo29.0048.5021.0231.01890.024.018.04.005.0...275.0200.069.002.05.000.01088.0243.0195.055.50
SpeziaSpezia33.0045.9021.0231.01890.015.010.02.002.0...225.0279.050.001.02.002.01225.0337.0285.054.20
TorinoTorino25.0053.0021.0231.01890.022.017.01.001.0...229.0287.023.003.01.000.01095.0347.0319.052.10
UdineseUdinese25.0050.0021.0231.01890.027.023.00.000.0...274.0242.034.002.00.001.01063.0222.0264.045.70
AvgAvg27.0549.9921.0231.01890.026.519.32.252.9...263.8249.836.352.12.850.71112.6275.5275.549.86
\n", "

21 rows × 303 columns

\n", "
" ], "text/plain": [ " team team_players_used team_possession team_games \\\n", "Atalanta Atalanta 24.00 49.00 21.0 \n", "Bologna Bologna 25.00 51.90 21.0 \n", "Cremonese Cremonese 30.00 44.20 21.0 \n", "Empoli Empoli 27.00 46.80 21.0 \n", "Fiorentina Fiorentina 28.00 57.30 21.0 \n", "Verona Hellas Verona 34.00 43.10 21.0 \n", "Inter Inter 23.00 54.00 21.0 \n", "Juventus Juventus 26.00 49.20 21.0 \n", "Lazio Lazio 21.00 51.40 21.0 \n", "Lecce Lecce 26.00 42.40 21.0 \n", "Milan Milan 27.00 53.90 21.0 \n", "Monza Monza 29.00 55.90 21.0 \n", "Napoli Napoli 24.00 61.40 21.0 \n", "Roma Roma 26.00 48.90 21.0 \n", "Salernitana Salernitana 28.00 45.10 21.0 \n", "Sampdoria Sampdoria 31.00 47.90 21.0 \n", "Sassuolo Sassuolo 29.00 48.50 21.0 \n", "Spezia Spezia 33.00 45.90 21.0 \n", "Torino Torino 25.00 53.00 21.0 \n", "Udinese Udinese 25.00 50.00 21.0 \n", "Avg Avg 27.05 49.99 21.0 \n", "\n", " team_games_starts team_minutes team_goals team_assists \\\n", "Atalanta 231.0 1890.0 38.0 27.0 \n", "Bologna 231.0 1890.0 27.0 20.0 \n", "Cremonese 231.0 1890.0 15.0 7.0 \n", "Empoli 231.0 1890.0 19.0 11.0 \n", "Fiorentina 231.0 1890.0 23.0 18.0 \n", "Verona 231.0 1890.0 17.0 14.0 \n", "Inter 231.0 1890.0 40.0 27.0 \n", "Juventus 231.0 1890.0 33.0 25.0 \n", "Lazio 231.0 1890.0 36.0 26.0 \n", "Lecce 231.0 1890.0 20.0 14.0 \n", "Milan 231.0 1890.0 35.0 30.0 \n", "Monza 231.0 1890.0 26.0 16.0 \n", "Napoli 231.0 1890.0 51.0 40.0 \n", "Roma 231.0 1890.0 28.0 19.0 \n", "Salernitana 231.0 1890.0 24.0 16.0 \n", "Sampdoria 231.0 1890.0 10.0 8.0 \n", "Sassuolo 231.0 1890.0 24.0 18.0 \n", "Spezia 231.0 1890.0 15.0 10.0 \n", "Torino 231.0 1890.0 22.0 17.0 \n", "Udinese 231.0 1890.0 27.0 23.0 \n", "Avg 231.0 1890.0 26.5 19.3 \n", "\n", " team_pens_made team_pens_att ... vs_team_fouls \\\n", "Atalanta 6.00 8.0 ... 232.0 \n", "Bologna 4.00 4.0 ... 262.0 \n", "Cremonese 2.00 4.0 ... 232.0 \n", "Empoli 0.00 0.0 ... 270.0 \n", "Fiorentina 2.00 4.0 ... 296.0 \n", "Verona 0.00 0.0 ... 213.0 \n", "Inter 2.00 2.0 ... 263.0 \n", "Juventus 3.00 4.0 ... 229.0 \n", "Lazio 3.00 4.0 ... 294.0 \n", "Lecce 1.00 2.0 ... 275.0 \n", "Milan 2.00 2.0 ... 255.0 \n", "Monza 4.00 4.0 ... 303.0 \n", "Napoli 5.00 6.0 ... 291.0 \n", "Roma 3.00 5.0 ... 292.0 \n", "Salernitana 1.00 1.0 ... 238.0 \n", "Sampdoria 0.00 0.0 ... 328.0 \n", "Sassuolo 4.00 5.0 ... 275.0 \n", "Spezia 2.00 2.0 ... 225.0 \n", "Torino 1.00 1.0 ... 229.0 \n", "Udinese 0.00 0.0 ... 274.0 \n", "Avg 2.25 2.9 ... 263.8 \n", "\n", " vs_team_fouled vs_team_offsides vs_team_pens_won \\\n", "Atalanta 244.0 26.00 1.0 \n", "Bologna 254.0 36.00 3.0 \n", "Cremonese 264.0 33.00 3.0 \n", "Empoli 244.0 35.00 2.0 \n", "Fiorentina 252.0 54.00 1.0 \n", "Verona 302.0 24.00 1.0 \n", "Inter 237.0 19.00 2.0 \n", "Juventus 232.0 27.00 0.0 \n", "Lazio 206.0 44.00 1.0 \n", "Lecce 279.0 45.00 3.0 \n", "Milan 251.0 25.00 4.0 \n", "Monza 263.0 37.00 0.0 \n", "Napoli 192.0 28.00 1.0 \n", "Roma 238.0 10.00 0.0 \n", "Salernitana 242.0 52.00 8.0 \n", "Sampdoria 288.0 56.00 4.0 \n", "Sassuolo 200.0 69.00 2.0 \n", "Spezia 279.0 50.00 1.0 \n", "Torino 287.0 23.00 3.0 \n", "Udinese 242.0 34.00 2.0 \n", "Avg 249.8 36.35 2.1 \n", "\n", " vs_team_pens_conceded vs_team_own_goals \\\n", "Atalanta 8.00 1.0 \n", "Bologna 4.00 1.0 \n", "Cremonese 4.00 0.0 \n", "Empoli 0.00 0.0 \n", "Fiorentina 4.00 0.0 \n", "Verona 0.00 2.0 \n", "Inter 2.00 1.0 \n", "Juventus 4.00 0.0 \n", "Lazio 4.00 1.0 \n", "Lecce 2.00 1.0 \n", "Milan 2.00 2.0 \n", "Monza 4.00 1.0 \n", "Napoli 5.00 0.0 \n", "Roma 5.00 0.0 \n", "Salernitana 1.00 1.0 \n", "Sampdoria 0.00 0.0 \n", "Sassuolo 5.00 0.0 \n", "Spezia 2.00 2.0 \n", "Torino 1.00 0.0 \n", "Udinese 0.00 1.0 \n", "Avg 2.85 0.7 \n", "\n", " vs_team_ball_recoveries vs_team_aerials_won \\\n", "Atalanta 1261.0 260.0 \n", "Bologna 1145.0 239.0 \n", "Cremonese 1168.0 388.0 \n", "Empoli 1104.0 242.0 \n", "Fiorentina 1061.0 274.0 \n", "Verona 1173.0 385.0 \n", "Inter 960.0 221.0 \n", "Juventus 1064.0 247.0 \n", "Lazio 1157.0 207.0 \n", "Lecce 1141.0 396.0 \n", "Milan 1059.0 249.0 \n", "Monza 1075.0 226.0 \n", "Napoli 1049.0 214.0 \n", "Roma 1095.0 205.0 \n", "Salernitana 1143.0 268.0 \n", "Sampdoria 1126.0 340.0 \n", "Sassuolo 1088.0 243.0 \n", "Spezia 1225.0 337.0 \n", "Torino 1095.0 347.0 \n", "Udinese 1063.0 222.0 \n", "Avg 1112.6 275.5 \n", "\n", " vs_team_aerials_lost vs_team_aerials_won_pct \n", "Atalanta 317.0 45.10 \n", "Bologna 193.0 55.30 \n", "Cremonese 296.0 56.70 \n", "Empoli 211.0 53.40 \n", "Fiorentina 317.0 46.40 \n", "Verona 422.0 47.70 \n", "Inter 266.0 45.40 \n", "Juventus 257.0 49.00 \n", "Lazio 216.0 48.90 \n", "Lecce 316.0 55.60 \n", "Milan 305.0 44.90 \n", "Monza 241.0 48.40 \n", "Napoli 259.0 45.20 \n", "Roma 245.0 45.60 \n", "Salernitana 247.0 52.00 \n", "Sampdoria 339.0 50.10 \n", "Sassuolo 195.0 55.50 \n", "Spezia 285.0 54.20 \n", "Torino 319.0 52.10 \n", "Udinese 264.0 45.70 \n", "Avg 275.5 49.86 \n", "\n", "[21 rows x 303 columns]" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "team_data = pd.read_excel('mid_outputs/team_data.xlsx', index_col = 0)\n", "\n", "avg_row = pd.DataFrame(index = ['Avg'], data = [team_data.mean()], columns = team_data.columns)\n", "avg_row['team']['Avg'] = 'Avg'\n", "\n", "team_data = pd.concat([team_data, avg_row])\n", "\n", "team_data" ] }, { "cell_type": "markdown", "id": "cc1cd13d", "metadata": {}, "source": [ "Data processing functions copied from player_match_dataset_creation" ] }, { "cell_type": "code", "execution_count": 8, "id": "32f56138", "metadata": {}, "outputs": [], "source": [ "features_abs = ['r',\n", " 'games',\n", " 'games_starts', \n", " 'minutes',\n", " 'shots_on_target_pct',\n", " 'goals_per_shot',\n", " 'goals_per_shot_on_target',\n", " 'passes_pct',\n", " #'dribble_tackles_pct',\n", " #'dribbles_completed_pct',\n", " 'aerials_won_pct',\n", " 'team_possession',\n", " 'team_goals_assists_per90',\n", " 'team_goals_pens_per90',\n", " 'team_goals_assists_pens_per90',\n", " 'team_xg_per90',\n", " 'team_gk_goals_against_per90',\n", " 'team_gk_save_pct',\n", " 'team_gk_clean_sheets_pct',\n", " 'team_passes_pct',\n", " 'team_passes_pct_medium',\n", " 'team_passes_pct_long',\n", " 'team_sca_per90',\n", " 'team_gca_per90',\n", " #'team_dribble_tackles_pct',\n", " 'team_aerials_won_pct',\n", " 'vs_team_possession',\n", " 'vs_team_goals_per90',\n", " 'vs_team_assists_per90',\n", " 'vs_team_xg_per90',\n", " 'vs_team_gk_save_pct',\n", " 'vs_team_gk_clean_sheets_pct',\n", " 'vs_team_gk_pct_passes_launched',\n", " 'vs_team_gk_crosses_stopped_pct',\n", " 'vs_team_shots_on_target_per90',\n", " 'vs_team_passes_pct',\n", " 'vs_team_passes_pct_short',\n", " 'vs_team_passes_pct_medium',\n", " 'vs_team_passes_pct_long',\n", " 'vs_team_sca_per90',\n", " 'vs_team_gca_per90',\n", " #'vs_team_dribble_tackles_pct',\n", " #'vs_team_dribbles_completed_pct',\n", " 'vs_team_aerials_won_pct',\n", " 'opp_team_possession',\n", " 'opp_team_goals_assists_per90',\n", " 'opp_team_goals_pens_per90',\n", " 'opp_team_goals_assists_pens_per90',\n", " 'opp_team_xg_per90',\n", " 'opp_team_gk_goals_against_per90',\n", " 'opp_team_gk_save_pct',\n", " 'opp_team_gk_clean_sheets_pct',\n", " 'opp_team_passes_pct',\n", " 'opp_team_passes_pct_medium',\n", " 'opp_team_passes_pct_long',\n", " 'opp_team_sca_per90',\n", " 'opp_team_gca_per90',\n", " #'opp_team_dribble_tackles_pct',\n", " 'opp_team_aerials_won_pct',\n", " 'opp_vs_team_possession',\n", " 'opp_vs_team_goals_per90',\n", " 'opp_vs_team_assists_per90',\n", " 'opp_vs_team_xg_per90',\n", " 'opp_vs_team_gk_save_pct',\n", " 'opp_vs_team_gk_clean_sheets_pct',\n", " 'opp_vs_team_gk_pct_passes_launched',\n", " 'opp_vs_team_gk_crosses_stopped_pct',\n", " 'opp_vs_team_shots_on_target_per90',\n", " 'opp_vs_team_passes_pct',\n", " 'opp_vs_team_passes_pct_short',\n", " 'opp_vs_team_passes_pct_medium',\n", " 'opp_vs_team_passes_pct_long',\n", " 'opp_vs_team_sca_per90',\n", " 'opp_vs_team_gca_per90',\n", " #'opp_vs_team_dribble_tackles_pct',\n", " #'opp_vs_team_dribbles_completed_pct',\n", " 'opp_vs_team_aerials_won_pct',\n", " \n", " 'vote_avg',\n", " 'vote_std']\n", "\n", "features_rel = [\n", " 'goals',\n", " 'assists',\n", " 'cards_yellow',\n", " 'cards_red',\n", " 'xg',\n", " 'npxg',\n", " 'shots_on_target',\n", " 'passes_completed',\n", " 'passes_into_final_third',\n", " 'passes_into_penalty_area',\n", " 'progressive_passes',\n", " 'passes_live',\n", " 'passes_dead',\n", " 'through_balls',\n", " 'passes_switches',\n", " 'crosses',\n", " 'corner_kicks',\n", " #'dribble_tackles',\n", " #'dribbles_vs',\n", " #'dribbled_past',\n", " 'blocks',\n", " 'blocked_shots',\n", " 'blocked_passes',\n", " 'interceptions',\n", " 'clearances',\n", " 'errors',\n", " 'touches',\n", " 'touches_def_pen_area',\n", " 'touches_def_3rd',\n", " 'touches_mid_3rd',\n", " 'touches_att_3rd',\n", " 'touches_att_pen_area',\n", " 'touches_live_ball',\n", " #'dribbles_completed',\n", " #'dribbles',\n", " 'passes_received',\n", " 'miscontrols',\n", " 'dispossessed',\n", " 'fouls',\n", " 'fouled',\n", " 'aerials_won',\n", " 'aerials_lost',\n", " 'carries',\n", " 'progressive_carries',\n", " 'carries_into_final_third',\n", " 'carries_into_penalty_area']\n", "\n", "features_rel_gamecorr = [\n", " 'goals',\n", " 'assists',\n", " 'xg',\n", " 'npxg',\n", " 'cards_yellow',\n", " 'cards_red'\n", "]" ] }, { "cell_type": "code", "execution_count": 9, "id": "4001f3f8", "metadata": {}, "outputs": [], "source": [ "features_abs_gk = [\n", " 'gk_games',\n", " 'gk_games_starts',\n", " 'gk_minutes',\n", " 'gk_goals_against_per90', \n", " 'gk_save_pct',\n", " 'gk_clean_sheets_pct',\n", " 'gk_psxg_net_per90',\n", " 'gk_passes_pct_launched',\n", " 'gk_pct_passes_launched',\n", " 'gk_passes_length_avg',\n", " 'gk_pct_goal_kicks_launched',\n", " 'gk_goal_kick_length_avg',\n", " 'gk_crosses_stopped_pct',\n", " 'gk_def_actions_outside_pen_area_per90',\n", " 'gk_avg_distance_def_actions',\n", " \n", " 'team_possession',\n", " 'team_goals_assists_per90',\n", " 'team_goals_pens_per90',\n", " 'team_goals_assists_pens_per90',\n", " 'team_xg_per90',\n", " 'team_gk_goals_against_per90',\n", " 'team_gk_save_pct',\n", " 'team_gk_clean_sheets_pct',\n", " 'team_passes_pct',\n", " 'team_passes_pct_medium',\n", " 'team_passes_pct_long',\n", " 'team_sca_per90',\n", " 'team_gca_per90',\n", " #'team_dribble_tackles_pct',\n", " 'team_aerials_won_pct',\n", " 'vs_team_possession',\n", " 'vs_team_goals_per90',\n", " 'vs_team_assists_per90',\n", " 'vs_team_xg_per90',\n", " 'vs_team_gk_save_pct',\n", " 'vs_team_gk_clean_sheets_pct',\n", " 'vs_team_gk_pct_passes_launched',\n", " 'vs_team_gk_crosses_stopped_pct',\n", " 'vs_team_shots_on_target_per90',\n", " 'vs_team_passes_pct',\n", " 'vs_team_passes_pct_short',\n", " 'vs_team_passes_pct_medium',\n", " 'vs_team_passes_pct_long',\n", " 'vs_team_sca_per90',\n", " 'vs_team_gca_per90',\n", " #'vs_team_dribble_tackles_pct',\n", " #'vs_team_dribbles_completed_pct',\n", " 'vs_team_aerials_won_pct',\n", " 'opp_team_possession',\n", " 'opp_team_goals_assists_per90',\n", " 'opp_team_goals_pens_per90',\n", " 'opp_team_goals_assists_pens_per90',\n", " 'opp_team_xg_per90',\n", " 'opp_team_gk_goals_against_per90',\n", " 'opp_team_gk_save_pct',\n", " 'opp_team_gk_clean_sheets_pct',\n", " 'opp_team_passes_pct',\n", " 'opp_team_passes_pct_medium',\n", " 'opp_team_passes_pct_long',\n", " 'opp_team_sca_per90',\n", " 'opp_team_gca_per90',\n", " #'opp_team_dribble_tackles_pct',\n", " 'opp_team_aerials_won_pct',\n", " 'opp_vs_team_possession',\n", " 'opp_vs_team_goals_per90',\n", " 'opp_vs_team_assists_per90',\n", " 'opp_vs_team_xg_per90',\n", " 'opp_vs_team_gk_save_pct',\n", " 'opp_vs_team_gk_clean_sheets_pct',\n", " 'opp_vs_team_gk_pct_passes_launched',\n", " 'opp_vs_team_gk_crosses_stopped_pct',\n", " 'opp_vs_team_shots_on_target_per90',\n", " 'opp_vs_team_passes_pct',\n", " 'opp_vs_team_passes_pct_short',\n", " 'opp_vs_team_passes_pct_medium',\n", " 'opp_vs_team_passes_pct_long',\n", " 'opp_vs_team_sca_per90',\n", " 'opp_vs_team_gca_per90',\n", " #'opp_vs_team_dribble_tackles_pct',\n", " #'opp_vs_team_dribbles_completed_pct',\n", " 'opp_vs_team_aerials_won_pct',\n", " \n", " 'vote_avg',\n", " 'vote_std']\n", "\n", "features_rel_gk = [\n", " 'gk_shots_on_target_against',\n", " 'gk_saves',\n", " 'gk_free_kick_goals_against',\n", " 'gk_corner_kick_goals_against',\n", " 'gk_own_goals_against',\n", " 'gk_psxg',\n", " 'gk_psnpxg_per_shot_on_target_against',\n", " 'gk_psxg_net',\n", " 'gk_passes_completed_launched',\n", " 'gk_passes_launched',\n", " 'gk_passes',\n", " 'gk_passes_throws',\n", " 'gk_goal_kicks',\n", " 'gk_crosses',\n", " 'gk_crosses_stopped',\n", "]" ] }, { "cell_type": "code", "execution_count": 10, "id": "f4017b2f", "metadata": {}, "outputs": [], "source": [ "DEL_G = False\n", "\n", "features_to_del = [\n", " 'goals',\n", " 'assists',\n", " 'xg',\n", " 'npxg'\n", "]\n", "\n", "def player_match_data(player, pteam, oppteam, oldseason = False):\n", " if(not(player in players.index)):\n", " return None\n", " \n", " if(oldseason):\n", " pdata = players_old.loc[[player]]\n", " else:\n", " pdata = players.loc[[player]]\n", " \n", " pteam_stats = team_data.loc[[pteam]].rename(index = {pteam : player})\n", " \n", " oppteam_stats = team_data.loc[[oppteam]].rename(index = {oppteam : player})\n", " \n", " oppteam_stats = oppteam_stats.rename(lambda x: 'opp_' + x, axis='columns')\n", " \n", " out = pd.concat([pdata, pteam_stats, oppteam_stats], axis = 1)\n", " \n", " return(out)\n", "\n", "def player_match_data_ext(player, pteam, oppteam, oldseason = False):\n", " pdata = player_match_data(player, pteam, oppteam, oldseason = oldseason)\n", " \n", " if(not isinstance(pdata, pd.DataFrame)):\n", " return None\n", " \n", " assert pdata['games'][0] > 0\n", " \n", " out = pd.concat([pdata[features_abs], pdata[features_rel]], axis = 1)\n", " \n", " out[features_rel] = out[features_rel] / max(pdata['minutes'][0], 1)\n", " \n", " out[features_rel_gamecorr] = out[features_rel_gamecorr] * (pdata['minutes'][0] / max(pdata['games'][0], 1) / 90)\n", " \n", " if(DEL_G):\n", " out[features_to_del] = 0\n", " \n", " return out\n", "\n", "def player_match_data_ext_gk(player, pteam, oppteam, oldseason = False):\n", " pdata = player_match_data(player, pteam, oppteam, oldseason = oldseason)\n", " \n", " if(not isinstance(pdata, pd.DataFrame)):\n", " return None\n", " \n", " if(pdata['gk_games'][0] <= 0):\n", " return None\n", " \n", " out = pd.concat([pdata[features_abs_gk], pdata[features_rel_gk]], axis = 1)\n", " \n", " out[features_rel_gk] = out[features_rel_gk] / max(pdata['minutes'][0], 1)\n", "\n", " return out\n", " " ] }, { "cell_type": "markdown", "id": "21fef3ae", "metadata": {}, "source": [ "Players stats rework:\n", "the current season stats are averaged (according to a calculated weight) with the past season data.\n", "In case a player doesn't have past season data, a config file (affine_players) can be used to load the data from an affine player (past season), e.g. Doig affine to Lazovic.\n", "In case, after this process, the player doesn't result in having a minimum amount of games, its stats are averaged with the average Serie A (defensive) player stat, depending on the games remaining to reach the minimum amount. This allows to use players who still haven't played a single game.\n", "\n", "These modified stats are used only for prediction, not for model traning.\n", "\n", "WEIGHT_0 = weight given to the current season in respect to the previous; if the player has a low amount of games this season, the weight is lowered\n", "min_games = minimum games so that the players stats are not averaged with the avg Serie A player stats" ] }, { "cell_type": "code", "execution_count": 11, "id": "6f8707b8", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " \n", "Averaging players stats with past seasons:\n", "Meret 1\n", "Provedel 1\n", "Vicario 1\n", "Szczesny 1\n", "Falcone 1\n", "Silvestri 1\n", "Rui Patricio 1\n", "Sepe 1\n", "Milinkovic-Savic V. 1\n", "Musso 1\n", "Maignan 0.7094551282051282\n", "Audero 1\n", "Montipo' 1\n", "Skorupski 1\n", "Consigli 1\n", "Dragowski 1\n", "Terracciano 1\n", "Tatarusanu 1\n", "Handanovic 0.7012375012375013\n", "Sportiello 1\n", "Perin 1\n", "Zoet 1\n", "Pegolo 1\n", "Mirante 0.0\n", "Ujkani 0.0\n", "Berisha 0.0\n", "Marchetti 0.0\n", "Padelli 0.0\n", "Bardi 0.0\n", "Cordaz 0.0\n", "Pinsoglio 0.0\n", "Fiorillo 0.0\n", "Cragno 0.0\n", "Sirigu 0.0\n", "Rossi F. 0.0\n", "Berardi A. 0.0\n", "Gemello 0.0\n", "Ravaglia 0.0\n", "Boer 0.0\n", "Adamonis 0.0\n", "Marfella 0.0\n", "Zovko 1\n", "Piana 0.0\n", "Dimarco 1\n", "Smalling 1\n", "Di Lorenzo 1\n", "Danilo 1\n", "Hernandez T. 0.9121565934065934\n", "Udogie 0.7876399790685507\n", "Parisi 1\n", "Mario Rui 0.8108058608058609\n", "Romagnoli 1\n", "Bastoni S. 0.6800307219662058\n", "Mazzocchi 1\n", "Tomori 0.9938910551813778\n", "Scalvini 1\n", "Toloi 1\n", "Demiral 0.9845499738356883\n", "Maehle 1\n", "Dumfries 0.8845154845154845\n", "Juan Jesus 0.5405372405372405\n", "Depaoli 1\n", "Mancini 1\n", "Ibanez 0.953889248006895\n", "Rodrigo Becao 0.6949764521193094\n", "Ebuehi 1\n", "Gosens 1\n", "Darmian 1\n", "Reca 1\n", "Bremer 0.9015984015984014\n", "Rrahmani 0.6879564879564879\n", "Vojvoda 0.8387646835922699\n", "Bastoni 0.8892709441096539\n", "Milenkovic 0.7631113984055161\n", "Kalulu 1\n", "Martinez Quarta 1\n", "Casale 0.6428062678062678\n", "Perez N. 1\n", "Izzo 1\n", "Luperto 1\n", "Skriniar 0.9266352694924124\n", "Rodriguez R. 0.8585003232062055\n", "Marusic 1\n", "Lazzari 0.8892709441096539\n", "Kyriakopoulos 0.056997600101048373\n", "Ampadu 0.911961601616774\n", "Ismajli 1\n", "Llorente D. affine to Ibanez\n", "Llorente D. 0.04769446240034476\n", "Cambiaso 1\n", "Hysaj 0.9505999747379058\n", "Biraghi 0.8765468765468765\n", "Medel 0.8353757353757354\n", "Bonucci 0.6081043956043956\n", "Calabria 0.8108058608058608\n", "Acerbi 0.7713675213675213\n", "Spinazzola 1\n", "Lykogiannis 0.9445316588173731\n", "Pellegrini Lu. 0.0\n", "Djidji 1\n", "Augello 0.9008954008954009\n", "Singo 0.6949764521193094\n", "Mari' 1\n", "De Vrij 0.7026984126984127\n", "Patric 0.6756715506715507\n", "Faraoni 0.40540293040293046\n", "Ceccherini 0.7154169360051713\n", "Hateboer 1\n", "Rogerio 1\n", "Aina 0.9266352694924122\n", "Ferrari G. 0.855850630850631\n", "Fazio 1\n", "Buongiorno 1\n", "Gunter 0.7162698412698413\n", "Troost-Ekong affine to Fazio\n", "Troost-Ekong 0.20270146520146523\n", "Soumaoro 0.8687205651491368\n", "Ceccaroni 0.0\n", "Soppy 0.5903322867608581\n", "Ferrari A. 0.359332696289218\n", "Zappacosta 0.23847231200172375\n", "Gyomber 0.7323407775020678\n", "Alex Sandro 0.9845499738356883\n", "Pezzella Giu. 0.7083987441130296\n", "Bereszynski 0.7083987441130298\n", "Venuti 0.6345437171524128\n", "Palomino 0.23847231200172375\n", "Nuytinck 0.36731786731786725\n", "Magnani 1\n", "Colley 0.8108058608058609\n", "Nikolaou 0.855850630850631\n", "Terzic 1\n", "Igor 0.8648595848595849\n", "Toljan 1\n", "Zortea 0.056997600101048373\n", "Dawidowicz 1\n", "Bellanova 0.5332033557840009\n", "Erlic 0.7713675213675213\n", "Ballo-Toure' affine to Calabria\n", "Ballo-Toure' 0.1871090448013525\n", "Stojanovic 0.8353757353757354\n", "Amian 0.7094551282051282\n", "Zima 0.7297252747252747\n", "De Winter 1\n", "Romagnoli S. 0.0\n", "Ghiglione 0.7628909551986474\n", "Rugani 0.4054029304029304\n", "De Sciglio 0.8108058608058608\n", "Djimsiti 0.47079049982275784\n", "Caldara 0.7464846980976013\n", "Karsdorp 0.4054029304029304\n", "Marchizza 0.34798534798534797\n", "Kjaer 1\n", "Ruggeri 1\n", "Zanoli 0.6887210012210012\n", "Radovanovic 1\n", "D'ambrosio 0.32432234432234436\n", "De Silvestri 0.47079049982275784\n", "Chiriches 0.455980800808387\n", "Murru 0.6633866133866133\n", "Bonifazi 0.5159673659673659\n", "Walukiewicz 0.9445316588173731\n", "Walukiewicz 0.36246197549180287\n", "Ranieri L. 0.12243928910595576\n", "Gabbia 1\n", "Kumbulla 0.38155569920275806\n", "Lovato 0.7231570512820512\n", "Tuia 0.18365893365893363\n", "Ferrer 0.12011938678605345\n", "Antov 1\n", "Vasquez 0.5903322867608581\n", "Ruan 1\n", "Ostigard 1\n", "Coppola D. 1\n", "Cacace 0.6486446886446887\n", "Conti 0.2316588173731031\n", "Conti 0.843001582405036\n", "Marrone 0.15742194313622884\n", "Tonelli 0.0\n", "Radu 1\n", "Florenzi 0.13513431013431015\n", "Sala 0.5405372405372405\n", "Fares 0.0\n", "Fares 0.0\n", "Romagna 0.0\n", "Romagna 0.0\n", "Muldur 0.05231005553586199\n", "Amey 0.0\n", "Zaccagni 1\n", "Milinkovic-Savic 0.8765468765468765\n", "Barella 0.9008954008954009\n", "Zielinski 0.972967032967033\n", "Luis Alberto 0.8585003232062055\n", "Felipe Anderson 0.8961538461538462\n", "Koopmeiners 1\n", "Calhanoglu 0.953889248006895\n", "Frattesi 0.945940170940171\n", "Diaz B. 0.9415809996455157\n", "Zambo Anguissa 1\n", "Elmas 0.8765468765468765\n", "Miranchuk 1\n", "Samardzic 1\n", "Pereyra 1\n", "Politano 0.9336552336552336\n", "Rabiot 0.8614812271062272\n", "Lazovic 0.8108058608058609\n", "Lobotka 1\n", "Bonaventura 0.9415809996455157\n", "Pessina 1\n", "Tonali 0.8108058608058608\n", "Pellegrini Lo. 1\n", "El Shaarawy 0.900895400895401\n", "Orsolini 1\n", "Ikone' 1\n", "Candreva 0.9182946682946682\n", "Bennacer 0.9938910551813778\n", "Pasalic 0.8327195327195327\n", "Mkhitaryan 0.9597660404112016\n", "Chiesa 0.8108058608058608\n", "Bandinelli 0.972967032967033\n", "Fagioli affine to Henderson L.\n", "Fagioli 0.512087912087912\n", "Messias 0.9355452240067625\n", "Arslan 1\n", "Ricci S. 1\n", "Verdi 1\n", "Sensi 1\n", "Barak 0.9689592017178223\n", "Soriano 0.9266352694924124\n", "Dominguez 1\n", "Brozovic 0.5096493982208269\n", "Cristante 1\n", "Saponara 0.9505999747379058\n", "Vecino 1\n", "Locatelli 0.9415809996455157\n", "Zaniolo 0.7528911564625851\n", "Maldini 1\n", "Marin 0.9182946682946682\n", "Zalewski 1\n", "Bajrami 0.04722658294086866\n", "Coulibaly L. 1\n", "De Roon 1\n", "Mandragora 1\n", "Bourabia 1\n", "Sottil 0.4729700854700855\n", "Aebischer 1\n", "Ederson D.s. 1\n", "Miretti 1\n", "Cataldi 0.9628319597069598\n", "Djuricic 1\n", "Linetty 1\n", "Haas 1\n", "Walace 0.945940170940171\n", "Agudelo 1\n", "Pobega 0.6010656010656009\n", "Nicolussi Caviglia 1\n", "Rovella 0.9445316588173729\n", "Amrabat 1\n", "Tameze 0.8534798534798534\n", "Gyasi 0.8108058608058608\n", "Ilic 0.5681948260073261\n", "Matheus Henrique 0.8432380952380952\n", "Harroui 0.9582251082251082\n", "Volpato 1\n", "Duncan 0.6388167388167388\n", "Cuadrado 0.7862359862359862\n", "Ekdal 0.8900394477317554\n", "Schouten 1\n", "Obiang 1\n", "Kovalenko 0.6236968160045083\n", "Crnigoj 0.09723120017237664\n", "Basic 0.7828470380194518\n", "Asllani 0.8623984710941232\n", "Sabiri 1\n", "Grassi 0.6060744810744811\n", "Krunic 0.5791470434327577\n", "Rincon 1\n", "Miguel Veloso 1\n", "Henderson L. 0.6401098901098902\n", "Lopez M. 0.6486446886446886\n", "Cuisance 0.12714849253310792\n", "Saelemaekers 0.5855820105820106\n", "Maggiore 0.4722658294086865\n", "Akpa Akpro 0.0\n", "Akpa Akpro 0.0\n", "Maleh 0.29516614338042907\n", "Romero L. 1\n", "Ceide 1\n", "Benassi 0.4132326007326007\n", "Gagliardini 0.9008954008954009\n", "Vieira 0.11806645735217164\n", "Bianco 1\n", "Galdames 0.0\n", "Kastanos 0.7207163207163206\n", "Vignato 0.20661630036630035\n", "Askildsen 1\n", "Bove 1\n", "Bohinen 1\n", "Bakayoko 0.0\n", "Zurkowski 0.04722658294086866\n", "Castrovilli 0.2115145723841376\n", "Demme 0.256043956043956\n", "Darboe 0.0\n", "Darboe 0.32432234432234436\n", "Urbanski 0.0\n", "Yepes 1\n", "Osimhen 1\n", "Martinez L. 0.972967032967033\n", "Dybala 0.8549640015157256\n", "Rafael Leao 0.953889248006895\n", "Immobile 0.8369608885737918\n", "Vlahovic 1\n", "Arnautovic 0.6879564879564879\n", "Dzeko 0.945940170940171\n", "Nzola 1\n", "Beto 1\n", "Giroud 1\n", "Abraham 0.9203742203742203\n", "Deulofeu 0.7631113984055161\n", "Simeone 0.5667189952904238\n", "Lozano 1\n", "Correa 1\n", "Berardi 0.6388167388167388\n", "Pedro 0.9628319597069598\n", "Sanabria 0.8946823291650877\n", "Thauvin affine to Deulofeu\n", "Thauvin 0.04769446240034476\n", "Cabral 1\n", "Caprari 0.9917582417582418\n", "Piatek 1\n", "Rebic 0.878373015873016\n", "Bonazzoli 0.9628319597069598\n", "Zapata D. 0.945940170940171\n", "Gonzalez N. 0.5405372405372406\n", "Brekalo 0.051654075091575095\n", "Kean 0.9628319597069598\n", "Okereke 1\n", "Muriel 0.7807760141093475\n", "Pinamonti 0.7805504680504681\n", "Di Francesco F. 1\n", "Caputo 0.27548840048840045\n", "Boga 1\n", "Alvarez A. affine to Raspadori\n", "Alvarez A. 0.7207163207163207\n", "Petagna 1\n", "Barrow 0.7154169360051713\n", "Djuric 1\n", "Henry 0.8014208014208013\n", "Success 1\n", "Gabbiadini 1\n", "Kallon 1\n", "Nestorovski 1\n", "Raspadori 0.6428062678062678\n", "Lasagna 0.9845499738356883\n", "Belotti 1\n", "Pellegri 1\n", "Verde 0.5405372405372406\n", "Destro 0.6121964455297788\n", "Seck 1\n", "Sansone 0.6005969339302673\n", "Quagliarella 0.7370962370962372\n", "Defrel 0.4267399267399267\n", "Pjaca 0.6887210012210012\n", "Gaich 0.11019536019536019\n", "Piccoli 0.3305860805860806\n", "Piccoli 0.30394544405533425\n", "Shomurodov 0.05903322867608582\n", "Afena-Gyan 1\n", "Ibrahimovic 0.0\n", "Pussetto 0.29516614338042907\n", "Cancellieri 1\n", "Oddei 0.0\n", "Oddei 0.6486446886446887\n", "Braaf 0.41323260073260076\n", "Raimondo 0.0\n", "Kaio Jorge 0.0\n", "Players with low quantity of games:\n", "Gravillon 0.0\n", "Masina 0.6666666666666667\n", "Aiwu 0.0\n", "Thiaw 0.8333333333333334\n", "Zeefuik 0.0\n", "Wisniewski 0.16666666666666663\n", "Dermaku 0.16666666666666663\n", "Donati 0.6666666666666667\n", "Antov 0.6666666666666667\n", "Ostigard 0.6666666666666667\n", "Gila 0.6666666666666667\n", "Bayeye 0.16666666666666663\n", "Moutinho J. 0.6666666666666667\n", "Paletta 0.0\n", "Romagna 0.0\n", "Cassandro 0.0\n", "Amey 0.16666666666666663\n", "Zanotti 0.0\n", "Ebosele 0.8333333333333334\n", "Buta 0.0\n", "Abankwah 0.0\n", "Guessand A. 0.0\n", "Cabal 0.5\n", "Sosa 0.8333333333333334\n", "Guarino 0.0\n", "Carboni F. 0.6666666666666667\n", "Pogba 0.0\n", "Duda 0.33333333333333337\n", "Wijnaldum 0.16666666666666663\n", "Nicolussi Caviglia 0.8333333333333334\n", "Volpato 0.8333333333333334\n", "Machin 0.0\n", "Esposito Sa. 0.5\n", "Akpa Akpro 0.0\n", "Romero L. 0.8333333333333334\n", "Bianco 0.5\n", "Galdames 0.0\n", "Tahirovic 0.8333333333333334\n", "Abildgaard 0.16666666666666663\n", "Winks 0.6666666666666667\n", "D'andrea 0.8333333333333334\n", "Cipot 0.33333333333333337\n", "Gaetano 0.5\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Darboe 0.6171184371184371\n", "Urbanski 0.16666666666666663\n", "Bertini 0.0\n", "Yepes 0.8333333333333334\n", "Pyyhtia 0.5\n", "Trimboli 0.0\n", "Pafundi 0.16666666666666663\n", "Adli 0.6666666666666667\n", "Vignato S. 0.5\n", "Samek 0.0\n", "Zerbin 0.6666666666666667\n", "Ilkhan 0.6666666666666667\n", "Degli Innocenti 0.16666666666666663\n", "Acella 0.0\n", "Carboni V. 0.33333333333333337\n", "Paoletti 0.6666666666666667\n", "Malagrida 0.16666666666666663\n", "Faticanti 0.0\n", "Solbakken 0.33333333333333337\n", "Ngonge 0.33333333333333337\n", "Oddei 0.5090109890109888\n", "Braaf 0.4600503663003662\n", "Raimondo 0.16666666666666663\n", "De Luca 0.16666666666666663\n", "Voelkerling Persson 0.5\n", "Krollis 0.16666666666666663\n", "Vivaldo 0.0\n" ] } ], "source": [ "#for i in range(players.columns.shape[0]):\n", "# print(str(i) + ' - ' + players.columns[i])\n", "\n", "cols_toadapt = players.columns[9:]\n", "\n", "players = players_orig.copy()\n", "\n", "min_games = 6\n", "\n", "current_season_games = max(players_orig['games'])\n", "\n", "# weight_0 as function of current_season_games --> 1 as match day reachs 30 ? \n", "WEIGHT_0_same_team = (1 - (1 - 0.7) * (30 - current_season_games) / (38 - 12)) # 0.7\n", "WEIGHT_0_different_team = (1 - (1 - 0.75) * (30 - current_season_games) / (38 - 12)) # 0.75\n", "WEIGHT_mul_gk = 2\n", "\n", "rcsv = pd.read_csv('config/affine_players.txt') \n", "affine_players = pd.DataFrame(rcsv)\n", "affine_players = affine_players.set_index('player')\n", "\n", "\n", "def calc_weight(games_curr, games_old, same_team = 1, maxgames = current_season_games):\n", " if(same_team):\n", " weight_0 = WEIGHT_0_same_team\n", " else:\n", " weight_0 = WEIGHT_0_different_team\n", "\n", " weight = weight_0 * (games_curr / maxgames) / (max(games_old, 1) / 38)\n", " weight = min(weight, 1)\n", "\n", " return abs(weight)\n", "\n", "print(' ')\n", "print('Averaging players stats with past seasons:')\n", "\n", "for i in range(players.shape[0]):\n", " p = players.index[i]\n", " \n", "\n", " if(p in players_old.index or p in affine_players.index):\n", " p_ = p\n", " affine = 0\n", " \n", " if(p in affine_players.index):\n", " affine = 1\n", " p_ = affine_players.loc[p]['alike']\n", " \n", " print(p + ' affine to ' + p_)\n", " \n", " if(players.loc[p]['r'] == 'P'):\n", " weight = calc_weight(players.loc[p]['gk_games'], players_old.loc[p_]['gk_games'], affine == 1 or players.loc[p]['team'] == players_old.loc[p]['team'])\n", " weight *= WEIGHT_mul_gk\n", " weight = min(weight, 1)\n", " else:\n", " weight = calc_weight(players.loc[p]['games'], players_old.loc[p_]['games'], affine == 1 or players.loc[p]['team'] == players_old.loc[p]['team'])\n", "\n", " players.at[p, cols_toadapt] = (players.loc[p][cols_toadapt] * weight + (1-weight) * players_old.loc[p_][cols_toadapt])\n", " \n", " print(p + ' ' + str(weight)) \n", " \n", " # to handle players like Lukaku, who only played 2 seasons ago; only outfield players\n", " if(players.loc[p]['r'] != 'P' and players.loc[p]['games'] < min_games and p in players_old_2.index): \n", " weight = calc_weight(players.loc[p]['games'], players_old_2.loc[p]['games'], players.loc[p]['team'] == players_old_2.loc[p]['team'])\n", " \n", " players.at[p, cols_toadapt] = (players.loc[p][cols_toadapt] * weight + (1-weight) * players_old_2.loc[p][cols_toadapt])\n", " \n", " print(p + ' ' + str(weight))\n", " \n", " \n", "# handle players with low quantitites of games\n", "\n", "print('Players with low quantity of games:')\n", "\n", "def calc_weight_low(current_games, min_games = min_games):\n", " weight = 1 - (min_games - current_games)/min_games\n", " \n", " weight = min(weight, 1)\n", "\n", " return abs(weight)\n", "\n", "#mean_players_stats = players_orig[players_orig['games'] >= min_games][cols_toadapt].mean()\n", "\n", "mean_players_stats = players_orig.loc[players_orig.index[0]][cols_toadapt] * 0\n", "count = 0\n", "\n", "for i in range(players_orig.shape[0]):\n", " if(players_orig['games'][i] >= min_games and (players_orig['r'][i] == 'D')): # counting only defenders, to add a penalty\n", " mean_players_stats += players_orig.loc[players_orig.index[i]][cols_toadapt]\n", " count = count + 1\n", " \n", "mean_players_stats /= count\n", "\n", "for i in range(players.shape[0]):\n", " p = players.index[i]\n", " \n", " if(players.loc[p]['games'] < min_games and players.loc[p]['r'] != 'P'):\n", " weight = calc_weight_low(players.loc[p]['games'])\n", " \n", " players.at[p, cols_toadapt] = players.loc[p][cols_toadapt] * weight + (1-weight) * mean_players_stats\n", " \n", " print(p + ' ' + str(weight))\n", " \n", " \n", "players_out = players.copy()\n", "players_out = players_out.set_index(players_out.columns[0])\n", "players_out.insert(2, 'name', players_out.index)\n", "players_out.to_excel('mid_outputs/players_stats_rwk.xlsx')\n" ] }, { "cell_type": "code", "execution_count": 12, "id": "49c28b07", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Index(['games', 'games_starts', 'minutes', 'goals', 'assists', 'pens_made',\n", " 'pens_att', 'cards_yellow', 'cards_red', 'goals_per90',\n", " ...\n", " 'gk_pct_goal_kicks_launched', 'gk_goal_kick_length_avg', 'gk_crosses',\n", " 'gk_crosses_stopped', 'gk_crosses_stopped_pct',\n", " 'gk_def_actions_outside_pen_area',\n", " 'gk_def_actions_outside_pen_area_per90', 'gk_avg_distance_def_actions',\n", " 'vote_avg', 'vote_std'],\n", " dtype='object', length=151)" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "players.columns[9:]" ] }, { "cell_type": "code", "execution_count": 13, "id": "d29102e5", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0 - matchday\n", "1 - player\n", "2 - team\n", "3 - oppteam\n", "4 - home\n", "5 - vote\n", "6 - goals\n", "7 - assists\n", "8 - cards_malus\n", "9 - fantavote\n", "10 - r\n", "11 - games\n", "12 - games_starts\n", "13 - minutes\n", "14 - shots_on_target_pct\n", "15 - goals_per_shot\n", "16 - goals_per_shot_on_target\n", "17 - passes_pct\n", "18 - aerials_won_pct\n", "19 - team_possession\n", "20 - team_goals_assists_per90\n", "21 - team_goals_pens_per90\n", "22 - team_goals_assists_pens_per90\n", "23 - team_xg_per90\n", "24 - team_gk_goals_against_per90\n", "25 - team_gk_save_pct\n", "26 - team_gk_clean_sheets_pct\n", "27 - team_passes_pct\n", "28 - team_passes_pct_medium\n", "29 - team_passes_pct_long\n", "30 - team_sca_per90\n", "31 - team_gca_per90\n", "32 - team_aerials_won_pct\n", "33 - vs_team_possession\n", "34 - vs_team_goals_per90\n", "35 - vs_team_assists_per90\n", "36 - vs_team_xg_per90\n", "37 - vs_team_gk_save_pct\n", "38 - vs_team_gk_clean_sheets_pct\n", "39 - vs_team_gk_pct_passes_launched\n", "40 - vs_team_gk_crosses_stopped_pct\n", "41 - vs_team_shots_on_target_per90\n", "42 - vs_team_passes_pct\n", "43 - vs_team_passes_pct_short\n", "44 - vs_team_passes_pct_medium\n", "45 - vs_team_passes_pct_long\n", "46 - vs_team_sca_per90\n", "47 - vs_team_gca_per90\n", "48 - vs_team_aerials_won_pct\n", "49 - opp_team_possession\n", "50 - opp_team_goals_assists_per90\n", "51 - opp_team_goals_pens_per90\n", "52 - opp_team_goals_assists_pens_per90\n", "53 - opp_team_xg_per90\n", "54 - opp_team_gk_goals_against_per90\n", "55 - opp_team_gk_save_pct\n", "56 - opp_team_gk_clean_sheets_pct\n", "57 - opp_team_passes_pct\n", "58 - opp_team_passes_pct_medium\n", "59 - opp_team_passes_pct_long\n", "60 - opp_team_sca_per90\n", "61 - opp_team_gca_per90\n", "62 - opp_team_aerials_won_pct\n", "63 - opp_vs_team_possession\n", "64 - opp_vs_team_goals_per90\n", "65 - opp_vs_team_assists_per90\n", "66 - opp_vs_team_xg_per90\n", "67 - opp_vs_team_gk_save_pct\n", "68 - opp_vs_team_gk_clean_sheets_pct\n", "69 - opp_vs_team_gk_pct_passes_launched\n", "70 - opp_vs_team_gk_crosses_stopped_pct\n", "71 - opp_vs_team_shots_on_target_per90\n", "72 - opp_vs_team_passes_pct\n", "73 - opp_vs_team_passes_pct_short\n", "74 - opp_vs_team_passes_pct_medium\n", "75 - opp_vs_team_passes_pct_long\n", "76 - opp_vs_team_sca_per90\n", "77 - opp_vs_team_gca_per90\n", "78 - opp_vs_team_aerials_won_pct\n", "79 - vote_avg\n", "80 - vote_std\n", "81 - goals.1\n", "82 - assists.1\n", "83 - cards_yellow\n", "84 - cards_red\n", "85 - xg\n", "86 - npxg\n", "87 - shots_on_target\n", "88 - passes_completed\n", "89 - passes_into_final_third\n", "90 - passes_into_penalty_area\n", "91 - progressive_passes\n", "92 - passes_live\n", "93 - passes_dead\n", "94 - through_balls\n", "95 - passes_switches\n", "96 - crosses\n", "97 - corner_kicks\n", "98 - blocks\n", "99 - blocked_shots\n", "100 - blocked_passes\n", "101 - interceptions\n", "102 - clearances\n", "103 - errors\n", "104 - touches\n", "105 - touches_def_pen_area\n", "106 - touches_def_3rd\n", "107 - touches_mid_3rd\n", "108 - touches_att_3rd\n", "109 - touches_att_pen_area\n", "110 - touches_live_ball\n", "111 - passes_received\n", "112 - miscontrols\n", "113 - dispossessed\n", "114 - fouls\n", "115 - fouled\n", "116 - aerials_won\n", "117 - aerials_lost\n", "118 - carries\n", "119 - progressive_carries\n", "120 - carries_into_final_third\n", "121 - carries_into_penalty_area\n" ] } ], "source": [ "for i in range(db.columns.shape[0]):\n", " print(str(i) + \" - \" + str(db.columns[i]))" ] }, { "cell_type": "markdown", "id": "089690d6", "metadata": {}, "source": [ "Elaborate databases data to have X and y for training, and split into a train test and a validation test.\n", "\n", "For outfield players: X -> y = [vote, fantavote]\n", "\n", "For goalkeepers: X -> y = [vote, fantavote, clean sheet probability]" ] }, { "cell_type": "code", "execution_count": 14, "id": "f19304f6", "metadata": {}, "outputs": [], "source": [ "npdb = np.array(db)\n", "\n", "y = npdb[:, [5,9]] # vote, fantavote\n", "\n", "#y[:, 1] = y[:, 1] - y[:, 0] # target = difference between fantavote and vote\n", "\n", "f_start = 14\n", "\n", "X = npdb[:, f_start:]\n", "\n", "if(DEL_G): \n", " del_g_idx = [\n", " list(db.columns).index('goals.1') - f_start,\n", " list(db.columns).index('assists.1') - f_start,\n", " list(db.columns).index('xg') - f_start,\n", " list(db.columns).index('npxg') - f_start,\n", " list(db.columns).index('shots_on_target') - f_start]\n", " \n", " X[:, del_g_idx] = 0\n", "\n", "\n", "# add role and home factor\n", "toadd = np.zeros((X.shape[0], 4))\n", "toadd[:, 0] = npdb[:, 4] # home\n", "\n", "toadd[:, 1] = npdb[:, 10] == 'D'\n", "toadd[:, 2] = npdb[:, 10] == 'C'\n", "toadd[:, 3] = npdb[:, 10] == 'A'\n", "\n", "X = np.concatenate((X, toadd), axis = 1)\n", "\n" ] }, { "cell_type": "code", "execution_count": 15, "id": "370d41d2", "metadata": {}, "outputs": [], "source": [ "scaler = StandardScaler()\n", "scaler.fit(X)\n", "\n", "X_train_, X_test_, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 12)\n", "\n", "X_train = scaler.transform(X_train_)\n", "X_test = scaler.transform(X_test_)" ] }, { "cell_type": "code", "execution_count": 16, "id": "a7b1fb52", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0 - matchday\n", "1 - player\n", "2 - team\n", "3 - oppteam\n", "4 - home\n", "5 - vote\n", "6 - goals\n", "7 - assists\n", "8 - cards_malus\n", "9 - fantavote\n", "10 - gk_games\n", "11 - gk_games_starts\n", "12 - gk_minutes\n", "13 - gk_goals_against_per90\n", "14 - gk_save_pct\n", "15 - gk_clean_sheets_pct\n", "16 - gk_psxg_net_per90\n", "17 - gk_passes_pct_launched\n", "18 - gk_pct_passes_launched\n", "19 - gk_passes_length_avg\n", "20 - gk_pct_goal_kicks_launched\n", "21 - gk_goal_kick_length_avg\n", "22 - gk_crosses_stopped_pct\n", "23 - gk_def_actions_outside_pen_area_per90\n", "24 - gk_avg_distance_def_actions\n", "25 - team_possession\n", "26 - team_goals_assists_per90\n", "27 - team_goals_pens_per90\n", "28 - team_goals_assists_pens_per90\n", "29 - team_xg_per90\n", "30 - team_gk_goals_against_per90\n", "31 - team_gk_save_pct\n", "32 - team_gk_clean_sheets_pct\n", "33 - team_passes_pct\n", "34 - team_passes_pct_medium\n", "35 - team_passes_pct_long\n", "36 - team_sca_per90\n", "37 - team_gca_per90\n", "38 - team_aerials_won_pct\n", "39 - vs_team_possession\n", "40 - vs_team_goals_per90\n", "41 - vs_team_assists_per90\n", "42 - vs_team_xg_per90\n", "43 - vs_team_gk_save_pct\n", "44 - vs_team_gk_clean_sheets_pct\n", "45 - vs_team_gk_pct_passes_launched\n", "46 - vs_team_gk_crosses_stopped_pct\n", "47 - vs_team_shots_on_target_per90\n", "48 - vs_team_passes_pct\n", "49 - vs_team_passes_pct_short\n", "50 - vs_team_passes_pct_medium\n", "51 - vs_team_passes_pct_long\n", "52 - vs_team_sca_per90\n", "53 - vs_team_gca_per90\n", "54 - vs_team_aerials_won_pct\n", "55 - opp_team_possession\n", "56 - opp_team_goals_assists_per90\n", "57 - opp_team_goals_pens_per90\n", "58 - opp_team_goals_assists_pens_per90\n", "59 - opp_team_xg_per90\n", "60 - opp_team_gk_goals_against_per90\n", "61 - opp_team_gk_save_pct\n", "62 - opp_team_gk_clean_sheets_pct\n", "63 - opp_team_passes_pct\n", "64 - opp_team_passes_pct_medium\n", "65 - opp_team_passes_pct_long\n", "66 - opp_team_sca_per90\n", "67 - opp_team_gca_per90\n", "68 - opp_team_aerials_won_pct\n", "69 - opp_vs_team_possession\n", "70 - opp_vs_team_goals_per90\n", "71 - opp_vs_team_assists_per90\n", "72 - opp_vs_team_xg_per90\n", "73 - opp_vs_team_gk_save_pct\n", "74 - opp_vs_team_gk_clean_sheets_pct\n", "75 - opp_vs_team_gk_pct_passes_launched\n", "76 - opp_vs_team_gk_crosses_stopped_pct\n", "77 - opp_vs_team_shots_on_target_per90\n", "78 - opp_vs_team_passes_pct\n", "79 - opp_vs_team_passes_pct_short\n", "80 - opp_vs_team_passes_pct_medium\n", "81 - opp_vs_team_passes_pct_long\n", "82 - opp_vs_team_sca_per90\n", "83 - opp_vs_team_gca_per90\n", "84 - opp_vs_team_aerials_won_pct\n", "85 - vote_avg\n", "86 - vote_std\n", "87 - gk_shots_on_target_against\n", "88 - gk_saves\n", "89 - gk_free_kick_goals_against\n", "90 - gk_corner_kick_goals_against\n", "91 - gk_own_goals_against\n", "92 - gk_psxg\n", "93 - gk_psnpxg_per_shot_on_target_against\n", "94 - gk_psxg_net\n", "95 - gk_passes_completed_launched\n", "96 - gk_passes_launched\n", "97 - gk_passes\n", "98 - gk_passes_throws\n", "99 - gk_goal_kicks\n", "100 - gk_crosses\n", "101 - gk_crosses_stopped\n" ] } ], "source": [ "for i in range(db_gk.columns.shape[0]):\n", " print(str(i) + \" - \" + str(db_gk.columns[i]))" ] }, { "cell_type": "code", "execution_count": 17, "id": "5a7cf079", "metadata": {}, "outputs": [], "source": [ "npdb_gk= np.array(db_gk)\n", "\n", "y_gk = npdb_gk[:, [5,9,6]] # vote, fantavote, goals == 0 (clean sheet)\n", "y_gk[:, 2] = (y_gk[:, 2] == 0) * 1\n", "\n", "f_start_gk = 13\n", "\n", "X_gk = npdb_gk[:, f_start_gk:]\n", "\n", "# add home factor\n", "toadd_gk = np.zeros((X_gk.shape[0], 1))\n", "toadd_gk[:, 0] = npdb_gk[:, 4] # home\n", "\n", "X_gk = np.concatenate((X_gk, toadd_gk), axis = 1)\n", "\n" ] }, { "cell_type": "code", "execution_count": 18, "id": "0bc0568b", "metadata": {}, "outputs": [], "source": [ "scaler_gk = StandardScaler()\n", "scaler_gk.fit(X_gk)\n", "\n", "X_gk_train_, X_gk_test_, y_gk_train, y_gk_test = train_test_split(X_gk, y_gk, test_size = 0.2, random_state = 18)\n", "\n", "X_gk_train = scaler_gk.transform(X_gk_train_)\n", "X_gk_test = scaler_gk.transform(X_gk_test_)" ] }, { "cell_type": "markdown", "id": "ebd27493", "metadata": {}, "source": [ "MLP Regressor , to see performance of a simple neural network" ] }, { "cell_type": "code", "execution_count": 17, "id": "04564bee", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0.1569906306642661\n", "0.19152381866355805\n" ] }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "0.1532751047011487\n", "0.17630547391900842\n" ] }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "regr = MLPRegressor(max_iter = 400000, solver = 'lbfgs', hidden_layer_sizes = (8, 8), alpha = 500, verbose = True)\n", "\n", "regr.fit(X_train, y_train)\n", "\n", "\n", "y_train_predict = regr.predict(X_train)\n", "\n", "plt.plot([0, 20], [0, 20])\n", "\n", "plt.scatter(y_train[:, 0], y_train_predict[:, 0], color = 'orange', edgecolors = 'black', s = 20)\n", "plt.scatter(y_train[:, 1], y_train_predict[:, 1], color = 'green', edgecolors = 'black', s = 20)\n", "\n", "print(r2_score(y_train[:, 0], y_train_predict[:, 0]))\n", "print(r2_score(y_train[:, 1], y_train_predict[:, 1]))\n", "\n", "\n", "plt.show()\n", "\n", "y_test_predict = regr.predict(X_test)\n", "\n", "plt.plot([0, 20], [0, 20])\n", "\n", "plt.scatter(y_test[:, 0], y_test_predict[:, 0], color = 'orange', edgecolors = 'black', s = 20)\n", "plt.scatter(y_test[:, 1], y_test_predict[:, 1], color = 'green', edgecolors = 'black', s = 20)\n", "\n", "print(r2_score(y_test[:, 0], y_test_predict[:, 0]))\n", "print(r2_score(y_test[:, 1], y_test_predict[:, 1]))\n", "\n", "\n", "plt.show()" ] }, { "cell_type": "markdown", "id": "f9513b25", "metadata": {}, "source": [ "Train neural network for outfield players.\n", "\n", "The outputs of the NN are probability distribution of SinhArcsinh type (a skewed distribution, which is a generalization of Gaussian)" ] }, { "cell_type": "code", "execution_count": 19, "id": "8aad9652", "metadata": {}, "outputs": [], "source": [ "load_model_of = True# load scaler and model weights for outfield player predictor\n", "refit_model_of = True\n", "\n", "if(load_model_of):\n", " scaler = pickle.load(open('saves/scaler.pkl', 'rb'))\n", " \n", " X_train = scaler.transform(X_train_)\n", " X_test = scaler.transform(X_test_)\n", "\n", "\n", "n_epochs = 1000\n", "\n", "n_samples = X_train.shape[0]\n", "\n", "batch_size = 256\n", "\n", "X_len = X_train.shape[1]\n", "y_len = y_train.shape[1]\n", "\n", "\n", "#tailweight_param = 1.1\n", "\n", "tailweight_min = 0.5\n", "tailweight_range = 1.2\n", "\n", "\n", "callback = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience = 10)\n", "neg_log_likelihood = lambda x, rv_x: -rv_x.log_prob(x)\n", "\n", "\n", "inputs = tfk.layers.Input(shape=(X_len,), name=\"input\")\n", "x = tfk.layers.Dropout(0.2)(inputs)\n", "x = tfk.layers.Dense(16, activation=\"relu\") (x)\n", "x = tfk.layers.Dropout(0.2)(x)\n", "x = tfk.layers.Dense(16, activation=\"relu\") (x)\n", "\n", "\n", "prob_dist_params = 4\n", "\n", "def prob_dist(t): \n", " return tfp.distributions.SinhArcsinh(loc=t[..., 0], scale=1e-3 + tf.math.softplus(t[..., 1]), skewness = t[..., 2], \n", " tailweight = tailweight_min + tailweight_range * tf.math.sigmoid(t[..., 3]),\n", " allow_nan_stats = False)\n", "\n", "x1 = tfk.layers.Dense(8, activation=\"sigmoid\")(x)\n", "x1 = tfk.layers.Dense(prob_dist_params, activation=\"linear\")(x1)\n", "out_1 = tfp.layers.DistributionLambda(prob_dist)(x1)\n", "\n", "x2 = tfk.layers.Dense(8, activation=\"sigmoid\")(x)\n", "x2 = tfk.layers.Dense(prob_dist_params, activation=\"linear\")(x2)\n", "out_2 = tfp.layers.DistributionLambda(prob_dist)(x2)\n", "\n", "\n", "modelb = tf.keras.Model(inputs, [out_1, out_2])\n", "\n", "modelb.compile(optimizer=tf.keras.optimizers.Nadam(learning_rate = 0.001), \n", " loss=neg_log_likelihood)\n", "\n", "if(load_model_of):\n", " modelb.load_weights('saves/modelb')\n", " \n", "if( (not load_model_of) or refit_model_of):\n", " modelb.fit(X_train.astype('float32'), [y_train[:, 0].astype('float32'), y_train[:, 1].astype('float32')], \n", " validation_data = (X_test.astype('float32'), [y_test[:, 0].astype('float32'), y_test[:, 1].astype('float32')]),\n", " batch_size = batch_size, shuffle = True, epochs=n_epochs, verbose=True, callbacks = [callback])" ] }, { "cell_type": "code", "execution_count": 55, "id": "4e2bf9dc", "metadata": {}, "outputs": [], "source": [ "def sample_predict(X, iterations = 100):\n", " y = np.zeros((2, X.shape[0]))\n", " \n", " dist = modelb(X)\n", " \n", " for i in range(iterations):\n", " y[0, :] += dist[0].sample()\n", " y[1, :] += dist[1].sample()\n", " \n", " return y.transpose() / iterations\n", " " ] }, { "cell_type": "code", "execution_count": 56, "id": "c2674211", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0.14539483185579238\n", "0.16229047232752447\n" ] }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "0.13160209075894191\n", "0.16563346611529572\n" ] }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "y_train_predict = sample_predict(X_train)\n", "\n", "plt.plot([0, 20], [0, 20])\n", "\n", "plt.scatter(y_train[:, 0], y_train_predict[:, 0], color = 'orange', edgecolors = 'black', s = 20)\n", "plt.scatter(y_train[:, 1], y_train_predict[:, 1], color = 'green', edgecolors = 'black', s = 20)\n", "\n", "print(r2_score(y_train[:, 0], y_train_predict[:, 0]))\n", "print(r2_score(y_train[:, 1], y_train_predict[:, 1]))\n", "\n", "plt.show()\n", "\n", "y_test_predict = sample_predict(X_test)\n", "\n", "plt.plot([0, 20], [0, 20])\n", "\n", "plt.scatter(y_test[:, 0], y_test_predict[:, 0], color = 'orange', edgecolors = 'black', s = 20)\n", "plt.scatter(y_test[:, 1], y_test_predict[:, 1], color = 'green', edgecolors = 'black', s = 20)\n", "\n", "print(r2_score(y_test[:, 0], y_test_predict[:, 0]))\n", "print(r2_score(y_test[:, 1], y_test_predict[:, 1]))\n", "\n", "\n" ] }, { "cell_type": "markdown", "id": "f574ffdb", "metadata": {}, "source": [ "Train neural network for goalkeepers.\n", "\n", "For clean sheet probability prediction, a Bernoulli distribution is used." ] }, { "cell_type": "code", "execution_count": 54, "id": "41e7e1ee", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Epoch 1/2500\n", "8/8 [==============================] - 4s 92ms/step - loss: 363.3525 - distribution_lambda_26_loss: 106.5460 - distribution_lambda_27_loss: 255.9949 - distribution_lambda_28_loss: 0.8116 - val_loss: 255.7005 - val_distribution_lambda_26_loss: 95.0135 - val_distribution_lambda_27_loss: 159.8931 - val_distribution_lambda_28_loss: 0.7939\n", "Epoch 2/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 242.5359 - distribution_lambda_26_loss: 90.2925 - distribution_lambda_27_loss: 151.4580 - distribution_lambda_28_loss: 0.7854 - val_loss: 181.1897 - val_distribution_lambda_26_loss: 80.4324 - val_distribution_lambda_27_loss: 99.9920 - val_distribution_lambda_28_loss: 0.7654\n", "Epoch 3/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 172.7781 - distribution_lambda_26_loss: 75.9389 - distribution_lambda_27_loss: 96.0833 - distribution_lambda_28_loss: 0.7559 - val_loss: 137.6391 - val_distribution_lambda_26_loss: 68.3221 - val_distribution_lambda_27_loss: 68.5772 - val_distribution_lambda_28_loss: 0.7398\n", "Epoch 4/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 134.3410 - distribution_lambda_26_loss: 64.5182 - distribution_lambda_27_loss: 69.0890 - distribution_lambda_28_loss: 0.7337 - val_loss: 109.9033 - val_distribution_lambda_26_loss: 58.6612 - val_distribution_lambda_27_loss: 50.5242 - val_distribution_lambda_28_loss: 0.7179\n", "Epoch 5/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 107.2862 - distribution_lambda_26_loss: 55.5948 - distribution_lambda_27_loss: 50.9793 - distribution_lambda_28_loss: 0.7121 - val_loss: 90.9552 - val_distribution_lambda_26_loss: 50.7684 - val_distribution_lambda_27_loss: 39.4882 - val_distribution_lambda_28_loss: 0.6985\n", "Epoch 6/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 89.6161 - distribution_lambda_26_loss: 48.2157 - distribution_lambda_27_loss: 40.7019 - distribution_lambda_28_loss: 0.6985 - val_loss: 77.0989 - val_distribution_lambda_26_loss: 44.2830 - val_distribution_lambda_27_loss: 32.1339 - val_distribution_lambda_28_loss: 0.6820\n", "Epoch 7/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 76.6649 - distribution_lambda_26_loss: 42.5049 - distribution_lambda_27_loss: 33.4795 - distribution_lambda_28_loss: 0.6805 - val_loss: 66.2563 - val_distribution_lambda_26_loss: 38.8386 - val_distribution_lambda_27_loss: 26.7498 - val_distribution_lambda_28_loss: 0.6679\n", "Epoch 8/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 65.1514 - distribution_lambda_26_loss: 36.9772 - distribution_lambda_27_loss: 27.5046 - distribution_lambda_28_loss: 0.6695 - val_loss: 57.5291 - val_distribution_lambda_26_loss: 34.2010 - val_distribution_lambda_27_loss: 22.6720 - val_distribution_lambda_28_loss: 0.6561\n", "Epoch 9/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 57.1919 - distribution_lambda_26_loss: 33.0281 - distribution_lambda_27_loss: 23.5040 - distribution_lambda_28_loss: 0.6597 - val_loss: 50.3063 - val_distribution_lambda_26_loss: 30.2402 - val_distribution_lambda_27_loss: 19.4200 - val_distribution_lambda_28_loss: 0.6460\n", "Epoch 10/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 49.8005 - distribution_lambda_26_loss: 28.9802 - distribution_lambda_27_loss: 20.1705 - distribution_lambda_28_loss: 0.6498 - val_loss: 44.2238 - val_distribution_lambda_26_loss: 26.8281 - val_distribution_lambda_27_loss: 16.7585 - val_distribution_lambda_28_loss: 0.6373\n", "Epoch 11/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 44.3848 - distribution_lambda_26_loss: 25.9915 - distribution_lambda_27_loss: 17.7523 - distribution_lambda_28_loss: 0.6409 - val_loss: 39.0558 - val_distribution_lambda_26_loss: 23.8972 - val_distribution_lambda_27_loss: 14.5287 - val_distribution_lambda_28_loss: 0.6299\n", "Epoch 12/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 39.3051 - distribution_lambda_26_loss: 23.1697 - distribution_lambda_27_loss: 15.4997 - distribution_lambda_28_loss: 0.6357 - val_loss: 34.6634 - val_distribution_lambda_26_loss: 21.3916 - val_distribution_lambda_27_loss: 12.6478 - val_distribution_lambda_28_loss: 0.6239\n", "Epoch 13/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 34.7644 - distribution_lambda_26_loss: 20.9584 - distribution_lambda_27_loss: 13.1741 - distribution_lambda_28_loss: 0.6319 - val_loss: 30.9429 - val_distribution_lambda_26_loss: 19.1970 - val_distribution_lambda_27_loss: 11.1269 - val_distribution_lambda_28_loss: 0.6190\n", "Epoch 14/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 31.1160 - distribution_lambda_26_loss: 18.6549 - distribution_lambda_27_loss: 11.8352 - distribution_lambda_28_loss: 0.6259 - val_loss: 27.8197 - val_distribution_lambda_26_loss: 17.3376 - val_distribution_lambda_27_loss: 9.8673 - val_distribution_lambda_28_loss: 0.6148\n", "Epoch 15/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 28.5349 - distribution_lambda_26_loss: 17.2940 - distribution_lambda_27_loss: 10.6187 - distribution_lambda_28_loss: 0.6222 - val_loss: 25.1625 - val_distribution_lambda_26_loss: 15.7275 - val_distribution_lambda_27_loss: 8.8238 - val_distribution_lambda_28_loss: 0.6112\n", "Epoch 16/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 25.6882 - distribution_lambda_26_loss: 15.7276 - distribution_lambda_27_loss: 9.3402 - distribution_lambda_28_loss: 0.6204 - val_loss: 22.9059 - val_distribution_lambda_26_loss: 14.3543 - val_distribution_lambda_27_loss: 7.9434 - val_distribution_lambda_28_loss: 0.6082\n", "Epoch 17/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 23.5566 - distribution_lambda_26_loss: 14.4582 - distribution_lambda_27_loss: 8.4842 - distribution_lambda_28_loss: 0.6141 - val_loss: 20.9612 - val_distribution_lambda_26_loss: 13.1507 - val_distribution_lambda_27_loss: 7.2048 - val_distribution_lambda_28_loss: 0.6057\n", "Epoch 18/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 21.7641 - distribution_lambda_26_loss: 13.3370 - distribution_lambda_27_loss: 7.8110 - distribution_lambda_28_loss: 0.6161 - val_loss: 19.2811 - val_distribution_lambda_26_loss: 12.1125 - val_distribution_lambda_27_loss: 6.5647 - val_distribution_lambda_28_loss: 0.6038\n", "Epoch 19/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 19.8883 - distribution_lambda_26_loss: 12.2286 - distribution_lambda_27_loss: 7.0458 - distribution_lambda_28_loss: 0.6139 - val_loss: 17.8345 - val_distribution_lambda_26_loss: 11.2082 - val_distribution_lambda_27_loss: 6.0240 - val_distribution_lambda_28_loss: 0.6023\n", "Epoch 20/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 18.8719 - distribution_lambda_26_loss: 11.5044 - distribution_lambda_27_loss: 6.7594 - distribution_lambda_28_loss: 0.6080 - val_loss: 16.5742 - val_distribution_lambda_26_loss: 10.4116 - val_distribution_lambda_27_loss: 5.5616 - val_distribution_lambda_28_loss: 0.6010\n", "Epoch 21/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 17.3019 - distribution_lambda_26_loss: 10.5656 - distribution_lambda_27_loss: 6.1266 - distribution_lambda_28_loss: 0.6097 - val_loss: 15.4846 - val_distribution_lambda_26_loss: 9.7153 - val_distribution_lambda_27_loss: 5.1693 - val_distribution_lambda_28_loss: 0.5999\n", "Epoch 22/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 16.4616 - distribution_lambda_26_loss: 9.9806 - distribution_lambda_27_loss: 5.8742 - distribution_lambda_28_loss: 0.6068 - val_loss: 14.5362 - val_distribution_lambda_26_loss: 9.1062 - val_distribution_lambda_27_loss: 4.8310 - val_distribution_lambda_28_loss: 0.5991\n", "Epoch 23/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 15.5441 - distribution_lambda_26_loss: 9.5332 - distribution_lambda_27_loss: 5.4061 - distribution_lambda_28_loss: 0.6048 - val_loss: 13.7131 - val_distribution_lambda_26_loss: 8.5677 - val_distribution_lambda_27_loss: 4.5472 - val_distribution_lambda_28_loss: 0.5982\n", "Epoch 24/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 14.4935 - distribution_lambda_26_loss: 8.8376 - distribution_lambda_27_loss: 5.0518 - distribution_lambda_28_loss: 0.6040 - val_loss: 12.9867 - val_distribution_lambda_26_loss: 8.0917 - val_distribution_lambda_27_loss: 4.2975 - val_distribution_lambda_28_loss: 0.5975\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 25/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 14.1258 - distribution_lambda_26_loss: 8.5527 - distribution_lambda_27_loss: 4.9674 - distribution_lambda_28_loss: 0.6057 - val_loss: 12.3423 - val_distribution_lambda_26_loss: 7.6652 - val_distribution_lambda_27_loss: 4.0803 - val_distribution_lambda_28_loss: 0.5969\n", "Epoch 26/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 13.1648 - distribution_lambda_26_loss: 7.9949 - distribution_lambda_27_loss: 4.5637 - distribution_lambda_28_loss: 0.6061 - val_loss: 11.7809 - val_distribution_lambda_26_loss: 7.2914 - val_distribution_lambda_27_loss: 3.8933 - val_distribution_lambda_28_loss: 0.5963\n", "Epoch 27/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 12.7060 - distribution_lambda_26_loss: 7.6410 - distribution_lambda_27_loss: 4.4611 - distribution_lambda_28_loss: 0.6039 - val_loss: 11.2842 - val_distribution_lambda_26_loss: 6.9593 - val_distribution_lambda_27_loss: 3.7291 - val_distribution_lambda_28_loss: 0.5958\n", "Epoch 28/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 12.1477 - distribution_lambda_26_loss: 7.2550 - distribution_lambda_27_loss: 4.2870 - distribution_lambda_28_loss: 0.6058 - val_loss: 10.8478 - val_distribution_lambda_26_loss: 6.6651 - val_distribution_lambda_27_loss: 3.5874 - val_distribution_lambda_28_loss: 0.5953\n", "Epoch 29/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 11.4911 - distribution_lambda_26_loss: 6.9293 - distribution_lambda_27_loss: 3.9596 - distribution_lambda_28_loss: 0.6023 - val_loss: 10.4625 - val_distribution_lambda_26_loss: 6.4030 - val_distribution_lambda_27_loss: 3.4646 - val_distribution_lambda_28_loss: 0.5949\n", "Epoch 30/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 11.3781 - distribution_lambda_26_loss: 6.7449 - distribution_lambda_27_loss: 4.0323 - distribution_lambda_28_loss: 0.6008 - val_loss: 10.1204 - val_distribution_lambda_26_loss: 6.1692 - val_distribution_lambda_27_loss: 3.3567 - val_distribution_lambda_28_loss: 0.5945\n", "Epoch 31/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 10.9506 - distribution_lambda_26_loss: 6.4987 - distribution_lambda_27_loss: 3.8503 - distribution_lambda_28_loss: 0.6017 - val_loss: 9.8183 - val_distribution_lambda_26_loss: 5.9612 - val_distribution_lambda_27_loss: 3.2630 - val_distribution_lambda_28_loss: 0.5941\n", "Epoch 32/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 10.6632 - distribution_lambda_26_loss: 6.3003 - distribution_lambda_27_loss: 3.7628 - distribution_lambda_28_loss: 0.6001 - val_loss: 9.5478 - val_distribution_lambda_26_loss: 5.7747 - val_distribution_lambda_27_loss: 3.1794 - val_distribution_lambda_28_loss: 0.5937\n", "Epoch 33/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 10.3353 - distribution_lambda_26_loss: 6.0883 - distribution_lambda_27_loss: 3.6496 - distribution_lambda_28_loss: 0.5974 - val_loss: 9.3017 - val_distribution_lambda_26_loss: 5.6040 - val_distribution_lambda_27_loss: 3.1043 - val_distribution_lambda_28_loss: 0.5934\n", "Epoch 34/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 9.9032 - distribution_lambda_26_loss: 5.8710 - distribution_lambda_27_loss: 3.4321 - distribution_lambda_28_loss: 0.6001 - val_loss: 9.0841 - val_distribution_lambda_26_loss: 5.4508 - val_distribution_lambda_27_loss: 3.0403 - val_distribution_lambda_28_loss: 0.5930\n", "Epoch 35/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 9.7848 - distribution_lambda_26_loss: 5.7083 - distribution_lambda_27_loss: 3.4772 - distribution_lambda_28_loss: 0.5993 - val_loss: 8.8900 - val_distribution_lambda_26_loss: 5.3140 - val_distribution_lambda_27_loss: 2.9834 - val_distribution_lambda_28_loss: 0.5926\n", "Epoch 36/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 9.6010 - distribution_lambda_26_loss: 5.5979 - distribution_lambda_27_loss: 3.4062 - distribution_lambda_28_loss: 0.5970 - val_loss: 8.7125 - val_distribution_lambda_26_loss: 5.1875 - val_distribution_lambda_27_loss: 2.9327 - val_distribution_lambda_28_loss: 0.5923\n", "Epoch 37/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 9.3883 - distribution_lambda_26_loss: 5.4777 - distribution_lambda_27_loss: 3.3108 - distribution_lambda_28_loss: 0.5998 - val_loss: 8.5506 - val_distribution_lambda_26_loss: 5.0721 - val_distribution_lambda_27_loss: 2.8865 - val_distribution_lambda_28_loss: 0.5920\n", "Epoch 38/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 9.1992 - distribution_lambda_26_loss: 5.3754 - distribution_lambda_27_loss: 3.2277 - distribution_lambda_28_loss: 0.5962 - val_loss: 8.4045 - val_distribution_lambda_26_loss: 4.9664 - val_distribution_lambda_27_loss: 2.8464 - val_distribution_lambda_28_loss: 0.5916\n", "Epoch 39/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 8.9762 - distribution_lambda_26_loss: 5.1713 - distribution_lambda_27_loss: 3.2076 - distribution_lambda_28_loss: 0.5973 - val_loss: 8.2727 - val_distribution_lambda_26_loss: 4.8711 - val_distribution_lambda_27_loss: 2.8104 - val_distribution_lambda_28_loss: 0.5913\n", "Epoch 40/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 8.8104 - distribution_lambda_26_loss: 5.1153 - distribution_lambda_27_loss: 3.0964 - distribution_lambda_28_loss: 0.5986 - val_loss: 8.1532 - val_distribution_lambda_26_loss: 4.7835 - val_distribution_lambda_27_loss: 2.7787 - val_distribution_lambda_28_loss: 0.5909\n", "Epoch 41/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 8.6865 - distribution_lambda_26_loss: 4.9994 - distribution_lambda_27_loss: 3.0898 - distribution_lambda_28_loss: 0.5974 - val_loss: 8.0424 - val_distribution_lambda_26_loss: 4.7024 - val_distribution_lambda_27_loss: 2.7494 - val_distribution_lambda_28_loss: 0.5906\n", "Epoch 42/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 8.6269 - distribution_lambda_26_loss: 4.9760 - distribution_lambda_27_loss: 3.0516 - distribution_lambda_28_loss: 0.5994 - val_loss: 7.9394 - val_distribution_lambda_26_loss: 4.6269 - val_distribution_lambda_27_loss: 2.7223 - val_distribution_lambda_28_loss: 0.5902\n", "Epoch 43/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 8.5404 - distribution_lambda_26_loss: 4.8860 - distribution_lambda_27_loss: 3.0587 - distribution_lambda_28_loss: 0.5957 - val_loss: 7.8433 - val_distribution_lambda_26_loss: 4.5563 - val_distribution_lambda_27_loss: 2.6972 - val_distribution_lambda_28_loss: 0.5899\n", "Epoch 44/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 8.3453 - distribution_lambda_26_loss: 4.8044 - distribution_lambda_27_loss: 2.9455 - distribution_lambda_28_loss: 0.5955 - val_loss: 7.7559 - val_distribution_lambda_26_loss: 4.4914 - val_distribution_lambda_27_loss: 2.6750 - val_distribution_lambda_28_loss: 0.5895\n", "Epoch 45/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 8.3607 - distribution_lambda_26_loss: 4.7509 - distribution_lambda_27_loss: 3.0136 - distribution_lambda_28_loss: 0.5962 - val_loss: 7.6743 - val_distribution_lambda_26_loss: 4.4308 - val_distribution_lambda_27_loss: 2.6544 - val_distribution_lambda_28_loss: 0.5891\n", "Epoch 46/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 8.1768 - distribution_lambda_26_loss: 4.6482 - distribution_lambda_27_loss: 2.9357 - distribution_lambda_28_loss: 0.5929 - val_loss: 7.5985 - val_distribution_lambda_26_loss: 4.3740 - val_distribution_lambda_27_loss: 2.6358 - val_distribution_lambda_28_loss: 0.5887\n", "Epoch 47/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 8.1367 - distribution_lambda_26_loss: 4.6072 - distribution_lambda_27_loss: 2.9355 - distribution_lambda_28_loss: 0.5940 - val_loss: 7.5274 - val_distribution_lambda_26_loss: 4.3208 - val_distribution_lambda_27_loss: 2.6182 - val_distribution_lambda_28_loss: 0.5884\n", "Epoch 48/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 7.9991 - distribution_lambda_26_loss: 4.5083 - distribution_lambda_27_loss: 2.8979 - distribution_lambda_28_loss: 0.5928 - val_loss: 7.4606 - val_distribution_lambda_26_loss: 4.2710 - val_distribution_lambda_27_loss: 2.6015 - val_distribution_lambda_28_loss: 0.5880\n", "Epoch 49/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 7.9865 - distribution_lambda_26_loss: 4.4911 - distribution_lambda_27_loss: 2.9055 - distribution_lambda_28_loss: 0.5899 - val_loss: 7.3985 - val_distribution_lambda_26_loss: 4.2245 - val_distribution_lambda_27_loss: 2.5863 - val_distribution_lambda_28_loss: 0.5877\n", "Epoch 50/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 7.8558 - distribution_lambda_26_loss: 4.4284 - distribution_lambda_27_loss: 2.8348 - distribution_lambda_28_loss: 0.5926 - val_loss: 7.3403 - val_distribution_lambda_26_loss: 4.1806 - val_distribution_lambda_27_loss: 2.5724 - val_distribution_lambda_28_loss: 0.5873\n", "Epoch 51/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 7.7991 - distribution_lambda_26_loss: 4.4161 - distribution_lambda_27_loss: 2.7907 - distribution_lambda_28_loss: 0.5923 - val_loss: 7.2854 - val_distribution_lambda_26_loss: 4.1390 - val_distribution_lambda_27_loss: 2.5595 - val_distribution_lambda_28_loss: 0.5870\n", "Epoch 52/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 7.7079 - distribution_lambda_26_loss: 4.3518 - distribution_lambda_27_loss: 2.7659 - distribution_lambda_28_loss: 0.5903 - val_loss: 7.2337 - val_distribution_lambda_26_loss: 4.0996 - val_distribution_lambda_27_loss: 2.5475 - val_distribution_lambda_28_loss: 0.5866\n", "Epoch 53/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 7.5517 - distribution_lambda_26_loss: 4.2326 - distribution_lambda_27_loss: 2.7278 - distribution_lambda_28_loss: 0.5913 - val_loss: 7.1862 - val_distribution_lambda_26_loss: 4.0635 - val_distribution_lambda_27_loss: 2.5364 - val_distribution_lambda_28_loss: 0.5863\n", "Epoch 54/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 7.6425 - distribution_lambda_26_loss: 4.2836 - distribution_lambda_27_loss: 2.7681 - distribution_lambda_28_loss: 0.5908 - val_loss: 7.1404 - val_distribution_lambda_26_loss: 4.0286 - val_distribution_lambda_27_loss: 2.5258 - val_distribution_lambda_28_loss: 0.5860\n", "Epoch 55/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 7.4601 - distribution_lambda_26_loss: 4.1682 - distribution_lambda_27_loss: 2.7026 - distribution_lambda_28_loss: 0.5892 - val_loss: 7.0985 - val_distribution_lambda_26_loss: 3.9967 - val_distribution_lambda_27_loss: 2.5162 - val_distribution_lambda_28_loss: 0.5857\n", "Epoch 56/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 7.5660 - distribution_lambda_26_loss: 4.2144 - distribution_lambda_27_loss: 2.7633 - distribution_lambda_28_loss: 0.5883 - val_loss: 7.0573 - val_distribution_lambda_26_loss: 3.9653 - val_distribution_lambda_27_loss: 2.5066 - val_distribution_lambda_28_loss: 0.5853\n", "Epoch 57/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 7.4166 - distribution_lambda_26_loss: 4.1323 - distribution_lambda_27_loss: 2.6956 - distribution_lambda_28_loss: 0.5888 - val_loss: 7.0188 - val_distribution_lambda_26_loss: 3.9358 - val_distribution_lambda_27_loss: 2.4980 - val_distribution_lambda_28_loss: 0.5850\n", "Epoch 58/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 7.4002 - distribution_lambda_26_loss: 4.1184 - distribution_lambda_27_loss: 2.6919 - distribution_lambda_28_loss: 0.5898 - val_loss: 6.9818 - val_distribution_lambda_26_loss: 3.9076 - val_distribution_lambda_27_loss: 2.4897 - val_distribution_lambda_28_loss: 0.5846\n", "Epoch 59/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 7.2561 - distribution_lambda_26_loss: 4.0319 - distribution_lambda_27_loss: 2.6340 - distribution_lambda_28_loss: 0.5903 - val_loss: 6.9477 - val_distribution_lambda_26_loss: 3.8813 - val_distribution_lambda_27_loss: 2.4822 - val_distribution_lambda_28_loss: 0.5842\n", "Epoch 60/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 7.2868 - distribution_lambda_26_loss: 4.0408 - distribution_lambda_27_loss: 2.6601 - distribution_lambda_28_loss: 0.5860 - val_loss: 6.9149 - val_distribution_lambda_26_loss: 3.8560 - val_distribution_lambda_27_loss: 2.4751 - val_distribution_lambda_28_loss: 0.5838\n", "Epoch 61/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 7.3000 - distribution_lambda_26_loss: 4.0213 - distribution_lambda_27_loss: 2.6898 - distribution_lambda_28_loss: 0.5889 - val_loss: 6.8832 - val_distribution_lambda_26_loss: 3.8317 - val_distribution_lambda_27_loss: 2.4679 - val_distribution_lambda_28_loss: 0.5835\n", "Epoch 62/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 7.1956 - distribution_lambda_26_loss: 3.9834 - distribution_lambda_27_loss: 2.6234 - distribution_lambda_28_loss: 0.5888 - val_loss: 6.8530 - val_distribution_lambda_26_loss: 3.8085 - val_distribution_lambda_27_loss: 2.4613 - val_distribution_lambda_28_loss: 0.5832\n", "Epoch 63/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 7.2197 - distribution_lambda_26_loss: 3.9880 - distribution_lambda_27_loss: 2.6420 - distribution_lambda_28_loss: 0.5896 - val_loss: 6.8242 - val_distribution_lambda_26_loss: 3.7863 - val_distribution_lambda_27_loss: 2.4551 - val_distribution_lambda_28_loss: 0.5829\n", "Epoch 64/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 7.1092 - distribution_lambda_26_loss: 3.9378 - distribution_lambda_27_loss: 2.5830 - distribution_lambda_28_loss: 0.5885 - val_loss: 6.7972 - val_distribution_lambda_26_loss: 3.7652 - val_distribution_lambda_27_loss: 2.4494 - val_distribution_lambda_28_loss: 0.5826\n", "Epoch 65/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 7.1478 - distribution_lambda_26_loss: 3.9366 - distribution_lambda_27_loss: 2.6254 - distribution_lambda_28_loss: 0.5858 - val_loss: 6.7703 - val_distribution_lambda_26_loss: 3.7446 - val_distribution_lambda_27_loss: 2.4434 - val_distribution_lambda_28_loss: 0.5823\n", "Epoch 66/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 7.0493 - distribution_lambda_26_loss: 3.8773 - distribution_lambda_27_loss: 2.5851 - distribution_lambda_28_loss: 0.5868 - val_loss: 6.7449 - val_distribution_lambda_26_loss: 3.7250 - val_distribution_lambda_27_loss: 2.4378 - val_distribution_lambda_28_loss: 0.5820\n", "Epoch 67/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 7.0647 - distribution_lambda_26_loss: 3.8819 - distribution_lambda_27_loss: 2.5956 - distribution_lambda_28_loss: 0.5872 - val_loss: 6.7206 - val_distribution_lambda_26_loss: 3.7063 - val_distribution_lambda_27_loss: 2.4326 - val_distribution_lambda_28_loss: 0.5817\n", "Epoch 68/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 7.0555 - distribution_lambda_26_loss: 3.8600 - distribution_lambda_27_loss: 2.6108 - distribution_lambda_28_loss: 0.5847 - val_loss: 6.6969 - val_distribution_lambda_26_loss: 3.6883 - val_distribution_lambda_27_loss: 2.4272 - val_distribution_lambda_28_loss: 0.5814\n", "Epoch 69/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 7.0164 - distribution_lambda_26_loss: 3.8324 - distribution_lambda_27_loss: 2.5987 - distribution_lambda_28_loss: 0.5853 - val_loss: 6.6741 - val_distribution_lambda_26_loss: 3.6709 - val_distribution_lambda_27_loss: 2.4221 - val_distribution_lambda_28_loss: 0.5811\n", "Epoch 70/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.9047 - distribution_lambda_26_loss: 3.7708 - distribution_lambda_27_loss: 2.5491 - distribution_lambda_28_loss: 0.5848 - val_loss: 6.6527 - val_distribution_lambda_26_loss: 3.6546 - val_distribution_lambda_27_loss: 2.4172 - val_distribution_lambda_28_loss: 0.5808\n", "Epoch 71/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.9685 - distribution_lambda_26_loss: 3.7961 - distribution_lambda_27_loss: 2.5857 - distribution_lambda_28_loss: 0.5868 - val_loss: 6.6319 - val_distribution_lambda_26_loss: 3.6387 - val_distribution_lambda_27_loss: 2.4126 - val_distribution_lambda_28_loss: 0.5805\n", "Epoch 72/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.9546 - distribution_lambda_26_loss: 3.7851 - distribution_lambda_27_loss: 2.5878 - distribution_lambda_28_loss: 0.5817 - val_loss: 6.6116 - val_distribution_lambda_26_loss: 3.6232 - val_distribution_lambda_27_loss: 2.4082 - val_distribution_lambda_28_loss: 0.5802\n", "Epoch 73/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 6.8357 - distribution_lambda_26_loss: 3.7325 - distribution_lambda_27_loss: 2.5194 - distribution_lambda_28_loss: 0.5838 - val_loss: 6.5927 - val_distribution_lambda_26_loss: 3.6086 - val_distribution_lambda_27_loss: 2.4042 - val_distribution_lambda_28_loss: 0.5799\n", "Epoch 74/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.9220 - distribution_lambda_26_loss: 3.7512 - distribution_lambda_27_loss: 2.5882 - distribution_lambda_28_loss: 0.5826 - val_loss: 6.5738 - val_distribution_lambda_26_loss: 3.5942 - val_distribution_lambda_27_loss: 2.4000 - val_distribution_lambda_28_loss: 0.5796\n", "Epoch 75/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.8587 - distribution_lambda_26_loss: 3.7066 - distribution_lambda_27_loss: 2.5710 - distribution_lambda_28_loss: 0.5810 - val_loss: 6.5556 - val_distribution_lambda_26_loss: 3.5805 - val_distribution_lambda_27_loss: 2.3958 - val_distribution_lambda_28_loss: 0.5793\n", "Epoch 76/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.8373 - distribution_lambda_26_loss: 3.7023 - distribution_lambda_27_loss: 2.5557 - distribution_lambda_28_loss: 0.5793 - val_loss: 6.5377 - val_distribution_lambda_26_loss: 3.5670 - val_distribution_lambda_27_loss: 2.3917 - val_distribution_lambda_28_loss: 0.5790\n", "Epoch 77/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.7754 - distribution_lambda_26_loss: 3.6723 - distribution_lambda_27_loss: 2.5190 - distribution_lambda_28_loss: 0.5840 - val_loss: 6.5206 - val_distribution_lambda_26_loss: 3.5541 - val_distribution_lambda_27_loss: 2.3878 - val_distribution_lambda_28_loss: 0.5787\n", "Epoch 78/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.8082 - distribution_lambda_26_loss: 3.6799 - distribution_lambda_27_loss: 2.5486 - distribution_lambda_28_loss: 0.5796 - val_loss: 6.5038 - val_distribution_lambda_26_loss: 3.5415 - val_distribution_lambda_27_loss: 2.3838 - val_distribution_lambda_28_loss: 0.5785\n", "Epoch 79/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.8400 - distribution_lambda_26_loss: 3.6829 - distribution_lambda_27_loss: 2.5745 - distribution_lambda_28_loss: 0.5827 - val_loss: 6.4873 - val_distribution_lambda_26_loss: 3.5290 - val_distribution_lambda_27_loss: 2.3800 - val_distribution_lambda_28_loss: 0.5782\n", "Epoch 80/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.8222 - distribution_lambda_26_loss: 3.6521 - distribution_lambda_27_loss: 2.5914 - distribution_lambda_28_loss: 0.5787 - val_loss: 6.4712 - val_distribution_lambda_26_loss: 3.5171 - val_distribution_lambda_27_loss: 2.3760 - val_distribution_lambda_28_loss: 0.5780\n", "Epoch 81/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.6748 - distribution_lambda_26_loss: 3.6043 - distribution_lambda_27_loss: 2.4888 - distribution_lambda_28_loss: 0.5817 - val_loss: 6.4562 - val_distribution_lambda_26_loss: 3.5057 - val_distribution_lambda_27_loss: 2.3727 - val_distribution_lambda_28_loss: 0.5778\n", "Epoch 82/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.6954 - distribution_lambda_26_loss: 3.6358 - distribution_lambda_27_loss: 2.4776 - distribution_lambda_28_loss: 0.5819 - val_loss: 6.4416 - val_distribution_lambda_26_loss: 3.4946 - val_distribution_lambda_27_loss: 2.3695 - val_distribution_lambda_28_loss: 0.5775\n", "Epoch 83/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.6958 - distribution_lambda_26_loss: 3.6084 - distribution_lambda_27_loss: 2.5088 - distribution_lambda_28_loss: 0.5786 - val_loss: 6.4276 - val_distribution_lambda_26_loss: 3.4838 - val_distribution_lambda_27_loss: 2.3665 - val_distribution_lambda_28_loss: 0.5773\n", "Epoch 84/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.6642 - distribution_lambda_26_loss: 3.6012 - distribution_lambda_27_loss: 2.4823 - distribution_lambda_28_loss: 0.5807 - val_loss: 6.4138 - val_distribution_lambda_26_loss: 3.4732 - val_distribution_lambda_27_loss: 2.3636 - val_distribution_lambda_28_loss: 0.5771\n", "Epoch 85/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.6607 - distribution_lambda_26_loss: 3.5855 - distribution_lambda_27_loss: 2.4950 - distribution_lambda_28_loss: 0.5802 - val_loss: 6.4004 - val_distribution_lambda_26_loss: 3.4631 - val_distribution_lambda_27_loss: 2.3605 - val_distribution_lambda_28_loss: 0.5768\n", "Epoch 86/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.6158 - distribution_lambda_26_loss: 3.5732 - distribution_lambda_27_loss: 2.4624 - distribution_lambda_28_loss: 0.5803 - val_loss: 6.3871 - val_distribution_lambda_26_loss: 3.4531 - val_distribution_lambda_27_loss: 2.3575 - val_distribution_lambda_28_loss: 0.5765\n", "Epoch 87/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.6540 - distribution_lambda_26_loss: 3.5599 - distribution_lambda_27_loss: 2.5137 - distribution_lambda_28_loss: 0.5804 - val_loss: 6.3742 - val_distribution_lambda_26_loss: 3.4434 - val_distribution_lambda_27_loss: 2.3545 - val_distribution_lambda_28_loss: 0.5763\n", "Epoch 88/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.6209 - distribution_lambda_26_loss: 3.5602 - distribution_lambda_27_loss: 2.4808 - distribution_lambda_28_loss: 0.5799 - val_loss: 6.3614 - val_distribution_lambda_26_loss: 3.4340 - val_distribution_lambda_27_loss: 2.3514 - val_distribution_lambda_28_loss: 0.5760\n", "Epoch 89/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.5930 - distribution_lambda_26_loss: 3.5228 - distribution_lambda_27_loss: 2.4925 - distribution_lambda_28_loss: 0.5778 - val_loss: 6.3490 - val_distribution_lambda_26_loss: 3.4249 - val_distribution_lambda_27_loss: 2.3482 - val_distribution_lambda_28_loss: 0.5758\n", "Epoch 90/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.5876 - distribution_lambda_26_loss: 3.5332 - distribution_lambda_27_loss: 2.4759 - distribution_lambda_28_loss: 0.5785 - val_loss: 6.3370 - val_distribution_lambda_26_loss: 3.4160 - val_distribution_lambda_27_loss: 2.3453 - val_distribution_lambda_28_loss: 0.5757\n", "Epoch 91/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.5707 - distribution_lambda_26_loss: 3.5098 - distribution_lambda_27_loss: 2.4839 - distribution_lambda_28_loss: 0.5770 - val_loss: 6.3253 - val_distribution_lambda_26_loss: 3.4073 - val_distribution_lambda_27_loss: 2.3425 - val_distribution_lambda_28_loss: 0.5755\n", "Epoch 92/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.5351 - distribution_lambda_26_loss: 3.4923 - distribution_lambda_27_loss: 2.4650 - distribution_lambda_28_loss: 0.5778 - val_loss: 6.3137 - val_distribution_lambda_26_loss: 3.3990 - val_distribution_lambda_27_loss: 2.3395 - val_distribution_lambda_28_loss: 0.5753\n", "Epoch 93/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.5455 - distribution_lambda_26_loss: 3.4892 - distribution_lambda_27_loss: 2.4786 - distribution_lambda_28_loss: 0.5777 - val_loss: 6.3023 - val_distribution_lambda_26_loss: 3.3907 - val_distribution_lambda_27_loss: 2.3364 - val_distribution_lambda_28_loss: 0.5751\n", "Epoch 94/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.4953 - distribution_lambda_26_loss: 3.4884 - distribution_lambda_27_loss: 2.4304 - distribution_lambda_28_loss: 0.5766 - val_loss: 6.2914 - val_distribution_lambda_26_loss: 3.3827 - val_distribution_lambda_27_loss: 2.3338 - val_distribution_lambda_28_loss: 0.5748\n", "Epoch 95/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.4939 - distribution_lambda_26_loss: 3.4717 - distribution_lambda_27_loss: 2.4445 - distribution_lambda_28_loss: 0.5778 - val_loss: 6.2807 - val_distribution_lambda_26_loss: 3.3749 - val_distribution_lambda_27_loss: 2.3311 - val_distribution_lambda_28_loss: 0.5747\n", "Epoch 96/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.5390 - distribution_lambda_26_loss: 3.4677 - distribution_lambda_27_loss: 2.4946 - distribution_lambda_28_loss: 0.5767 - val_loss: 6.2698 - val_distribution_lambda_26_loss: 3.3673 - val_distribution_lambda_27_loss: 2.3279 - val_distribution_lambda_28_loss: 0.5746\n", "Epoch 97/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 6.5053 - distribution_lambda_26_loss: 3.4508 - distribution_lambda_27_loss: 2.4788 - distribution_lambda_28_loss: 0.5757 - val_loss: 6.2593 - val_distribution_lambda_26_loss: 3.3599 - val_distribution_lambda_27_loss: 2.3249 - val_distribution_lambda_28_loss: 0.5744\n", "Epoch 98/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.4582 - distribution_lambda_26_loss: 3.4334 - distribution_lambda_27_loss: 2.4484 - distribution_lambda_28_loss: 0.5763 - val_loss: 6.2490 - val_distribution_lambda_26_loss: 3.3528 - val_distribution_lambda_27_loss: 2.3219 - val_distribution_lambda_28_loss: 0.5743\n", "Epoch 99/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.4362 - distribution_lambda_26_loss: 3.4256 - distribution_lambda_27_loss: 2.4321 - distribution_lambda_28_loss: 0.5785 - val_loss: 6.2392 - val_distribution_lambda_26_loss: 3.3458 - val_distribution_lambda_27_loss: 2.3192 - val_distribution_lambda_28_loss: 0.5741\n", "Epoch 100/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.3701 - distribution_lambda_26_loss: 3.4155 - distribution_lambda_27_loss: 2.3779 - distribution_lambda_28_loss: 0.5767 - val_loss: 6.2296 - val_distribution_lambda_26_loss: 3.3389 - val_distribution_lambda_27_loss: 2.3167 - val_distribution_lambda_28_loss: 0.5740\n", "Epoch 101/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.4250 - distribution_lambda_26_loss: 3.4243 - distribution_lambda_27_loss: 2.4247 - distribution_lambda_28_loss: 0.5760 - val_loss: 6.2199 - val_distribution_lambda_26_loss: 3.3320 - val_distribution_lambda_27_loss: 2.3141 - val_distribution_lambda_28_loss: 0.5738\n", "Epoch 102/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.4525 - distribution_lambda_26_loss: 3.4184 - distribution_lambda_27_loss: 2.4600 - distribution_lambda_28_loss: 0.5741 - val_loss: 6.2103 - val_distribution_lambda_26_loss: 3.3253 - val_distribution_lambda_27_loss: 2.3113 - val_distribution_lambda_28_loss: 0.5736\n", "Epoch 103/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.4002 - distribution_lambda_26_loss: 3.4002 - distribution_lambda_27_loss: 2.4233 - distribution_lambda_28_loss: 0.5767 - val_loss: 6.2007 - val_distribution_lambda_26_loss: 3.3187 - val_distribution_lambda_27_loss: 2.3085 - val_distribution_lambda_28_loss: 0.5735\n", "Epoch 104/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.3744 - distribution_lambda_26_loss: 3.3859 - distribution_lambda_27_loss: 2.4140 - distribution_lambda_28_loss: 0.5745 - val_loss: 6.1915 - val_distribution_lambda_26_loss: 3.3124 - val_distribution_lambda_27_loss: 2.3058 - val_distribution_lambda_28_loss: 0.5734\n", "Epoch 105/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.3603 - distribution_lambda_26_loss: 3.3772 - distribution_lambda_27_loss: 2.4061 - distribution_lambda_28_loss: 0.5770 - val_loss: 6.1826 - val_distribution_lambda_26_loss: 3.3063 - val_distribution_lambda_27_loss: 2.3031 - val_distribution_lambda_28_loss: 0.5732\n", "Epoch 106/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.3977 - distribution_lambda_26_loss: 3.4049 - distribution_lambda_27_loss: 2.4182 - distribution_lambda_28_loss: 0.5746 - val_loss: 6.1735 - val_distribution_lambda_26_loss: 3.3000 - val_distribution_lambda_27_loss: 2.3005 - val_distribution_lambda_28_loss: 0.5730\n", "Epoch 107/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.3382 - distribution_lambda_26_loss: 3.3856 - distribution_lambda_27_loss: 2.3786 - distribution_lambda_28_loss: 0.5740 - val_loss: 6.1645 - val_distribution_lambda_26_loss: 3.2939 - val_distribution_lambda_27_loss: 2.2978 - val_distribution_lambda_28_loss: 0.5728\n", "Epoch 108/2500\n", "8/8 [==============================] - 0s 8ms/step - loss: 6.3401 - distribution_lambda_26_loss: 3.3849 - distribution_lambda_27_loss: 2.3806 - distribution_lambda_28_loss: 0.5746 - val_loss: 6.1558 - val_distribution_lambda_26_loss: 3.2879 - val_distribution_lambda_27_loss: 2.2952 - val_distribution_lambda_28_loss: 0.5726\n", "Epoch 109/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.3294 - distribution_lambda_26_loss: 3.3572 - distribution_lambda_27_loss: 2.3981 - distribution_lambda_28_loss: 0.5741 - val_loss: 6.1471 - val_distribution_lambda_26_loss: 3.2821 - val_distribution_lambda_27_loss: 2.2926 - val_distribution_lambda_28_loss: 0.5725\n", "Epoch 110/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.3046 - distribution_lambda_26_loss: 3.3532 - distribution_lambda_27_loss: 2.3763 - distribution_lambda_28_loss: 0.5751 - val_loss: 6.1385 - val_distribution_lambda_26_loss: 3.2763 - val_distribution_lambda_27_loss: 2.2900 - val_distribution_lambda_28_loss: 0.5722\n", "Epoch 111/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 6.2776 - distribution_lambda_26_loss: 3.3557 - distribution_lambda_27_loss: 2.3471 - distribution_lambda_28_loss: 0.5748 - val_loss: 6.1301 - val_distribution_lambda_26_loss: 3.2707 - val_distribution_lambda_27_loss: 2.2873 - val_distribution_lambda_28_loss: 0.5721\n", "Epoch 112/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 6.2688 - distribution_lambda_26_loss: 3.3376 - distribution_lambda_27_loss: 2.3592 - distribution_lambda_28_loss: 0.5720 - val_loss: 6.1219 - val_distribution_lambda_26_loss: 3.2653 - val_distribution_lambda_27_loss: 2.2848 - val_distribution_lambda_28_loss: 0.5719\n", "Epoch 113/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 6.2774 - distribution_lambda_26_loss: 3.3282 - distribution_lambda_27_loss: 2.3749 - distribution_lambda_28_loss: 0.5743 - val_loss: 6.1137 - val_distribution_lambda_26_loss: 3.2599 - val_distribution_lambda_27_loss: 2.2821 - val_distribution_lambda_28_loss: 0.5717\n", "Epoch 114/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 6.2866 - distribution_lambda_26_loss: 3.3389 - distribution_lambda_27_loss: 2.3759 - distribution_lambda_28_loss: 0.5718 - val_loss: 6.1055 - val_distribution_lambda_26_loss: 3.2546 - val_distribution_lambda_27_loss: 2.2794 - val_distribution_lambda_28_loss: 0.5715\n", "Epoch 115/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 6.2735 - distribution_lambda_26_loss: 3.3219 - distribution_lambda_27_loss: 2.3752 - distribution_lambda_28_loss: 0.5764 - val_loss: 6.0975 - val_distribution_lambda_26_loss: 3.2493 - val_distribution_lambda_27_loss: 2.2768 - val_distribution_lambda_28_loss: 0.5713\n", "Epoch 116/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 6.2745 - distribution_lambda_26_loss: 3.3024 - distribution_lambda_27_loss: 2.3987 - distribution_lambda_28_loss: 0.5734 - val_loss: 6.0894 - val_distribution_lambda_26_loss: 3.2443 - val_distribution_lambda_27_loss: 2.2739 - val_distribution_lambda_28_loss: 0.5712\n", "Epoch 117/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.2611 - distribution_lambda_26_loss: 3.3117 - distribution_lambda_27_loss: 2.3754 - distribution_lambda_28_loss: 0.5740 - val_loss: 6.0815 - val_distribution_lambda_26_loss: 3.2393 - val_distribution_lambda_27_loss: 2.2711 - val_distribution_lambda_28_loss: 0.5710\n", "Epoch 118/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.2662 - distribution_lambda_26_loss: 3.3111 - distribution_lambda_27_loss: 2.3817 - distribution_lambda_28_loss: 0.5734 - val_loss: 6.0734 - val_distribution_lambda_26_loss: 3.2344 - val_distribution_lambda_27_loss: 2.2681 - val_distribution_lambda_28_loss: 0.5708\n", "Epoch 119/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.2177 - distribution_lambda_26_loss: 3.2944 - distribution_lambda_27_loss: 2.3522 - distribution_lambda_28_loss: 0.5711 - val_loss: 6.0654 - val_distribution_lambda_26_loss: 3.2296 - val_distribution_lambda_27_loss: 2.2652 - val_distribution_lambda_28_loss: 0.5707\n", "Epoch 120/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.1789 - distribution_lambda_26_loss: 3.2795 - distribution_lambda_27_loss: 2.3245 - distribution_lambda_28_loss: 0.5749 - val_loss: 6.0578 - val_distribution_lambda_26_loss: 3.2249 - val_distribution_lambda_27_loss: 2.2624 - val_distribution_lambda_28_loss: 0.5705\n", "Epoch 121/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 6.1763 - distribution_lambda_26_loss: 3.2829 - distribution_lambda_27_loss: 2.3200 - distribution_lambda_28_loss: 0.5734 - val_loss: 6.0500 - val_distribution_lambda_26_loss: 3.2203 - val_distribution_lambda_27_loss: 2.2593 - val_distribution_lambda_28_loss: 0.5703\n", "Epoch 122/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.2184 - distribution_lambda_26_loss: 3.2996 - distribution_lambda_27_loss: 2.3482 - distribution_lambda_28_loss: 0.5706 - val_loss: 6.0421 - val_distribution_lambda_26_loss: 3.2157 - val_distribution_lambda_27_loss: 2.2563 - val_distribution_lambda_28_loss: 0.5702\n", "Epoch 123/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 6.2204 - distribution_lambda_26_loss: 3.2970 - distribution_lambda_27_loss: 2.3538 - distribution_lambda_28_loss: 0.5695 - val_loss: 6.0344 - val_distribution_lambda_26_loss: 3.2111 - val_distribution_lambda_27_loss: 2.2533 - val_distribution_lambda_28_loss: 0.5700\n", "Epoch 124/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 6.1525 - distribution_lambda_26_loss: 3.2630 - distribution_lambda_27_loss: 2.3157 - distribution_lambda_28_loss: 0.5739 - val_loss: 6.0268 - val_distribution_lambda_26_loss: 3.2066 - val_distribution_lambda_27_loss: 2.2503 - val_distribution_lambda_28_loss: 0.5699\n", "Epoch 125/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 6.1438 - distribution_lambda_26_loss: 3.2643 - distribution_lambda_27_loss: 2.3068 - distribution_lambda_28_loss: 0.5728 - val_loss: 6.0193 - val_distribution_lambda_26_loss: 3.2023 - val_distribution_lambda_27_loss: 2.2473 - val_distribution_lambda_28_loss: 0.5697\n", "Epoch 126/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 6.1700 - distribution_lambda_26_loss: 3.2618 - distribution_lambda_27_loss: 2.3394 - distribution_lambda_28_loss: 0.5689 - val_loss: 6.0116 - val_distribution_lambda_26_loss: 3.1980 - val_distribution_lambda_27_loss: 2.2440 - val_distribution_lambda_28_loss: 0.5695\n", "Epoch 127/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 6.1289 - distribution_lambda_26_loss: 3.2549 - distribution_lambda_27_loss: 2.3017 - distribution_lambda_28_loss: 0.5723 - val_loss: 6.0040 - val_distribution_lambda_26_loss: 3.1938 - val_distribution_lambda_27_loss: 2.2408 - val_distribution_lambda_28_loss: 0.5693\n", "Epoch 128/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.1165 - distribution_lambda_26_loss: 3.2462 - distribution_lambda_27_loss: 2.2996 - distribution_lambda_28_loss: 0.5706 - val_loss: 5.9966 - val_distribution_lambda_26_loss: 3.1897 - val_distribution_lambda_27_loss: 2.2378 - val_distribution_lambda_28_loss: 0.5691\n", "Epoch 129/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.1276 - distribution_lambda_26_loss: 3.2485 - distribution_lambda_27_loss: 2.3105 - distribution_lambda_28_loss: 0.5687 - val_loss: 5.9888 - val_distribution_lambda_26_loss: 3.1856 - val_distribution_lambda_27_loss: 2.2343 - val_distribution_lambda_28_loss: 0.5689\n", "Epoch 130/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.1094 - distribution_lambda_26_loss: 3.2358 - distribution_lambda_27_loss: 2.3020 - distribution_lambda_28_loss: 0.5716 - val_loss: 5.9815 - val_distribution_lambda_26_loss: 3.1815 - val_distribution_lambda_27_loss: 2.2312 - val_distribution_lambda_28_loss: 0.5687\n", "Epoch 131/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.0963 - distribution_lambda_26_loss: 3.2302 - distribution_lambda_27_loss: 2.2980 - distribution_lambda_28_loss: 0.5681 - val_loss: 5.9740 - val_distribution_lambda_26_loss: 3.1776 - val_distribution_lambda_27_loss: 2.2278 - val_distribution_lambda_28_loss: 0.5686\n", "Epoch 132/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.1378 - distribution_lambda_26_loss: 3.2399 - distribution_lambda_27_loss: 2.3273 - distribution_lambda_28_loss: 0.5705 - val_loss: 5.9663 - val_distribution_lambda_26_loss: 3.1736 - val_distribution_lambda_27_loss: 2.2242 - val_distribution_lambda_28_loss: 0.5685\n", "Epoch 133/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.0720 - distribution_lambda_26_loss: 3.2271 - distribution_lambda_27_loss: 2.2748 - distribution_lambda_28_loss: 0.5701 - val_loss: 5.9588 - val_distribution_lambda_26_loss: 3.1697 - val_distribution_lambda_27_loss: 2.2208 - val_distribution_lambda_28_loss: 0.5683\n", "Epoch 134/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.0585 - distribution_lambda_26_loss: 3.2114 - distribution_lambda_27_loss: 2.2756 - distribution_lambda_28_loss: 0.5715 - val_loss: 5.9513 - val_distribution_lambda_26_loss: 3.1659 - val_distribution_lambda_27_loss: 2.2173 - val_distribution_lambda_28_loss: 0.5680\n", "Epoch 135/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.0802 - distribution_lambda_26_loss: 3.2205 - distribution_lambda_27_loss: 2.2904 - distribution_lambda_28_loss: 0.5693 - val_loss: 5.9435 - val_distribution_lambda_26_loss: 3.1622 - val_distribution_lambda_27_loss: 2.2135 - val_distribution_lambda_28_loss: 0.5678\n", "Epoch 136/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.0524 - distribution_lambda_26_loss: 3.2046 - distribution_lambda_27_loss: 2.2800 - distribution_lambda_28_loss: 0.5678 - val_loss: 5.9357 - val_distribution_lambda_26_loss: 3.1585 - val_distribution_lambda_27_loss: 2.2097 - val_distribution_lambda_28_loss: 0.5676\n", "Epoch 137/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.0519 - distribution_lambda_26_loss: 3.2057 - distribution_lambda_27_loss: 2.2789 - distribution_lambda_28_loss: 0.5674 - val_loss: 5.9281 - val_distribution_lambda_26_loss: 3.1548 - val_distribution_lambda_27_loss: 2.2060 - val_distribution_lambda_28_loss: 0.5673\n", "Epoch 138/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 6.0541 - distribution_lambda_26_loss: 3.2116 - distribution_lambda_27_loss: 2.2741 - distribution_lambda_28_loss: 0.5683 - val_loss: 5.9210 - val_distribution_lambda_26_loss: 3.1512 - val_distribution_lambda_27_loss: 2.2027 - val_distribution_lambda_28_loss: 0.5671\n", "Epoch 139/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.0206 - distribution_lambda_26_loss: 3.1984 - distribution_lambda_27_loss: 2.2549 - distribution_lambda_28_loss: 0.5672 - val_loss: 5.9139 - val_distribution_lambda_26_loss: 3.1476 - val_distribution_lambda_27_loss: 2.1995 - val_distribution_lambda_28_loss: 0.5668\n", "Epoch 140/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.0170 - distribution_lambda_26_loss: 3.1888 - distribution_lambda_27_loss: 2.2614 - distribution_lambda_28_loss: 0.5668 - val_loss: 5.9066 - val_distribution_lambda_26_loss: 3.1441 - val_distribution_lambda_27_loss: 2.1960 - val_distribution_lambda_28_loss: 0.5666\n", "Epoch 141/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.0386 - distribution_lambda_26_loss: 3.1943 - distribution_lambda_27_loss: 2.2723 - distribution_lambda_28_loss: 0.5720 - val_loss: 5.8994 - val_distribution_lambda_26_loss: 3.1406 - val_distribution_lambda_27_loss: 2.1924 - val_distribution_lambda_28_loss: 0.5664\n", "Epoch 142/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.0554 - distribution_lambda_26_loss: 3.1947 - distribution_lambda_27_loss: 2.2904 - distribution_lambda_28_loss: 0.5703 - val_loss: 5.8917 - val_distribution_lambda_26_loss: 3.1371 - val_distribution_lambda_27_loss: 2.1883 - val_distribution_lambda_28_loss: 0.5662\n", "Epoch 143/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.0379 - distribution_lambda_26_loss: 3.1952 - distribution_lambda_27_loss: 2.2752 - distribution_lambda_28_loss: 0.5676 - val_loss: 5.8843 - val_distribution_lambda_26_loss: 3.1336 - val_distribution_lambda_27_loss: 2.1846 - val_distribution_lambda_28_loss: 0.5660\n", "Epoch 144/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 6.0120 - distribution_lambda_26_loss: 3.1776 - distribution_lambda_27_loss: 2.2673 - distribution_lambda_28_loss: 0.5670 - val_loss: 5.8769 - val_distribution_lambda_26_loss: 3.1302 - val_distribution_lambda_27_loss: 2.1809 - val_distribution_lambda_28_loss: 0.5657\n", "Epoch 145/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 5.9823 - distribution_lambda_26_loss: 3.1807 - distribution_lambda_27_loss: 2.2378 - distribution_lambda_28_loss: 0.5638 - val_loss: 5.8696 - val_distribution_lambda_26_loss: 3.1269 - val_distribution_lambda_27_loss: 2.1773 - val_distribution_lambda_28_loss: 0.5654\n", "Epoch 146/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.9690 - distribution_lambda_26_loss: 3.1695 - distribution_lambda_27_loss: 2.2318 - distribution_lambda_28_loss: 0.5677 - val_loss: 5.8626 - val_distribution_lambda_26_loss: 3.1236 - val_distribution_lambda_27_loss: 2.1739 - val_distribution_lambda_28_loss: 0.5652\n", "Epoch 147/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 6.0001 - distribution_lambda_26_loss: 3.1676 - distribution_lambda_27_loss: 2.2660 - distribution_lambda_28_loss: 0.5666 - val_loss: 5.8555 - val_distribution_lambda_26_loss: 3.1203 - val_distribution_lambda_27_loss: 2.1702 - val_distribution_lambda_28_loss: 0.5649\n", "Epoch 148/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.9706 - distribution_lambda_26_loss: 3.1575 - distribution_lambda_27_loss: 2.2477 - distribution_lambda_28_loss: 0.5654 - val_loss: 5.8482 - val_distribution_lambda_26_loss: 3.1172 - val_distribution_lambda_27_loss: 2.1665 - val_distribution_lambda_28_loss: 0.5646\n", "Epoch 149/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.9570 - distribution_lambda_26_loss: 3.1698 - distribution_lambda_27_loss: 2.2199 - distribution_lambda_28_loss: 0.5674 - val_loss: 5.8414 - val_distribution_lambda_26_loss: 3.1140 - val_distribution_lambda_27_loss: 2.1631 - val_distribution_lambda_28_loss: 0.5643\n", "Epoch 150/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.9711 - distribution_lambda_26_loss: 3.1599 - distribution_lambda_27_loss: 2.2489 - distribution_lambda_28_loss: 0.5623 - val_loss: 5.8347 - val_distribution_lambda_26_loss: 3.1108 - val_distribution_lambda_27_loss: 2.1599 - val_distribution_lambda_28_loss: 0.5640\n", "Epoch 151/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.9577 - distribution_lambda_26_loss: 3.1533 - distribution_lambda_27_loss: 2.2386 - distribution_lambda_28_loss: 0.5657 - val_loss: 5.8282 - val_distribution_lambda_26_loss: 3.1076 - val_distribution_lambda_27_loss: 2.1567 - val_distribution_lambda_28_loss: 0.5639\n", "Epoch 152/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.9068 - distribution_lambda_26_loss: 3.1458 - distribution_lambda_27_loss: 2.1976 - distribution_lambda_28_loss: 0.5634 - val_loss: 5.8218 - val_distribution_lambda_26_loss: 3.1045 - val_distribution_lambda_27_loss: 2.1536 - val_distribution_lambda_28_loss: 0.5637\n", "Epoch 153/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.9105 - distribution_lambda_26_loss: 3.1397 - distribution_lambda_27_loss: 2.2066 - distribution_lambda_28_loss: 0.5641 - val_loss: 5.8154 - val_distribution_lambda_26_loss: 3.1015 - val_distribution_lambda_27_loss: 2.1505 - val_distribution_lambda_28_loss: 0.5634\n", "Epoch 154/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.9347 - distribution_lambda_26_loss: 3.1517 - distribution_lambda_27_loss: 2.2166 - distribution_lambda_28_loss: 0.5664 - val_loss: 5.8092 - val_distribution_lambda_26_loss: 3.0984 - val_distribution_lambda_27_loss: 2.1476 - val_distribution_lambda_28_loss: 0.5632\n", "Epoch 155/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.9025 - distribution_lambda_26_loss: 3.1408 - distribution_lambda_27_loss: 2.1963 - distribution_lambda_28_loss: 0.5654 - val_loss: 5.8032 - val_distribution_lambda_26_loss: 3.0954 - val_distribution_lambda_27_loss: 2.1448 - val_distribution_lambda_28_loss: 0.5630\n", "Epoch 156/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.9016 - distribution_lambda_26_loss: 3.1358 - distribution_lambda_27_loss: 2.1995 - distribution_lambda_28_loss: 0.5663 - val_loss: 5.7970 - val_distribution_lambda_26_loss: 3.0924 - val_distribution_lambda_27_loss: 2.1419 - val_distribution_lambda_28_loss: 0.5627\n", "Epoch 157/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.8962 - distribution_lambda_26_loss: 3.1378 - distribution_lambda_27_loss: 2.1971 - distribution_lambda_28_loss: 0.5613 - val_loss: 5.7911 - val_distribution_lambda_26_loss: 3.0895 - val_distribution_lambda_27_loss: 2.1392 - val_distribution_lambda_28_loss: 0.5624\n", "Epoch 158/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.9291 - distribution_lambda_26_loss: 3.1431 - distribution_lambda_27_loss: 2.2264 - distribution_lambda_28_loss: 0.5596 - val_loss: 5.7852 - val_distribution_lambda_26_loss: 3.0865 - val_distribution_lambda_27_loss: 2.1365 - val_distribution_lambda_28_loss: 0.5621\n", "Epoch 159/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.9008 - distribution_lambda_26_loss: 3.1228 - distribution_lambda_27_loss: 2.2164 - distribution_lambda_28_loss: 0.5617 - val_loss: 5.7794 - val_distribution_lambda_26_loss: 3.0836 - val_distribution_lambda_27_loss: 2.1338 - val_distribution_lambda_28_loss: 0.5619\n", "Epoch 160/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.8811 - distribution_lambda_26_loss: 3.1247 - distribution_lambda_27_loss: 2.1900 - distribution_lambda_28_loss: 0.5665 - val_loss: 5.7737 - val_distribution_lambda_26_loss: 3.0807 - val_distribution_lambda_27_loss: 2.1312 - val_distribution_lambda_28_loss: 0.5618\n", "Epoch 161/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.8612 - distribution_lambda_26_loss: 3.1140 - distribution_lambda_27_loss: 2.1856 - distribution_lambda_28_loss: 0.5616 - val_loss: 5.7682 - val_distribution_lambda_26_loss: 3.0779 - val_distribution_lambda_27_loss: 2.1287 - val_distribution_lambda_28_loss: 0.5616\n", "Epoch 162/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.8490 - distribution_lambda_26_loss: 3.1143 - distribution_lambda_27_loss: 2.1726 - distribution_lambda_28_loss: 0.5622 - val_loss: 5.7626 - val_distribution_lambda_26_loss: 3.0751 - val_distribution_lambda_27_loss: 2.1260 - val_distribution_lambda_28_loss: 0.5614\n", "Epoch 163/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.8400 - distribution_lambda_26_loss: 3.1080 - distribution_lambda_27_loss: 2.1710 - distribution_lambda_28_loss: 0.5611 - val_loss: 5.7572 - val_distribution_lambda_26_loss: 3.0724 - val_distribution_lambda_27_loss: 2.1235 - val_distribution_lambda_28_loss: 0.5613\n", "Epoch 164/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.8673 - distribution_lambda_26_loss: 3.1100 - distribution_lambda_27_loss: 2.1942 - distribution_lambda_28_loss: 0.5632 - val_loss: 5.7517 - val_distribution_lambda_26_loss: 3.0696 - val_distribution_lambda_27_loss: 2.1210 - val_distribution_lambda_28_loss: 0.5611\n", "Epoch 165/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.8581 - distribution_lambda_26_loss: 3.1068 - distribution_lambda_27_loss: 2.1911 - distribution_lambda_28_loss: 0.5602 - val_loss: 5.7464 - val_distribution_lambda_26_loss: 3.0669 - val_distribution_lambda_27_loss: 2.1185 - val_distribution_lambda_28_loss: 0.5609\n", "Epoch 166/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.8260 - distribution_lambda_26_loss: 3.1027 - distribution_lambda_27_loss: 2.1638 - distribution_lambda_28_loss: 0.5595 - val_loss: 5.7413 - val_distribution_lambda_26_loss: 3.0642 - val_distribution_lambda_27_loss: 2.1164 - val_distribution_lambda_28_loss: 0.5607\n", "Epoch 167/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.8411 - distribution_lambda_26_loss: 3.1043 - distribution_lambda_27_loss: 2.1745 - distribution_lambda_28_loss: 0.5623 - val_loss: 5.7363 - val_distribution_lambda_26_loss: 3.0615 - val_distribution_lambda_27_loss: 2.1142 - val_distribution_lambda_28_loss: 0.5606\n", "Epoch 168/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.8305 - distribution_lambda_26_loss: 3.0973 - distribution_lambda_27_loss: 2.1731 - distribution_lambda_28_loss: 0.5601 - val_loss: 5.7311 - val_distribution_lambda_26_loss: 3.0588 - val_distribution_lambda_27_loss: 2.1119 - val_distribution_lambda_28_loss: 0.5605\n", "Epoch 169/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 5.8549 - distribution_lambda_26_loss: 3.1014 - distribution_lambda_27_loss: 2.1939 - distribution_lambda_28_loss: 0.5597 - val_loss: 5.7260 - val_distribution_lambda_26_loss: 3.0561 - val_distribution_lambda_27_loss: 2.1096 - val_distribution_lambda_28_loss: 0.5603\n", "Epoch 170/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.8284 - distribution_lambda_26_loss: 3.0923 - distribution_lambda_27_loss: 2.1738 - distribution_lambda_28_loss: 0.5623 - val_loss: 5.7211 - val_distribution_lambda_26_loss: 3.0535 - val_distribution_lambda_27_loss: 2.1075 - val_distribution_lambda_28_loss: 0.5602\n", "Epoch 171/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 5.8032 - distribution_lambda_26_loss: 3.0871 - distribution_lambda_27_loss: 2.1566 - distribution_lambda_28_loss: 0.5595 - val_loss: 5.7165 - val_distribution_lambda_26_loss: 3.0509 - val_distribution_lambda_27_loss: 2.1056 - val_distribution_lambda_28_loss: 0.5601\n", "Epoch 172/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.8121 - distribution_lambda_26_loss: 3.0853 - distribution_lambda_27_loss: 2.1654 - distribution_lambda_28_loss: 0.5614 - val_loss: 5.7119 - val_distribution_lambda_26_loss: 3.0483 - val_distribution_lambda_27_loss: 2.1037 - val_distribution_lambda_28_loss: 0.5599\n", "Epoch 173/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.8025 - distribution_lambda_26_loss: 3.0866 - distribution_lambda_27_loss: 2.1538 - distribution_lambda_28_loss: 0.5620 - val_loss: 5.7073 - val_distribution_lambda_26_loss: 3.0457 - val_distribution_lambda_27_loss: 2.1017 - val_distribution_lambda_28_loss: 0.5599\n", "Epoch 174/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.7760 - distribution_lambda_26_loss: 3.0770 - distribution_lambda_27_loss: 2.1429 - distribution_lambda_28_loss: 0.5561 - val_loss: 5.7028 - val_distribution_lambda_26_loss: 3.0431 - val_distribution_lambda_27_loss: 2.0999 - val_distribution_lambda_28_loss: 0.5597\n", "Epoch 175/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.7941 - distribution_lambda_26_loss: 3.0769 - distribution_lambda_27_loss: 2.1585 - distribution_lambda_28_loss: 0.5587 - val_loss: 5.6981 - val_distribution_lambda_26_loss: 3.0406 - val_distribution_lambda_27_loss: 2.0980 - val_distribution_lambda_28_loss: 0.5596\n", "Epoch 176/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.7763 - distribution_lambda_26_loss: 3.0692 - distribution_lambda_27_loss: 2.1490 - distribution_lambda_28_loss: 0.5580 - val_loss: 5.6934 - val_distribution_lambda_26_loss: 3.0381 - val_distribution_lambda_27_loss: 2.0959 - val_distribution_lambda_28_loss: 0.5594\n", "Epoch 177/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.7925 - distribution_lambda_26_loss: 3.0757 - distribution_lambda_27_loss: 2.1572 - distribution_lambda_28_loss: 0.5595 - val_loss: 5.6889 - val_distribution_lambda_26_loss: 3.0356 - val_distribution_lambda_27_loss: 2.0940 - val_distribution_lambda_28_loss: 0.5593\n", "Epoch 178/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 5.7822 - distribution_lambda_26_loss: 3.0739 - distribution_lambda_27_loss: 2.1511 - distribution_lambda_28_loss: 0.5572 - val_loss: 5.6845 - val_distribution_lambda_26_loss: 3.0331 - val_distribution_lambda_27_loss: 2.0921 - val_distribution_lambda_28_loss: 0.5592\n", "Epoch 179/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 5.7518 - distribution_lambda_26_loss: 3.0646 - distribution_lambda_27_loss: 2.1256 - distribution_lambda_28_loss: 0.5616 - val_loss: 5.6802 - val_distribution_lambda_26_loss: 3.0307 - val_distribution_lambda_27_loss: 2.0904 - val_distribution_lambda_28_loss: 0.5591\n", "Epoch 180/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.7672 - distribution_lambda_26_loss: 3.0642 - distribution_lambda_27_loss: 2.1415 - distribution_lambda_28_loss: 0.5614 - val_loss: 5.6759 - val_distribution_lambda_26_loss: 3.0282 - val_distribution_lambda_27_loss: 2.0887 - val_distribution_lambda_28_loss: 0.5590\n", "Epoch 181/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.7460 - distribution_lambda_26_loss: 3.0576 - distribution_lambda_27_loss: 2.1299 - distribution_lambda_28_loss: 0.5585 - val_loss: 5.6716 - val_distribution_lambda_26_loss: 3.0258 - val_distribution_lambda_27_loss: 2.0871 - val_distribution_lambda_28_loss: 0.5587\n", "Epoch 182/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.7566 - distribution_lambda_26_loss: 3.0564 - distribution_lambda_27_loss: 2.1386 - distribution_lambda_28_loss: 0.5617 - val_loss: 5.6673 - val_distribution_lambda_26_loss: 3.0234 - val_distribution_lambda_27_loss: 2.0853 - val_distribution_lambda_28_loss: 0.5586\n", "Epoch 183/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.7569 - distribution_lambda_26_loss: 3.0610 - distribution_lambda_27_loss: 2.1411 - distribution_lambda_28_loss: 0.5547 - val_loss: 5.6631 - val_distribution_lambda_26_loss: 3.0210 - val_distribution_lambda_27_loss: 2.0838 - val_distribution_lambda_28_loss: 0.5584\n", "Epoch 184/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.7131 - distribution_lambda_26_loss: 3.0527 - distribution_lambda_27_loss: 2.1042 - distribution_lambda_28_loss: 0.5561 - val_loss: 5.6590 - val_distribution_lambda_26_loss: 3.0186 - val_distribution_lambda_27_loss: 2.0821 - val_distribution_lambda_28_loss: 0.5583\n", "Epoch 185/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.7210 - distribution_lambda_26_loss: 3.0469 - distribution_lambda_27_loss: 2.1167 - distribution_lambda_28_loss: 0.5574 - val_loss: 5.6551 - val_distribution_lambda_26_loss: 3.0162 - val_distribution_lambda_27_loss: 2.0807 - val_distribution_lambda_28_loss: 0.5582\n", "Epoch 186/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.7416 - distribution_lambda_26_loss: 3.0454 - distribution_lambda_27_loss: 2.1356 - distribution_lambda_28_loss: 0.5606 - val_loss: 5.6511 - val_distribution_lambda_26_loss: 3.0138 - val_distribution_lambda_27_loss: 2.0791 - val_distribution_lambda_28_loss: 0.5582\n", "Epoch 187/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.7254 - distribution_lambda_26_loss: 3.0443 - distribution_lambda_27_loss: 2.1227 - distribution_lambda_28_loss: 0.5585 - val_loss: 5.6472 - val_distribution_lambda_26_loss: 3.0115 - val_distribution_lambda_27_loss: 2.0776 - val_distribution_lambda_28_loss: 0.5581\n", "Epoch 188/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.7077 - distribution_lambda_26_loss: 3.0387 - distribution_lambda_27_loss: 2.1106 - distribution_lambda_28_loss: 0.5584 - val_loss: 5.6432 - val_distribution_lambda_26_loss: 3.0092 - val_distribution_lambda_27_loss: 2.0760 - val_distribution_lambda_28_loss: 0.5580\n", "Epoch 189/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.7043 - distribution_lambda_26_loss: 3.0371 - distribution_lambda_27_loss: 2.1116 - distribution_lambda_28_loss: 0.5557 - val_loss: 5.6393 - val_distribution_lambda_26_loss: 3.0069 - val_distribution_lambda_27_loss: 2.0746 - val_distribution_lambda_28_loss: 0.5579\n", "Epoch 190/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.7072 - distribution_lambda_26_loss: 3.0410 - distribution_lambda_27_loss: 2.1077 - distribution_lambda_28_loss: 0.5584 - val_loss: 5.6354 - val_distribution_lambda_26_loss: 3.0045 - val_distribution_lambda_27_loss: 2.0731 - val_distribution_lambda_28_loss: 0.5578\n", "Epoch 191/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 5.7156 - distribution_lambda_26_loss: 3.0419 - distribution_lambda_27_loss: 2.1157 - distribution_lambda_28_loss: 0.5580 - val_loss: 5.6314 - val_distribution_lambda_26_loss: 3.0022 - val_distribution_lambda_27_loss: 2.0715 - val_distribution_lambda_28_loss: 0.5577\n", "Epoch 192/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.7023 - distribution_lambda_26_loss: 3.0287 - distribution_lambda_27_loss: 2.1138 - distribution_lambda_28_loss: 0.5597 - val_loss: 5.6275 - val_distribution_lambda_26_loss: 2.9999 - val_distribution_lambda_27_loss: 2.0700 - val_distribution_lambda_28_loss: 0.5576\n", "Epoch 193/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 5.7163 - distribution_lambda_26_loss: 3.0303 - distribution_lambda_27_loss: 2.1293 - distribution_lambda_28_loss: 0.5567 - val_loss: 5.6235 - val_distribution_lambda_26_loss: 2.9976 - val_distribution_lambda_27_loss: 2.0684 - val_distribution_lambda_28_loss: 0.5575\n", "Epoch 194/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.6814 - distribution_lambda_26_loss: 3.0234 - distribution_lambda_27_loss: 2.1016 - distribution_lambda_28_loss: 0.5565 - val_loss: 5.6198 - val_distribution_lambda_26_loss: 2.9953 - val_distribution_lambda_27_loss: 2.0671 - val_distribution_lambda_28_loss: 0.5574\n", "Epoch 195/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.6617 - distribution_lambda_26_loss: 3.0216 - distribution_lambda_27_loss: 2.0872 - distribution_lambda_28_loss: 0.5530 - val_loss: 5.6161 - val_distribution_lambda_26_loss: 2.9931 - val_distribution_lambda_27_loss: 2.0658 - val_distribution_lambda_28_loss: 0.5572\n", "Epoch 196/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.6780 - distribution_lambda_26_loss: 3.0206 - distribution_lambda_27_loss: 2.0986 - distribution_lambda_28_loss: 0.5588 - val_loss: 5.6123 - val_distribution_lambda_26_loss: 2.9908 - val_distribution_lambda_27_loss: 2.0644 - val_distribution_lambda_28_loss: 0.5572\n", "Epoch 197/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.6912 - distribution_lambda_26_loss: 3.0260 - distribution_lambda_27_loss: 2.1096 - distribution_lambda_28_loss: 0.5556 - val_loss: 5.6084 - val_distribution_lambda_26_loss: 2.9885 - val_distribution_lambda_27_loss: 2.0628 - val_distribution_lambda_28_loss: 0.5570\n", "Epoch 198/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.6718 - distribution_lambda_26_loss: 3.0166 - distribution_lambda_27_loss: 2.1010 - distribution_lambda_28_loss: 0.5541 - val_loss: 5.6046 - val_distribution_lambda_26_loss: 2.9863 - val_distribution_lambda_27_loss: 2.0614 - val_distribution_lambda_28_loss: 0.5569\n", "Epoch 199/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.6668 - distribution_lambda_26_loss: 3.0131 - distribution_lambda_27_loss: 2.0956 - distribution_lambda_28_loss: 0.5581 - val_loss: 5.6008 - val_distribution_lambda_26_loss: 2.9841 - val_distribution_lambda_27_loss: 2.0599 - val_distribution_lambda_28_loss: 0.5568\n", "Epoch 200/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.6588 - distribution_lambda_26_loss: 3.0117 - distribution_lambda_27_loss: 2.0898 - distribution_lambda_28_loss: 0.5573 - val_loss: 5.5971 - val_distribution_lambda_26_loss: 2.9818 - val_distribution_lambda_27_loss: 2.0586 - val_distribution_lambda_28_loss: 0.5568\n", "Epoch 201/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 5.6729 - distribution_lambda_26_loss: 3.0113 - distribution_lambda_27_loss: 2.1067 - distribution_lambda_28_loss: 0.5549 - val_loss: 5.5934 - val_distribution_lambda_26_loss: 2.9796 - val_distribution_lambda_27_loss: 2.0571 - val_distribution_lambda_28_loss: 0.5567\n", "Epoch 202/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 5.6901 - distribution_lambda_26_loss: 3.0077 - distribution_lambda_27_loss: 2.1280 - distribution_lambda_28_loss: 0.5544 - val_loss: 5.5896 - val_distribution_lambda_26_loss: 2.9774 - val_distribution_lambda_27_loss: 2.0556 - val_distribution_lambda_28_loss: 0.5566\n", "Epoch 203/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.6398 - distribution_lambda_26_loss: 3.0039 - distribution_lambda_27_loss: 2.0808 - distribution_lambda_28_loss: 0.5550 - val_loss: 5.5860 - val_distribution_lambda_26_loss: 2.9752 - val_distribution_lambda_27_loss: 2.0543 - val_distribution_lambda_28_loss: 0.5565\n", "Epoch 204/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.6561 - distribution_lambda_26_loss: 3.0048 - distribution_lambda_27_loss: 2.0957 - distribution_lambda_28_loss: 0.5556 - val_loss: 5.5823 - val_distribution_lambda_26_loss: 2.9730 - val_distribution_lambda_27_loss: 2.0529 - val_distribution_lambda_28_loss: 0.5564\n", "Epoch 205/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.6183 - distribution_lambda_26_loss: 2.9929 - distribution_lambda_27_loss: 2.0698 - distribution_lambda_28_loss: 0.5557 - val_loss: 5.5787 - val_distribution_lambda_26_loss: 2.9708 - val_distribution_lambda_27_loss: 2.0516 - val_distribution_lambda_28_loss: 0.5563\n", "Epoch 206/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.6400 - distribution_lambda_26_loss: 3.0027 - distribution_lambda_27_loss: 2.0827 - distribution_lambda_28_loss: 0.5546 - val_loss: 5.5751 - val_distribution_lambda_26_loss: 2.9686 - val_distribution_lambda_27_loss: 2.0503 - val_distribution_lambda_28_loss: 0.5561\n", "Epoch 207/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.6294 - distribution_lambda_26_loss: 2.9966 - distribution_lambda_27_loss: 2.0829 - distribution_lambda_28_loss: 0.5499 - val_loss: 5.5715 - val_distribution_lambda_26_loss: 2.9664 - val_distribution_lambda_27_loss: 2.0491 - val_distribution_lambda_28_loss: 0.5559\n", "Epoch 208/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.6165 - distribution_lambda_26_loss: 2.9874 - distribution_lambda_27_loss: 2.0703 - distribution_lambda_28_loss: 0.5587 - val_loss: 5.5679 - val_distribution_lambda_26_loss: 2.9643 - val_distribution_lambda_27_loss: 2.0478 - val_distribution_lambda_28_loss: 0.5558\n", "Epoch 209/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.6372 - distribution_lambda_26_loss: 2.9928 - distribution_lambda_27_loss: 2.0925 - distribution_lambda_28_loss: 0.5519 - val_loss: 5.5643 - val_distribution_lambda_26_loss: 2.9621 - val_distribution_lambda_27_loss: 2.0464 - val_distribution_lambda_28_loss: 0.5557\n", "Epoch 210/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.6111 - distribution_lambda_26_loss: 2.9820 - distribution_lambda_27_loss: 2.0733 - distribution_lambda_28_loss: 0.5559 - val_loss: 5.5605 - val_distribution_lambda_26_loss: 2.9600 - val_distribution_lambda_27_loss: 2.0449 - val_distribution_lambda_28_loss: 0.5557\n", "Epoch 211/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.6369 - distribution_lambda_26_loss: 2.9847 - distribution_lambda_27_loss: 2.0992 - distribution_lambda_28_loss: 0.5530 - val_loss: 5.5567 - val_distribution_lambda_26_loss: 2.9578 - val_distribution_lambda_27_loss: 2.0433 - val_distribution_lambda_28_loss: 0.5556\n", "Epoch 212/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.6148 - distribution_lambda_26_loss: 2.9878 - distribution_lambda_27_loss: 2.0730 - distribution_lambda_28_loss: 0.5540 - val_loss: 5.5532 - val_distribution_lambda_26_loss: 2.9557 - val_distribution_lambda_27_loss: 2.0419 - val_distribution_lambda_28_loss: 0.5556\n", "Epoch 213/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.6249 - distribution_lambda_26_loss: 2.9842 - distribution_lambda_27_loss: 2.0884 - distribution_lambda_28_loss: 0.5523 - val_loss: 5.5495 - val_distribution_lambda_26_loss: 2.9535 - val_distribution_lambda_27_loss: 2.0406 - val_distribution_lambda_28_loss: 0.5554\n", "Epoch 214/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.6259 - distribution_lambda_26_loss: 2.9809 - distribution_lambda_27_loss: 2.0968 - distribution_lambda_28_loss: 0.5482 - val_loss: 5.5455 - val_distribution_lambda_26_loss: 2.9513 - val_distribution_lambda_27_loss: 2.0389 - val_distribution_lambda_28_loss: 0.5552\n", "Epoch 215/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.5844 - distribution_lambda_26_loss: 2.9730 - distribution_lambda_27_loss: 2.0569 - distribution_lambda_28_loss: 0.5545 - val_loss: 5.5418 - val_distribution_lambda_26_loss: 2.9492 - val_distribution_lambda_27_loss: 2.0376 - val_distribution_lambda_28_loss: 0.5550\n", "Epoch 216/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.5720 - distribution_lambda_26_loss: 2.9728 - distribution_lambda_27_loss: 2.0448 - distribution_lambda_28_loss: 0.5543 - val_loss: 5.5383 - val_distribution_lambda_26_loss: 2.9471 - val_distribution_lambda_27_loss: 2.0363 - val_distribution_lambda_28_loss: 0.5549\n", "Epoch 217/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 5.5990 - distribution_lambda_26_loss: 2.9679 - distribution_lambda_27_loss: 2.0818 - distribution_lambda_28_loss: 0.5493 - val_loss: 5.5349 - val_distribution_lambda_26_loss: 2.9449 - val_distribution_lambda_27_loss: 2.0351 - val_distribution_lambda_28_loss: 0.5548\n", "Epoch 218/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.5639 - distribution_lambda_26_loss: 2.9647 - distribution_lambda_27_loss: 2.0469 - distribution_lambda_28_loss: 0.5523 - val_loss: 5.5313 - val_distribution_lambda_26_loss: 2.9428 - val_distribution_lambda_27_loss: 2.0338 - val_distribution_lambda_28_loss: 0.5547\n", "Epoch 219/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.5621 - distribution_lambda_26_loss: 2.9656 - distribution_lambda_27_loss: 2.0419 - distribution_lambda_28_loss: 0.5546 - val_loss: 5.5279 - val_distribution_lambda_26_loss: 2.9407 - val_distribution_lambda_27_loss: 2.0326 - val_distribution_lambda_28_loss: 0.5546\n", "Epoch 220/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.5914 - distribution_lambda_26_loss: 2.9622 - distribution_lambda_27_loss: 2.0757 - distribution_lambda_28_loss: 0.5535 - val_loss: 5.5246 - val_distribution_lambda_26_loss: 2.9386 - val_distribution_lambda_27_loss: 2.0314 - val_distribution_lambda_28_loss: 0.5546\n", "Epoch 221/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.5614 - distribution_lambda_26_loss: 2.9646 - distribution_lambda_27_loss: 2.0439 - distribution_lambda_28_loss: 0.5529 - val_loss: 5.5213 - val_distribution_lambda_26_loss: 2.9365 - val_distribution_lambda_27_loss: 2.0304 - val_distribution_lambda_28_loss: 0.5545\n", "Epoch 222/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.5668 - distribution_lambda_26_loss: 2.9603 - distribution_lambda_27_loss: 2.0584 - distribution_lambda_28_loss: 0.5481 - val_loss: 5.5179 - val_distribution_lambda_26_loss: 2.9343 - val_distribution_lambda_27_loss: 2.0291 - val_distribution_lambda_28_loss: 0.5544\n", "Epoch 223/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.5697 - distribution_lambda_26_loss: 2.9570 - distribution_lambda_27_loss: 2.0623 - distribution_lambda_28_loss: 0.5503 - val_loss: 5.5143 - val_distribution_lambda_26_loss: 2.9322 - val_distribution_lambda_27_loss: 2.0278 - val_distribution_lambda_28_loss: 0.5543\n", "Epoch 224/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.5893 - distribution_lambda_26_loss: 2.9595 - distribution_lambda_27_loss: 2.0783 - distribution_lambda_28_loss: 0.5515 - val_loss: 5.5109 - val_distribution_lambda_26_loss: 2.9301 - val_distribution_lambda_27_loss: 2.0266 - val_distribution_lambda_28_loss: 0.5542\n", "Epoch 225/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.5722 - distribution_lambda_26_loss: 2.9538 - distribution_lambda_27_loss: 2.0624 - distribution_lambda_28_loss: 0.5560 - val_loss: 5.5075 - val_distribution_lambda_26_loss: 2.9279 - val_distribution_lambda_27_loss: 2.0255 - val_distribution_lambda_28_loss: 0.5541\n", "Epoch 226/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.5900 - distribution_lambda_26_loss: 2.9602 - distribution_lambda_27_loss: 2.0782 - distribution_lambda_28_loss: 0.5516 - val_loss: 5.5043 - val_distribution_lambda_26_loss: 2.9258 - val_distribution_lambda_27_loss: 2.0244 - val_distribution_lambda_28_loss: 0.5541\n", "Epoch 227/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.5387 - distribution_lambda_26_loss: 2.9479 - distribution_lambda_27_loss: 2.0406 - distribution_lambda_28_loss: 0.5502 - val_loss: 5.5009 - val_distribution_lambda_26_loss: 2.9237 - val_distribution_lambda_27_loss: 2.0232 - val_distribution_lambda_28_loss: 0.5540\n", "Epoch 228/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.5283 - distribution_lambda_26_loss: 2.9409 - distribution_lambda_27_loss: 2.0366 - distribution_lambda_28_loss: 0.5508 - val_loss: 5.4975 - val_distribution_lambda_26_loss: 2.9216 - val_distribution_lambda_27_loss: 2.0220 - val_distribution_lambda_28_loss: 0.5540\n", "Epoch 229/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.5524 - distribution_lambda_26_loss: 2.9467 - distribution_lambda_27_loss: 2.0495 - distribution_lambda_28_loss: 0.5561 - val_loss: 5.4940 - val_distribution_lambda_26_loss: 2.9195 - val_distribution_lambda_27_loss: 2.0206 - val_distribution_lambda_28_loss: 0.5539\n", "Epoch 230/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.5513 - distribution_lambda_26_loss: 2.9435 - distribution_lambda_27_loss: 2.0592 - distribution_lambda_28_loss: 0.5486 - val_loss: 5.4905 - val_distribution_lambda_26_loss: 2.9173 - val_distribution_lambda_27_loss: 2.0193 - val_distribution_lambda_28_loss: 0.5539\n", "Epoch 231/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.5481 - distribution_lambda_26_loss: 2.9455 - distribution_lambda_27_loss: 2.0495 - distribution_lambda_28_loss: 0.5531 - val_loss: 5.4869 - val_distribution_lambda_26_loss: 2.9152 - val_distribution_lambda_27_loss: 2.0179 - val_distribution_lambda_28_loss: 0.5537\n", "Epoch 232/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.5492 - distribution_lambda_26_loss: 2.9392 - distribution_lambda_27_loss: 2.0598 - distribution_lambda_28_loss: 0.5502 - val_loss: 5.4833 - val_distribution_lambda_26_loss: 2.9131 - val_distribution_lambda_27_loss: 2.0165 - val_distribution_lambda_28_loss: 0.5536\n", "Epoch 233/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.5333 - distribution_lambda_26_loss: 2.9380 - distribution_lambda_27_loss: 2.0438 - distribution_lambda_28_loss: 0.5516 - val_loss: 5.4798 - val_distribution_lambda_26_loss: 2.9110 - val_distribution_lambda_27_loss: 2.0153 - val_distribution_lambda_28_loss: 0.5535\n", "Epoch 234/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.5236 - distribution_lambda_26_loss: 2.9358 - distribution_lambda_27_loss: 2.0342 - distribution_lambda_28_loss: 0.5536 - val_loss: 5.4763 - val_distribution_lambda_26_loss: 2.9089 - val_distribution_lambda_27_loss: 2.0140 - val_distribution_lambda_28_loss: 0.5534\n", "Epoch 235/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.5030 - distribution_lambda_26_loss: 2.9267 - distribution_lambda_27_loss: 2.0261 - distribution_lambda_28_loss: 0.5502 - val_loss: 5.4726 - val_distribution_lambda_26_loss: 2.9067 - val_distribution_lambda_27_loss: 2.0126 - val_distribution_lambda_28_loss: 0.5533\n", "Epoch 236/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.4961 - distribution_lambda_26_loss: 2.9268 - distribution_lambda_27_loss: 2.0187 - distribution_lambda_28_loss: 0.5506 - val_loss: 5.4692 - val_distribution_lambda_26_loss: 2.9046 - val_distribution_lambda_27_loss: 2.0114 - val_distribution_lambda_28_loss: 0.5532\n", "Epoch 237/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.4963 - distribution_lambda_26_loss: 2.9263 - distribution_lambda_27_loss: 2.0204 - distribution_lambda_28_loss: 0.5496 - val_loss: 5.4656 - val_distribution_lambda_26_loss: 2.9025 - val_distribution_lambda_27_loss: 2.0100 - val_distribution_lambda_28_loss: 0.5531\n", "Epoch 238/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.5490 - distribution_lambda_26_loss: 2.9236 - distribution_lambda_27_loss: 2.0745 - distribution_lambda_28_loss: 0.5508 - val_loss: 5.4619 - val_distribution_lambda_26_loss: 2.9004 - val_distribution_lambda_27_loss: 2.0085 - val_distribution_lambda_28_loss: 0.5529\n", "Epoch 239/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.4974 - distribution_lambda_26_loss: 2.9191 - distribution_lambda_27_loss: 2.0285 - distribution_lambda_28_loss: 0.5497 - val_loss: 5.4581 - val_distribution_lambda_26_loss: 2.8983 - val_distribution_lambda_27_loss: 2.0069 - val_distribution_lambda_28_loss: 0.5529\n", "Epoch 240/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.5136 - distribution_lambda_26_loss: 2.9248 - distribution_lambda_27_loss: 2.0320 - distribution_lambda_28_loss: 0.5568 - val_loss: 5.4546 - val_distribution_lambda_26_loss: 2.8962 - val_distribution_lambda_27_loss: 2.0056 - val_distribution_lambda_28_loss: 0.5528\n", "Epoch 241/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 5.4933 - distribution_lambda_26_loss: 2.9149 - distribution_lambda_27_loss: 2.0280 - distribution_lambda_28_loss: 0.5503 - val_loss: 5.4510 - val_distribution_lambda_26_loss: 2.8941 - val_distribution_lambda_27_loss: 2.0042 - val_distribution_lambda_28_loss: 0.5527\n", "Epoch 242/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.4970 - distribution_lambda_26_loss: 2.9121 - distribution_lambda_27_loss: 2.0347 - distribution_lambda_28_loss: 0.5502 - val_loss: 5.4474 - val_distribution_lambda_26_loss: 2.8920 - val_distribution_lambda_27_loss: 2.0027 - val_distribution_lambda_28_loss: 0.5528\n", "Epoch 243/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.4949 - distribution_lambda_26_loss: 2.9142 - distribution_lambda_27_loss: 2.0293 - distribution_lambda_28_loss: 0.5514 - val_loss: 5.4438 - val_distribution_lambda_26_loss: 2.8898 - val_distribution_lambda_27_loss: 2.0013 - val_distribution_lambda_28_loss: 0.5527\n", "Epoch 244/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.4918 - distribution_lambda_26_loss: 2.9132 - distribution_lambda_27_loss: 2.0283 - distribution_lambda_28_loss: 0.5503 - val_loss: 5.4402 - val_distribution_lambda_26_loss: 2.8877 - val_distribution_lambda_27_loss: 1.9999 - val_distribution_lambda_28_loss: 0.5526\n", "Epoch 245/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.4831 - distribution_lambda_26_loss: 2.9084 - distribution_lambda_27_loss: 2.0272 - distribution_lambda_28_loss: 0.5475 - val_loss: 5.4368 - val_distribution_lambda_26_loss: 2.8856 - val_distribution_lambda_27_loss: 1.9987 - val_distribution_lambda_28_loss: 0.5525\n", "Epoch 246/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.4677 - distribution_lambda_26_loss: 2.9064 - distribution_lambda_27_loss: 2.0108 - distribution_lambda_28_loss: 0.5506 - val_loss: 5.4330 - val_distribution_lambda_26_loss: 2.8834 - val_distribution_lambda_27_loss: 1.9971 - val_distribution_lambda_28_loss: 0.5524\n", "Epoch 247/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.4641 - distribution_lambda_26_loss: 2.9020 - distribution_lambda_27_loss: 2.0159 - distribution_lambda_28_loss: 0.5462 - val_loss: 5.4295 - val_distribution_lambda_26_loss: 2.8813 - val_distribution_lambda_27_loss: 1.9958 - val_distribution_lambda_28_loss: 0.5524\n", "Epoch 248/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 5.4622 - distribution_lambda_26_loss: 2.9051 - distribution_lambda_27_loss: 2.0090 - distribution_lambda_28_loss: 0.5481 - val_loss: 5.4263 - val_distribution_lambda_26_loss: 2.8791 - val_distribution_lambda_27_loss: 1.9948 - val_distribution_lambda_28_loss: 0.5523\n", "Epoch 249/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.4505 - distribution_lambda_26_loss: 2.8962 - distribution_lambda_27_loss: 2.0040 - distribution_lambda_28_loss: 0.5503 - val_loss: 5.4229 - val_distribution_lambda_26_loss: 2.8770 - val_distribution_lambda_27_loss: 1.9935 - val_distribution_lambda_28_loss: 0.5524\n", "Epoch 250/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.4577 - distribution_lambda_26_loss: 2.8953 - distribution_lambda_27_loss: 2.0160 - distribution_lambda_28_loss: 0.5464 - val_loss: 5.4194 - val_distribution_lambda_26_loss: 2.8749 - val_distribution_lambda_27_loss: 1.9923 - val_distribution_lambda_28_loss: 0.5523\n", "Epoch 251/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.4813 - distribution_lambda_26_loss: 2.8955 - distribution_lambda_27_loss: 2.0351 - distribution_lambda_28_loss: 0.5507 - val_loss: 5.4161 - val_distribution_lambda_26_loss: 2.8727 - val_distribution_lambda_27_loss: 1.9912 - val_distribution_lambda_28_loss: 0.5522\n", "Epoch 252/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.4420 - distribution_lambda_26_loss: 2.8945 - distribution_lambda_27_loss: 1.9973 - distribution_lambda_28_loss: 0.5502 - val_loss: 5.4126 - val_distribution_lambda_26_loss: 2.8705 - val_distribution_lambda_27_loss: 1.9899 - val_distribution_lambda_28_loss: 0.5522\n", "Epoch 253/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.4392 - distribution_lambda_26_loss: 2.8870 - distribution_lambda_27_loss: 2.0047 - distribution_lambda_28_loss: 0.5476 - val_loss: 5.4089 - val_distribution_lambda_26_loss: 2.8684 - val_distribution_lambda_27_loss: 1.9884 - val_distribution_lambda_28_loss: 0.5521\n", "Epoch 254/2500\n", "8/8 [==============================] - 0s 12ms/step - loss: 5.4326 - distribution_lambda_26_loss: 2.8895 - distribution_lambda_27_loss: 1.9955 - distribution_lambda_28_loss: 0.5475 - val_loss: 5.4050 - val_distribution_lambda_26_loss: 2.8662 - val_distribution_lambda_27_loss: 1.9868 - val_distribution_lambda_28_loss: 0.5520\n", "Epoch 255/2500\n", "8/8 [==============================] - 0s 10ms/step - loss: 5.4582 - distribution_lambda_26_loss: 2.8938 - distribution_lambda_27_loss: 2.0174 - distribution_lambda_28_loss: 0.5470 - val_loss: 5.4012 - val_distribution_lambda_26_loss: 2.8641 - val_distribution_lambda_27_loss: 1.9853 - val_distribution_lambda_28_loss: 0.5519\n", "Epoch 256/2500\n", "8/8 [==============================] - 0s 8ms/step - loss: 5.4370 - distribution_lambda_26_loss: 2.8834 - distribution_lambda_27_loss: 2.0053 - distribution_lambda_28_loss: 0.5483 - val_loss: 5.3972 - val_distribution_lambda_26_loss: 2.8619 - val_distribution_lambda_27_loss: 1.9836 - val_distribution_lambda_28_loss: 0.5517\n", "Epoch 257/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.4342 - distribution_lambda_26_loss: 2.8797 - distribution_lambda_27_loss: 2.0100 - distribution_lambda_28_loss: 0.5445 - val_loss: 5.3935 - val_distribution_lambda_26_loss: 2.8597 - val_distribution_lambda_27_loss: 1.9820 - val_distribution_lambda_28_loss: 0.5518\n", "Epoch 258/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 5.4209 - distribution_lambda_26_loss: 2.8801 - distribution_lambda_27_loss: 1.9954 - distribution_lambda_28_loss: 0.5455 - val_loss: 5.3902 - val_distribution_lambda_26_loss: 2.8575 - val_distribution_lambda_27_loss: 1.9809 - val_distribution_lambda_28_loss: 0.5517\n", "Epoch 259/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.4172 - distribution_lambda_26_loss: 2.8801 - distribution_lambda_27_loss: 1.9881 - distribution_lambda_28_loss: 0.5490 - val_loss: 5.3868 - val_distribution_lambda_26_loss: 2.8553 - val_distribution_lambda_27_loss: 1.9797 - val_distribution_lambda_28_loss: 0.5517\n", "Epoch 260/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.4378 - distribution_lambda_26_loss: 2.8796 - distribution_lambda_27_loss: 2.0091 - distribution_lambda_28_loss: 0.5490 - val_loss: 5.3830 - val_distribution_lambda_26_loss: 2.8531 - val_distribution_lambda_27_loss: 1.9782 - val_distribution_lambda_28_loss: 0.5517\n", "Epoch 261/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 5.4026 - distribution_lambda_26_loss: 2.8714 - distribution_lambda_27_loss: 1.9829 - distribution_lambda_28_loss: 0.5483 - val_loss: 5.3796 - val_distribution_lambda_26_loss: 2.8509 - val_distribution_lambda_27_loss: 1.9770 - val_distribution_lambda_28_loss: 0.5517\n", "Epoch 262/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 5.4168 - distribution_lambda_26_loss: 2.8679 - distribution_lambda_27_loss: 1.9992 - distribution_lambda_28_loss: 0.5496 - val_loss: 5.3758 - val_distribution_lambda_26_loss: 2.8487 - val_distribution_lambda_27_loss: 1.9754 - val_distribution_lambda_28_loss: 0.5517\n", "Epoch 263/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 5.4089 - distribution_lambda_26_loss: 2.8653 - distribution_lambda_27_loss: 1.9960 - distribution_lambda_28_loss: 0.5476 - val_loss: 5.3723 - val_distribution_lambda_26_loss: 2.8465 - val_distribution_lambda_27_loss: 1.9740 - val_distribution_lambda_28_loss: 0.5517\n", "Epoch 264/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 5.4039 - distribution_lambda_26_loss: 2.8657 - distribution_lambda_27_loss: 1.9880 - distribution_lambda_28_loss: 0.5502 - val_loss: 5.3688 - val_distribution_lambda_26_loss: 2.8443 - val_distribution_lambda_27_loss: 1.9728 - val_distribution_lambda_28_loss: 0.5517\n", "Epoch 265/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 7ms/step - loss: 5.4131 - distribution_lambda_26_loss: 2.8648 - distribution_lambda_27_loss: 2.0029 - distribution_lambda_28_loss: 0.5455 - val_loss: 5.3653 - val_distribution_lambda_26_loss: 2.8421 - val_distribution_lambda_27_loss: 1.9716 - val_distribution_lambda_28_loss: 0.5516\n", "Epoch 266/2500\n", "8/8 [==============================] - 0s 8ms/step - loss: 5.3878 - distribution_lambda_26_loss: 2.8584 - distribution_lambda_27_loss: 1.9777 - distribution_lambda_28_loss: 0.5518 - val_loss: 5.3613 - val_distribution_lambda_26_loss: 2.8399 - val_distribution_lambda_27_loss: 1.9699 - val_distribution_lambda_28_loss: 0.5515\n", "Epoch 267/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 5.4038 - distribution_lambda_26_loss: 2.8583 - distribution_lambda_27_loss: 1.9958 - distribution_lambda_28_loss: 0.5497 - val_loss: 5.3574 - val_distribution_lambda_26_loss: 2.8377 - val_distribution_lambda_27_loss: 1.9682 - val_distribution_lambda_28_loss: 0.5516\n", "Epoch 268/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.4231 - distribution_lambda_26_loss: 2.8608 - distribution_lambda_27_loss: 2.0128 - distribution_lambda_28_loss: 0.5495 - val_loss: 5.3538 - val_distribution_lambda_26_loss: 2.8354 - val_distribution_lambda_27_loss: 1.9668 - val_distribution_lambda_28_loss: 0.5515\n", "Epoch 269/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 5.3826 - distribution_lambda_26_loss: 2.8502 - distribution_lambda_27_loss: 1.9854 - distribution_lambda_28_loss: 0.5470 - val_loss: 5.3503 - val_distribution_lambda_26_loss: 2.8332 - val_distribution_lambda_27_loss: 1.9656 - val_distribution_lambda_28_loss: 0.5515\n", "Epoch 270/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.3678 - distribution_lambda_26_loss: 2.8497 - distribution_lambda_27_loss: 1.9753 - distribution_lambda_28_loss: 0.5428 - val_loss: 5.3467 - val_distribution_lambda_26_loss: 2.8309 - val_distribution_lambda_27_loss: 1.9644 - val_distribution_lambda_28_loss: 0.5514\n", "Epoch 271/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.3741 - distribution_lambda_26_loss: 2.8492 - distribution_lambda_27_loss: 1.9848 - distribution_lambda_28_loss: 0.5401 - val_loss: 5.3430 - val_distribution_lambda_26_loss: 2.8287 - val_distribution_lambda_27_loss: 1.9630 - val_distribution_lambda_28_loss: 0.5514\n", "Epoch 272/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.3615 - distribution_lambda_26_loss: 2.8463 - distribution_lambda_27_loss: 1.9719 - distribution_lambda_28_loss: 0.5432 - val_loss: 5.3390 - val_distribution_lambda_26_loss: 2.8264 - val_distribution_lambda_27_loss: 1.9613 - val_distribution_lambda_28_loss: 0.5513\n", "Epoch 273/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.3622 - distribution_lambda_26_loss: 2.8455 - distribution_lambda_27_loss: 1.9691 - distribution_lambda_28_loss: 0.5476 - val_loss: 5.3350 - val_distribution_lambda_26_loss: 2.8241 - val_distribution_lambda_27_loss: 1.9596 - val_distribution_lambda_28_loss: 0.5513\n", "Epoch 274/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.3657 - distribution_lambda_26_loss: 2.8403 - distribution_lambda_27_loss: 1.9772 - distribution_lambda_28_loss: 0.5482 - val_loss: 5.3308 - val_distribution_lambda_26_loss: 2.8219 - val_distribution_lambda_27_loss: 1.9578 - val_distribution_lambda_28_loss: 0.5511\n", "Epoch 275/2500\n", "8/8 [==============================] - 0s 8ms/step - loss: 5.3588 - distribution_lambda_26_loss: 2.8368 - distribution_lambda_27_loss: 1.9758 - distribution_lambda_28_loss: 0.5462 - val_loss: 5.3267 - val_distribution_lambda_26_loss: 2.8196 - val_distribution_lambda_27_loss: 1.9561 - val_distribution_lambda_28_loss: 0.5510\n", "Epoch 276/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.3475 - distribution_lambda_26_loss: 2.8373 - distribution_lambda_27_loss: 1.9630 - distribution_lambda_28_loss: 0.5472 - val_loss: 5.3231 - val_distribution_lambda_26_loss: 2.8173 - val_distribution_lambda_27_loss: 1.9548 - val_distribution_lambda_28_loss: 0.5510\n", "Epoch 277/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.3629 - distribution_lambda_26_loss: 2.8327 - distribution_lambda_27_loss: 1.9826 - distribution_lambda_28_loss: 0.5477 - val_loss: 5.3195 - val_distribution_lambda_26_loss: 2.8150 - val_distribution_lambda_27_loss: 1.9535 - val_distribution_lambda_28_loss: 0.5511\n", "Epoch 278/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.3547 - distribution_lambda_26_loss: 2.8314 - distribution_lambda_27_loss: 1.9749 - distribution_lambda_28_loss: 0.5484 - val_loss: 5.3158 - val_distribution_lambda_26_loss: 2.8127 - val_distribution_lambda_27_loss: 1.9520 - val_distribution_lambda_28_loss: 0.5511\n", "Epoch 279/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.3517 - distribution_lambda_26_loss: 2.8331 - distribution_lambda_27_loss: 1.9708 - distribution_lambda_28_loss: 0.5479 - val_loss: 5.3119 - val_distribution_lambda_26_loss: 2.8104 - val_distribution_lambda_27_loss: 1.9505 - val_distribution_lambda_28_loss: 0.5510\n", "Epoch 280/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 5.3429 - distribution_lambda_26_loss: 2.8290 - distribution_lambda_27_loss: 1.9699 - distribution_lambda_28_loss: 0.5439 - val_loss: 5.3081 - val_distribution_lambda_26_loss: 2.8080 - val_distribution_lambda_27_loss: 1.9491 - val_distribution_lambda_28_loss: 0.5510\n", "Epoch 281/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.3504 - distribution_lambda_26_loss: 2.8299 - distribution_lambda_27_loss: 1.9741 - distribution_lambda_28_loss: 0.5464 - val_loss: 5.3042 - val_distribution_lambda_26_loss: 2.8057 - val_distribution_lambda_27_loss: 1.9476 - val_distribution_lambda_28_loss: 0.5509\n", "Epoch 282/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.3580 - distribution_lambda_26_loss: 2.8234 - distribution_lambda_27_loss: 1.9875 - distribution_lambda_28_loss: 0.5471 - val_loss: 5.3000 - val_distribution_lambda_26_loss: 2.8034 - val_distribution_lambda_27_loss: 1.9457 - val_distribution_lambda_28_loss: 0.5510\n", "Epoch 283/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.3440 - distribution_lambda_26_loss: 2.8204 - distribution_lambda_27_loss: 1.9787 - distribution_lambda_28_loss: 0.5449 - val_loss: 5.2963 - val_distribution_lambda_26_loss: 2.8010 - val_distribution_lambda_27_loss: 1.9443 - val_distribution_lambda_28_loss: 0.5510\n", "Epoch 284/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.3394 - distribution_lambda_26_loss: 2.8160 - distribution_lambda_27_loss: 1.9764 - distribution_lambda_28_loss: 0.5470 - val_loss: 5.2926 - val_distribution_lambda_26_loss: 2.7986 - val_distribution_lambda_27_loss: 1.9428 - val_distribution_lambda_28_loss: 0.5512\n", "Epoch 285/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 5.3119 - distribution_lambda_26_loss: 2.8166 - distribution_lambda_27_loss: 1.9512 - distribution_lambda_28_loss: 0.5441 - val_loss: 5.2886 - val_distribution_lambda_26_loss: 2.7963 - val_distribution_lambda_27_loss: 1.9413 - val_distribution_lambda_28_loss: 0.5511\n", "Epoch 286/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.3433 - distribution_lambda_26_loss: 2.8184 - distribution_lambda_27_loss: 1.9758 - distribution_lambda_28_loss: 0.5492 - val_loss: 5.2847 - val_distribution_lambda_26_loss: 2.7939 - val_distribution_lambda_27_loss: 1.9396 - val_distribution_lambda_28_loss: 0.5512\n", "Epoch 287/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.3138 - distribution_lambda_26_loss: 2.8094 - distribution_lambda_27_loss: 1.9555 - distribution_lambda_28_loss: 0.5489 - val_loss: 5.2807 - val_distribution_lambda_26_loss: 2.7915 - val_distribution_lambda_27_loss: 1.9381 - val_distribution_lambda_28_loss: 0.5510\n", "Epoch 288/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 5.3188 - distribution_lambda_26_loss: 2.8080 - distribution_lambda_27_loss: 1.9621 - distribution_lambda_28_loss: 0.5486 - val_loss: 5.2766 - val_distribution_lambda_26_loss: 2.7891 - val_distribution_lambda_27_loss: 1.9364 - val_distribution_lambda_28_loss: 0.5510\n", "Epoch 289/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 5.3148 - distribution_lambda_26_loss: 2.8050 - distribution_lambda_27_loss: 1.9621 - distribution_lambda_28_loss: 0.5476 - val_loss: 5.2723 - val_distribution_lambda_26_loss: 2.7867 - val_distribution_lambda_27_loss: 1.9346 - val_distribution_lambda_28_loss: 0.5511\n", "Epoch 290/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.3096 - distribution_lambda_26_loss: 2.8030 - distribution_lambda_27_loss: 1.9591 - distribution_lambda_28_loss: 0.5476 - val_loss: 5.2682 - val_distribution_lambda_26_loss: 2.7843 - val_distribution_lambda_27_loss: 1.9329 - val_distribution_lambda_28_loss: 0.5510\n", "Epoch 291/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.2874 - distribution_lambda_26_loss: 2.8080 - distribution_lambda_27_loss: 1.9343 - distribution_lambda_28_loss: 0.5451 - val_loss: 5.2642 - val_distribution_lambda_26_loss: 2.7818 - val_distribution_lambda_27_loss: 1.9315 - val_distribution_lambda_28_loss: 0.5508\n", "Epoch 292/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.2927 - distribution_lambda_26_loss: 2.8010 - distribution_lambda_27_loss: 1.9440 - distribution_lambda_28_loss: 0.5476 - val_loss: 5.2607 - val_distribution_lambda_26_loss: 2.7794 - val_distribution_lambda_27_loss: 1.9306 - val_distribution_lambda_28_loss: 0.5508\n", "Epoch 293/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.2689 - distribution_lambda_26_loss: 2.7942 - distribution_lambda_27_loss: 1.9279 - distribution_lambda_28_loss: 0.5467 - val_loss: 5.2569 - val_distribution_lambda_26_loss: 2.7769 - val_distribution_lambda_27_loss: 1.9293 - val_distribution_lambda_28_loss: 0.5507\n", "Epoch 294/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.2909 - distribution_lambda_26_loss: 2.7962 - distribution_lambda_27_loss: 1.9457 - distribution_lambda_28_loss: 0.5490 - val_loss: 5.2529 - val_distribution_lambda_26_loss: 2.7744 - val_distribution_lambda_27_loss: 1.9278 - val_distribution_lambda_28_loss: 0.5506\n", "Epoch 295/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.2771 - distribution_lambda_26_loss: 2.7905 - distribution_lambda_27_loss: 1.9449 - distribution_lambda_28_loss: 0.5417 - val_loss: 5.2487 - val_distribution_lambda_26_loss: 2.7720 - val_distribution_lambda_27_loss: 1.9261 - val_distribution_lambda_28_loss: 0.5506\n", "Epoch 296/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.2774 - distribution_lambda_26_loss: 2.7910 - distribution_lambda_27_loss: 1.9455 - distribution_lambda_28_loss: 0.5409 - val_loss: 5.2446 - val_distribution_lambda_26_loss: 2.7695 - val_distribution_lambda_27_loss: 1.9244 - val_distribution_lambda_28_loss: 0.5507\n", "Epoch 297/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.2597 - distribution_lambda_26_loss: 2.7863 - distribution_lambda_27_loss: 1.9253 - distribution_lambda_28_loss: 0.5481 - val_loss: 5.2404 - val_distribution_lambda_26_loss: 2.7670 - val_distribution_lambda_27_loss: 1.9227 - val_distribution_lambda_28_loss: 0.5507\n", "Epoch 298/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.2783 - distribution_lambda_26_loss: 2.7830 - distribution_lambda_27_loss: 1.9471 - distribution_lambda_28_loss: 0.5482 - val_loss: 5.2363 - val_distribution_lambda_26_loss: 2.7645 - val_distribution_lambda_27_loss: 1.9211 - val_distribution_lambda_28_loss: 0.5508\n", "Epoch 299/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.2835 - distribution_lambda_26_loss: 2.7845 - distribution_lambda_27_loss: 1.9500 - distribution_lambda_28_loss: 0.5489 - val_loss: 5.2323 - val_distribution_lambda_26_loss: 2.7620 - val_distribution_lambda_27_loss: 1.9196 - val_distribution_lambda_28_loss: 0.5508\n", "Epoch 300/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.2767 - distribution_lambda_26_loss: 2.7798 - distribution_lambda_27_loss: 1.9498 - distribution_lambda_28_loss: 0.5471 - val_loss: 5.2279 - val_distribution_lambda_26_loss: 2.7594 - val_distribution_lambda_27_loss: 1.9177 - val_distribution_lambda_28_loss: 0.5508\n", "Epoch 301/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 5.2783 - distribution_lambda_26_loss: 2.7777 - distribution_lambda_27_loss: 1.9574 - distribution_lambda_28_loss: 0.5432 - val_loss: 5.2233 - val_distribution_lambda_26_loss: 2.7569 - val_distribution_lambda_27_loss: 1.9157 - val_distribution_lambda_28_loss: 0.5507\n", "Epoch 302/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.2620 - distribution_lambda_26_loss: 2.7765 - distribution_lambda_27_loss: 1.9387 - distribution_lambda_28_loss: 0.5468 - val_loss: 5.2188 - val_distribution_lambda_26_loss: 2.7543 - val_distribution_lambda_27_loss: 1.9137 - val_distribution_lambda_28_loss: 0.5507\n", "Epoch 303/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 5.2479 - distribution_lambda_26_loss: 2.7715 - distribution_lambda_27_loss: 1.9302 - distribution_lambda_28_loss: 0.5462 - val_loss: 5.2141 - val_distribution_lambda_26_loss: 2.7518 - val_distribution_lambda_27_loss: 1.9119 - val_distribution_lambda_28_loss: 0.5505\n", "Epoch 304/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.2521 - distribution_lambda_26_loss: 2.7699 - distribution_lambda_27_loss: 1.9350 - distribution_lambda_28_loss: 0.5472 - val_loss: 5.2098 - val_distribution_lambda_26_loss: 2.7492 - val_distribution_lambda_27_loss: 1.9101 - val_distribution_lambda_28_loss: 0.5505\n", "Epoch 305/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.2397 - distribution_lambda_26_loss: 2.7649 - distribution_lambda_27_loss: 1.9291 - distribution_lambda_28_loss: 0.5457 - val_loss: 5.2053 - val_distribution_lambda_26_loss: 2.7466 - val_distribution_lambda_27_loss: 1.9084 - val_distribution_lambda_28_loss: 0.5503\n", "Epoch 306/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.2389 - distribution_lambda_26_loss: 2.7633 - distribution_lambda_27_loss: 1.9309 - distribution_lambda_28_loss: 0.5447 - val_loss: 5.2008 - val_distribution_lambda_26_loss: 2.7440 - val_distribution_lambda_27_loss: 1.9065 - val_distribution_lambda_28_loss: 0.5503\n", "Epoch 307/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.2263 - distribution_lambda_26_loss: 2.7628 - distribution_lambda_27_loss: 1.9200 - distribution_lambda_28_loss: 0.5434 - val_loss: 5.1964 - val_distribution_lambda_26_loss: 2.7414 - val_distribution_lambda_27_loss: 1.9049 - val_distribution_lambda_28_loss: 0.5501\n", "Epoch 308/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.2368 - distribution_lambda_26_loss: 2.7602 - distribution_lambda_27_loss: 1.9308 - distribution_lambda_28_loss: 0.5458 - val_loss: 5.1923 - val_distribution_lambda_26_loss: 2.7387 - val_distribution_lambda_27_loss: 1.9036 - val_distribution_lambda_28_loss: 0.5500\n", "Epoch 309/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.2157 - distribution_lambda_26_loss: 2.7547 - distribution_lambda_27_loss: 1.9167 - distribution_lambda_28_loss: 0.5443 - val_loss: 5.1881 - val_distribution_lambda_26_loss: 2.7361 - val_distribution_lambda_27_loss: 1.9021 - val_distribution_lambda_28_loss: 0.5499\n", "Epoch 310/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.2305 - distribution_lambda_26_loss: 2.7546 - distribution_lambda_27_loss: 1.9297 - distribution_lambda_28_loss: 0.5462 - val_loss: 5.1839 - val_distribution_lambda_26_loss: 2.7334 - val_distribution_lambda_27_loss: 1.9007 - val_distribution_lambda_28_loss: 0.5498\n", "Epoch 311/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.1935 - distribution_lambda_26_loss: 2.7472 - distribution_lambda_27_loss: 1.9036 - distribution_lambda_28_loss: 0.5427 - val_loss: 5.1793 - val_distribution_lambda_26_loss: 2.7308 - val_distribution_lambda_27_loss: 1.8989 - val_distribution_lambda_28_loss: 0.5497\n", "Epoch 312/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.1952 - distribution_lambda_26_loss: 2.7444 - distribution_lambda_27_loss: 1.9100 - distribution_lambda_28_loss: 0.5408 - val_loss: 5.1747 - val_distribution_lambda_26_loss: 2.7281 - val_distribution_lambda_27_loss: 1.8970 - val_distribution_lambda_28_loss: 0.5496\n", "Epoch 313/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 5ms/step - loss: 5.1948 - distribution_lambda_26_loss: 2.7446 - distribution_lambda_27_loss: 1.9082 - distribution_lambda_28_loss: 0.5420 - val_loss: 5.1702 - val_distribution_lambda_26_loss: 2.7254 - val_distribution_lambda_27_loss: 1.8953 - val_distribution_lambda_28_loss: 0.5496\n", "Epoch 314/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.2203 - distribution_lambda_26_loss: 2.7440 - distribution_lambda_27_loss: 1.9284 - distribution_lambda_28_loss: 0.5479 - val_loss: 5.1654 - val_distribution_lambda_26_loss: 2.7227 - val_distribution_lambda_27_loss: 1.8932 - val_distribution_lambda_28_loss: 0.5495\n", "Epoch 315/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.1790 - distribution_lambda_26_loss: 2.7374 - distribution_lambda_27_loss: 1.8972 - distribution_lambda_28_loss: 0.5445 - val_loss: 5.1607 - val_distribution_lambda_26_loss: 2.7199 - val_distribution_lambda_27_loss: 1.8914 - val_distribution_lambda_28_loss: 0.5494\n", "Epoch 316/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.2023 - distribution_lambda_26_loss: 2.7354 - distribution_lambda_27_loss: 1.9269 - distribution_lambda_28_loss: 0.5400 - val_loss: 5.1562 - val_distribution_lambda_26_loss: 2.7172 - val_distribution_lambda_27_loss: 1.8895 - val_distribution_lambda_28_loss: 0.5494\n", "Epoch 317/2500\n", "8/8 [==============================] - 0s 8ms/step - loss: 5.1782 - distribution_lambda_26_loss: 2.7311 - distribution_lambda_27_loss: 1.9018 - distribution_lambda_28_loss: 0.5452 - val_loss: 5.1518 - val_distribution_lambda_26_loss: 2.7145 - val_distribution_lambda_27_loss: 1.8879 - val_distribution_lambda_28_loss: 0.5494\n", "Epoch 318/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.2114 - distribution_lambda_26_loss: 2.7300 - distribution_lambda_27_loss: 1.9336 - distribution_lambda_28_loss: 0.5478 - val_loss: 5.1475 - val_distribution_lambda_26_loss: 2.7117 - val_distribution_lambda_27_loss: 1.8864 - val_distribution_lambda_28_loss: 0.5494\n", "Epoch 319/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.1867 - distribution_lambda_26_loss: 2.7282 - distribution_lambda_27_loss: 1.9174 - distribution_lambda_28_loss: 0.5412 - val_loss: 5.1429 - val_distribution_lambda_26_loss: 2.7089 - val_distribution_lambda_27_loss: 1.8848 - val_distribution_lambda_28_loss: 0.5492\n", "Epoch 320/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.1778 - distribution_lambda_26_loss: 2.7241 - distribution_lambda_27_loss: 1.9144 - distribution_lambda_28_loss: 0.5394 - val_loss: 5.1382 - val_distribution_lambda_26_loss: 2.7061 - val_distribution_lambda_27_loss: 1.8831 - val_distribution_lambda_28_loss: 0.5490\n", "Epoch 321/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.1689 - distribution_lambda_26_loss: 2.7208 - distribution_lambda_27_loss: 1.9052 - distribution_lambda_28_loss: 0.5429 - val_loss: 5.1337 - val_distribution_lambda_26_loss: 2.7033 - val_distribution_lambda_27_loss: 1.8815 - val_distribution_lambda_28_loss: 0.5489\n", "Epoch 322/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.1701 - distribution_lambda_26_loss: 2.7159 - distribution_lambda_27_loss: 1.9095 - distribution_lambda_28_loss: 0.5448 - val_loss: 5.1292 - val_distribution_lambda_26_loss: 2.7005 - val_distribution_lambda_27_loss: 1.8799 - val_distribution_lambda_28_loss: 0.5488\n", "Epoch 323/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.1761 - distribution_lambda_26_loss: 2.7182 - distribution_lambda_27_loss: 1.9170 - distribution_lambda_28_loss: 0.5409 - val_loss: 5.1244 - val_distribution_lambda_26_loss: 2.6976 - val_distribution_lambda_27_loss: 1.8780 - val_distribution_lambda_28_loss: 0.5488\n", "Epoch 324/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 5.1731 - distribution_lambda_26_loss: 2.7134 - distribution_lambda_27_loss: 1.9131 - distribution_lambda_28_loss: 0.5466 - val_loss: 5.1196 - val_distribution_lambda_26_loss: 2.6948 - val_distribution_lambda_27_loss: 1.8761 - val_distribution_lambda_28_loss: 0.5488\n", "Epoch 325/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.1464 - distribution_lambda_26_loss: 2.7142 - distribution_lambda_27_loss: 1.8917 - distribution_lambda_28_loss: 0.5405 - val_loss: 5.1150 - val_distribution_lambda_26_loss: 2.6919 - val_distribution_lambda_27_loss: 1.8744 - val_distribution_lambda_28_loss: 0.5486\n", "Epoch 326/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.1687 - distribution_lambda_26_loss: 2.7093 - distribution_lambda_27_loss: 1.9153 - distribution_lambda_28_loss: 0.5440 - val_loss: 5.1105 - val_distribution_lambda_26_loss: 2.6890 - val_distribution_lambda_27_loss: 1.8729 - val_distribution_lambda_28_loss: 0.5486\n", "Epoch 327/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 5.1532 - distribution_lambda_26_loss: 2.7032 - distribution_lambda_27_loss: 1.9081 - distribution_lambda_28_loss: 0.5419 - val_loss: 5.1055 - val_distribution_lambda_26_loss: 2.6861 - val_distribution_lambda_27_loss: 1.8711 - val_distribution_lambda_28_loss: 0.5483\n", "Epoch 328/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.1426 - distribution_lambda_26_loss: 2.6988 - distribution_lambda_27_loss: 1.9018 - distribution_lambda_28_loss: 0.5421 - val_loss: 5.1005 - val_distribution_lambda_26_loss: 2.6832 - val_distribution_lambda_27_loss: 1.8693 - val_distribution_lambda_28_loss: 0.5480\n", "Epoch 329/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.1305 - distribution_lambda_26_loss: 2.6991 - distribution_lambda_27_loss: 1.8890 - distribution_lambda_28_loss: 0.5425 - val_loss: 5.0958 - val_distribution_lambda_26_loss: 2.6802 - val_distribution_lambda_27_loss: 1.8676 - val_distribution_lambda_28_loss: 0.5479\n", "Epoch 330/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.1289 - distribution_lambda_26_loss: 2.6955 - distribution_lambda_27_loss: 1.8885 - distribution_lambda_28_loss: 0.5449 - val_loss: 5.0911 - val_distribution_lambda_26_loss: 2.6773 - val_distribution_lambda_27_loss: 1.8660 - val_distribution_lambda_28_loss: 0.5478\n", "Epoch 331/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.1341 - distribution_lambda_26_loss: 2.6923 - distribution_lambda_27_loss: 1.8993 - distribution_lambda_28_loss: 0.5425 - val_loss: 5.0865 - val_distribution_lambda_26_loss: 2.6743 - val_distribution_lambda_27_loss: 1.8644 - val_distribution_lambda_28_loss: 0.5478\n", "Epoch 332/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.1192 - distribution_lambda_26_loss: 2.6901 - distribution_lambda_27_loss: 1.8890 - distribution_lambda_28_loss: 0.5401 - val_loss: 5.0817 - val_distribution_lambda_26_loss: 2.6713 - val_distribution_lambda_27_loss: 1.8628 - val_distribution_lambda_28_loss: 0.5476\n", "Epoch 333/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.1263 - distribution_lambda_26_loss: 2.6908 - distribution_lambda_27_loss: 1.8950 - distribution_lambda_28_loss: 0.5405 - val_loss: 5.0773 - val_distribution_lambda_26_loss: 2.6683 - val_distribution_lambda_27_loss: 1.8617 - val_distribution_lambda_28_loss: 0.5474\n", "Epoch 334/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.1177 - distribution_lambda_26_loss: 2.6833 - distribution_lambda_27_loss: 1.8909 - distribution_lambda_28_loss: 0.5434 - val_loss: 5.0729 - val_distribution_lambda_26_loss: 2.6652 - val_distribution_lambda_27_loss: 1.8604 - val_distribution_lambda_28_loss: 0.5473\n", "Epoch 335/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.0959 - distribution_lambda_26_loss: 2.6794 - distribution_lambda_27_loss: 1.8705 - distribution_lambda_28_loss: 0.5460 - val_loss: 5.0681 - val_distribution_lambda_26_loss: 2.6622 - val_distribution_lambda_27_loss: 1.8589 - val_distribution_lambda_28_loss: 0.5471\n", "Epoch 336/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.1345 - distribution_lambda_26_loss: 2.6786 - distribution_lambda_27_loss: 1.9136 - distribution_lambda_28_loss: 0.5424 - val_loss: 5.0637 - val_distribution_lambda_26_loss: 2.6591 - val_distribution_lambda_27_loss: 1.8576 - val_distribution_lambda_28_loss: 0.5470\n", "Epoch 337/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 5ms/step - loss: 5.0965 - distribution_lambda_26_loss: 2.6719 - distribution_lambda_27_loss: 1.8765 - distribution_lambda_28_loss: 0.5480 - val_loss: 5.0584 - val_distribution_lambda_26_loss: 2.6560 - val_distribution_lambda_27_loss: 1.8556 - val_distribution_lambda_28_loss: 0.5468\n", "Epoch 338/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 5.0961 - distribution_lambda_26_loss: 2.6718 - distribution_lambda_27_loss: 1.8841 - distribution_lambda_28_loss: 0.5403 - val_loss: 5.0535 - val_distribution_lambda_26_loss: 2.6529 - val_distribution_lambda_27_loss: 1.8538 - val_distribution_lambda_28_loss: 0.5468\n", "Epoch 339/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.0752 - distribution_lambda_26_loss: 2.6696 - distribution_lambda_27_loss: 1.8658 - distribution_lambda_28_loss: 0.5398 - val_loss: 5.0490 - val_distribution_lambda_26_loss: 2.6498 - val_distribution_lambda_27_loss: 1.8526 - val_distribution_lambda_28_loss: 0.5467\n", "Epoch 340/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.0930 - distribution_lambda_26_loss: 2.6666 - distribution_lambda_27_loss: 1.8825 - distribution_lambda_28_loss: 0.5439 - val_loss: 5.0444 - val_distribution_lambda_26_loss: 2.6466 - val_distribution_lambda_27_loss: 1.8512 - val_distribution_lambda_28_loss: 0.5466\n", "Epoch 341/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.0947 - distribution_lambda_26_loss: 2.6623 - distribution_lambda_27_loss: 1.8894 - distribution_lambda_28_loss: 0.5430 - val_loss: 5.0396 - val_distribution_lambda_26_loss: 2.6435 - val_distribution_lambda_27_loss: 1.8497 - val_distribution_lambda_28_loss: 0.5464\n", "Epoch 342/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.0675 - distribution_lambda_26_loss: 2.6555 - distribution_lambda_27_loss: 1.8708 - distribution_lambda_28_loss: 0.5412 - val_loss: 5.0349 - val_distribution_lambda_26_loss: 2.6403 - val_distribution_lambda_27_loss: 1.8482 - val_distribution_lambda_28_loss: 0.5464\n", "Epoch 343/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 5.0530 - distribution_lambda_26_loss: 2.6538 - distribution_lambda_27_loss: 1.8574 - distribution_lambda_28_loss: 0.5418 - val_loss: 5.0297 - val_distribution_lambda_26_loss: 2.6371 - val_distribution_lambda_27_loss: 1.8464 - val_distribution_lambda_28_loss: 0.5462\n", "Epoch 344/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.0719 - distribution_lambda_26_loss: 2.6513 - distribution_lambda_27_loss: 1.8773 - distribution_lambda_28_loss: 0.5433 - val_loss: 5.0250 - val_distribution_lambda_26_loss: 2.6339 - val_distribution_lambda_27_loss: 1.8451 - val_distribution_lambda_28_loss: 0.5461\n", "Epoch 345/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.0732 - distribution_lambda_26_loss: 2.6464 - distribution_lambda_27_loss: 1.8846 - distribution_lambda_28_loss: 0.5422 - val_loss: 5.0203 - val_distribution_lambda_26_loss: 2.6307 - val_distribution_lambda_27_loss: 1.8436 - val_distribution_lambda_28_loss: 0.5460\n", "Epoch 346/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.0657 - distribution_lambda_26_loss: 2.6445 - distribution_lambda_27_loss: 1.8789 - distribution_lambda_28_loss: 0.5423 - val_loss: 5.0157 - val_distribution_lambda_26_loss: 2.6274 - val_distribution_lambda_27_loss: 1.8423 - val_distribution_lambda_28_loss: 0.5460\n", "Epoch 347/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.0689 - distribution_lambda_26_loss: 2.6430 - distribution_lambda_27_loss: 1.8873 - distribution_lambda_28_loss: 0.5386 - val_loss: 5.0106 - val_distribution_lambda_26_loss: 2.6241 - val_distribution_lambda_27_loss: 1.8408 - val_distribution_lambda_28_loss: 0.5457\n", "Epoch 348/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.0324 - distribution_lambda_26_loss: 2.6373 - distribution_lambda_27_loss: 1.8549 - distribution_lambda_28_loss: 0.5402 - val_loss: 5.0055 - val_distribution_lambda_26_loss: 2.6208 - val_distribution_lambda_27_loss: 1.8391 - val_distribution_lambda_28_loss: 0.5455\n", "Epoch 349/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.0558 - distribution_lambda_26_loss: 2.6382 - distribution_lambda_27_loss: 1.8730 - distribution_lambda_28_loss: 0.5447 - val_loss: 5.0005 - val_distribution_lambda_26_loss: 2.6175 - val_distribution_lambda_27_loss: 1.8376 - val_distribution_lambda_28_loss: 0.5454\n", "Epoch 350/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.0384 - distribution_lambda_26_loss: 2.6307 - distribution_lambda_27_loss: 1.8642 - distribution_lambda_28_loss: 0.5435 - val_loss: 4.9953 - val_distribution_lambda_26_loss: 2.6142 - val_distribution_lambda_27_loss: 1.8360 - val_distribution_lambda_28_loss: 0.5450\n", "Epoch 351/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.0455 - distribution_lambda_26_loss: 2.6305 - distribution_lambda_27_loss: 1.8744 - distribution_lambda_28_loss: 0.5405 - val_loss: 4.9906 - val_distribution_lambda_26_loss: 2.6108 - val_distribution_lambda_27_loss: 1.8349 - val_distribution_lambda_28_loss: 0.5448\n", "Epoch 352/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.0334 - distribution_lambda_26_loss: 2.6250 - distribution_lambda_27_loss: 1.8630 - distribution_lambda_28_loss: 0.5454 - val_loss: 4.9858 - val_distribution_lambda_26_loss: 2.6074 - val_distribution_lambda_27_loss: 1.8336 - val_distribution_lambda_28_loss: 0.5448\n", "Epoch 353/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.0327 - distribution_lambda_26_loss: 2.6258 - distribution_lambda_27_loss: 1.8690 - distribution_lambda_28_loss: 0.5379 - val_loss: 4.9808 - val_distribution_lambda_26_loss: 2.6040 - val_distribution_lambda_27_loss: 1.8321 - val_distribution_lambda_28_loss: 0.5446\n", "Epoch 354/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 5.0416 - distribution_lambda_26_loss: 2.6208 - distribution_lambda_27_loss: 1.8726 - distribution_lambda_28_loss: 0.5482 - val_loss: 4.9758 - val_distribution_lambda_26_loss: 2.6006 - val_distribution_lambda_27_loss: 1.8307 - val_distribution_lambda_28_loss: 0.5445\n", "Epoch 355/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 5.0207 - distribution_lambda_26_loss: 2.6131 - distribution_lambda_27_loss: 1.8627 - distribution_lambda_28_loss: 0.5450 - val_loss: 4.9707 - val_distribution_lambda_26_loss: 2.5972 - val_distribution_lambda_27_loss: 1.8291 - val_distribution_lambda_28_loss: 0.5444\n", "Epoch 356/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.9912 - distribution_lambda_26_loss: 2.6099 - distribution_lambda_27_loss: 1.8431 - distribution_lambda_28_loss: 0.5382 - val_loss: 4.9658 - val_distribution_lambda_26_loss: 2.5937 - val_distribution_lambda_27_loss: 1.8278 - val_distribution_lambda_28_loss: 0.5443\n", "Epoch 357/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.9918 - distribution_lambda_26_loss: 2.6073 - distribution_lambda_27_loss: 1.8442 - distribution_lambda_28_loss: 0.5403 - val_loss: 4.9606 - val_distribution_lambda_26_loss: 2.5902 - val_distribution_lambda_27_loss: 1.8261 - val_distribution_lambda_28_loss: 0.5443\n", "Epoch 358/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.9856 - distribution_lambda_26_loss: 2.6076 - distribution_lambda_27_loss: 1.8365 - distribution_lambda_28_loss: 0.5415 - val_loss: 4.9554 - val_distribution_lambda_26_loss: 2.5867 - val_distribution_lambda_27_loss: 1.8246 - val_distribution_lambda_28_loss: 0.5440\n", "Epoch 359/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.9873 - distribution_lambda_26_loss: 2.5990 - distribution_lambda_27_loss: 1.8496 - distribution_lambda_28_loss: 0.5388 - val_loss: 4.9502 - val_distribution_lambda_26_loss: 2.5832 - val_distribution_lambda_27_loss: 1.8232 - val_distribution_lambda_28_loss: 0.5438\n", "Epoch 360/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.9931 - distribution_lambda_26_loss: 2.5979 - distribution_lambda_27_loss: 1.8582 - distribution_lambda_28_loss: 0.5370 - val_loss: 4.9452 - val_distribution_lambda_26_loss: 2.5797 - val_distribution_lambda_27_loss: 1.8218 - val_distribution_lambda_28_loss: 0.5437\n", "Epoch 361/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 4.9860 - distribution_lambda_26_loss: 2.5938 - distribution_lambda_27_loss: 1.8539 - distribution_lambda_28_loss: 0.5382 - val_loss: 4.9400 - val_distribution_lambda_26_loss: 2.5761 - val_distribution_lambda_27_loss: 1.8205 - val_distribution_lambda_28_loss: 0.5434\n", "Epoch 362/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.9819 - distribution_lambda_26_loss: 2.5936 - distribution_lambda_27_loss: 1.8524 - distribution_lambda_28_loss: 0.5358 - val_loss: 4.9348 - val_distribution_lambda_26_loss: 2.5725 - val_distribution_lambda_27_loss: 1.8191 - val_distribution_lambda_28_loss: 0.5432\n", "Epoch 363/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.9847 - distribution_lambda_26_loss: 2.5881 - distribution_lambda_27_loss: 1.8544 - distribution_lambda_28_loss: 0.5422 - val_loss: 4.9298 - val_distribution_lambda_26_loss: 2.5688 - val_distribution_lambda_27_loss: 1.8181 - val_distribution_lambda_28_loss: 0.5428\n", "Epoch 364/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.9816 - distribution_lambda_26_loss: 2.5832 - distribution_lambda_27_loss: 1.8610 - distribution_lambda_28_loss: 0.5374 - val_loss: 4.9242 - val_distribution_lambda_26_loss: 2.5652 - val_distribution_lambda_27_loss: 1.8164 - val_distribution_lambda_28_loss: 0.5426\n", "Epoch 365/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.9789 - distribution_lambda_26_loss: 2.5770 - distribution_lambda_27_loss: 1.8545 - distribution_lambda_28_loss: 0.5474 - val_loss: 4.9191 - val_distribution_lambda_26_loss: 2.5615 - val_distribution_lambda_27_loss: 1.8151 - val_distribution_lambda_28_loss: 0.5425\n", "Epoch 366/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.9607 - distribution_lambda_26_loss: 2.5744 - distribution_lambda_27_loss: 1.8482 - distribution_lambda_28_loss: 0.5381 - val_loss: 4.9141 - val_distribution_lambda_26_loss: 2.5579 - val_distribution_lambda_27_loss: 1.8140 - val_distribution_lambda_28_loss: 0.5423\n", "Epoch 367/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.9602 - distribution_lambda_26_loss: 2.5744 - distribution_lambda_27_loss: 1.8484 - distribution_lambda_28_loss: 0.5374 - val_loss: 4.9092 - val_distribution_lambda_26_loss: 2.5541 - val_distribution_lambda_27_loss: 1.8129 - val_distribution_lambda_28_loss: 0.5422\n", "Epoch 368/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.9365 - distribution_lambda_26_loss: 2.5664 - distribution_lambda_27_loss: 1.8343 - distribution_lambda_28_loss: 0.5359 - val_loss: 4.9041 - val_distribution_lambda_26_loss: 2.5504 - val_distribution_lambda_27_loss: 1.8116 - val_distribution_lambda_28_loss: 0.5421\n", "Epoch 369/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.9636 - distribution_lambda_26_loss: 2.5660 - distribution_lambda_27_loss: 1.8525 - distribution_lambda_28_loss: 0.5451 - val_loss: 4.8990 - val_distribution_lambda_26_loss: 2.5466 - val_distribution_lambda_27_loss: 1.8103 - val_distribution_lambda_28_loss: 0.5420\n", "Epoch 370/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.9622 - distribution_lambda_26_loss: 2.5602 - distribution_lambda_27_loss: 1.8624 - distribution_lambda_28_loss: 0.5395 - val_loss: 4.8933 - val_distribution_lambda_26_loss: 2.5429 - val_distribution_lambda_27_loss: 1.8087 - val_distribution_lambda_28_loss: 0.5417\n", "Epoch 371/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.9245 - distribution_lambda_26_loss: 2.5556 - distribution_lambda_27_loss: 1.8271 - distribution_lambda_28_loss: 0.5419 - val_loss: 4.8880 - val_distribution_lambda_26_loss: 2.5391 - val_distribution_lambda_27_loss: 1.8075 - val_distribution_lambda_28_loss: 0.5415\n", "Epoch 372/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.9560 - distribution_lambda_26_loss: 2.5570 - distribution_lambda_27_loss: 1.8602 - distribution_lambda_28_loss: 0.5389 - val_loss: 4.8827 - val_distribution_lambda_26_loss: 2.5352 - val_distribution_lambda_27_loss: 1.8062 - val_distribution_lambda_28_loss: 0.5413\n", "Epoch 373/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.9156 - distribution_lambda_26_loss: 2.5506 - distribution_lambda_27_loss: 1.8245 - distribution_lambda_28_loss: 0.5405 - val_loss: 4.8773 - val_distribution_lambda_26_loss: 2.5313 - val_distribution_lambda_27_loss: 1.8048 - val_distribution_lambda_28_loss: 0.5412\n", "Epoch 374/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.9272 - distribution_lambda_26_loss: 2.5449 - distribution_lambda_27_loss: 1.8403 - distribution_lambda_28_loss: 0.5420 - val_loss: 4.8721 - val_distribution_lambda_26_loss: 2.5275 - val_distribution_lambda_27_loss: 1.8035 - val_distribution_lambda_28_loss: 0.5411\n", "Epoch 375/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.9437 - distribution_lambda_26_loss: 2.5407 - distribution_lambda_27_loss: 1.8667 - distribution_lambda_28_loss: 0.5363 - val_loss: 4.8666 - val_distribution_lambda_26_loss: 2.5235 - val_distribution_lambda_27_loss: 1.8021 - val_distribution_lambda_28_loss: 0.5410\n", "Epoch 376/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.9001 - distribution_lambda_26_loss: 2.5357 - distribution_lambda_27_loss: 1.8296 - distribution_lambda_28_loss: 0.5348 - val_loss: 4.8613 - val_distribution_lambda_26_loss: 2.5196 - val_distribution_lambda_27_loss: 1.8006 - val_distribution_lambda_28_loss: 0.5410\n", "Epoch 377/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.8994 - distribution_lambda_26_loss: 2.5318 - distribution_lambda_27_loss: 1.8297 - distribution_lambda_28_loss: 0.5378 - val_loss: 4.8561 - val_distribution_lambda_26_loss: 2.5157 - val_distribution_lambda_27_loss: 1.7996 - val_distribution_lambda_28_loss: 0.5408\n", "Epoch 378/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.8976 - distribution_lambda_26_loss: 2.5330 - distribution_lambda_27_loss: 1.8306 - distribution_lambda_28_loss: 0.5341 - val_loss: 4.8507 - val_distribution_lambda_26_loss: 2.5117 - val_distribution_lambda_27_loss: 1.7986 - val_distribution_lambda_28_loss: 0.5405\n", "Epoch 379/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.9048 - distribution_lambda_26_loss: 2.5268 - distribution_lambda_27_loss: 1.8357 - distribution_lambda_28_loss: 0.5423 - val_loss: 4.8456 - val_distribution_lambda_26_loss: 2.5077 - val_distribution_lambda_27_loss: 1.7976 - val_distribution_lambda_28_loss: 0.5403\n", "Epoch 380/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.8841 - distribution_lambda_26_loss: 2.5210 - distribution_lambda_27_loss: 1.8190 - distribution_lambda_28_loss: 0.5441 - val_loss: 4.8400 - val_distribution_lambda_26_loss: 2.5036 - val_distribution_lambda_27_loss: 1.7962 - val_distribution_lambda_28_loss: 0.5402\n", "Epoch 381/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.8701 - distribution_lambda_26_loss: 2.5178 - distribution_lambda_27_loss: 1.8137 - distribution_lambda_28_loss: 0.5386 - val_loss: 4.8345 - val_distribution_lambda_26_loss: 2.4996 - val_distribution_lambda_27_loss: 1.7948 - val_distribution_lambda_28_loss: 0.5401\n", "Epoch 382/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.8731 - distribution_lambda_26_loss: 2.5150 - distribution_lambda_27_loss: 1.8150 - distribution_lambda_28_loss: 0.5431 - val_loss: 4.8289 - val_distribution_lambda_26_loss: 2.4955 - val_distribution_lambda_27_loss: 1.7934 - val_distribution_lambda_28_loss: 0.5400\n", "Epoch 383/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.8721 - distribution_lambda_26_loss: 2.5105 - distribution_lambda_27_loss: 1.8221 - distribution_lambda_28_loss: 0.5394 - val_loss: 4.8232 - val_distribution_lambda_26_loss: 2.4914 - val_distribution_lambda_27_loss: 1.7920 - val_distribution_lambda_28_loss: 0.5398\n", "Epoch 384/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.8660 - distribution_lambda_26_loss: 2.5057 - distribution_lambda_27_loss: 1.8234 - distribution_lambda_28_loss: 0.5370 - val_loss: 4.8177 - val_distribution_lambda_26_loss: 2.4872 - val_distribution_lambda_27_loss: 1.7909 - val_distribution_lambda_28_loss: 0.5396\n", "Epoch 385/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 4.8841 - distribution_lambda_26_loss: 2.5009 - distribution_lambda_27_loss: 1.8430 - distribution_lambda_28_loss: 0.5402 - val_loss: 4.8124 - val_distribution_lambda_26_loss: 2.4831 - val_distribution_lambda_27_loss: 1.7899 - val_distribution_lambda_28_loss: 0.5394\n", "Epoch 386/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.8728 - distribution_lambda_26_loss: 2.4988 - distribution_lambda_27_loss: 1.8329 - distribution_lambda_28_loss: 0.5411 - val_loss: 4.8072 - val_distribution_lambda_26_loss: 2.4789 - val_distribution_lambda_27_loss: 1.7889 - val_distribution_lambda_28_loss: 0.5394\n", "Epoch 387/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.8342 - distribution_lambda_26_loss: 2.4932 - distribution_lambda_27_loss: 1.8050 - distribution_lambda_28_loss: 0.5361 - val_loss: 4.8019 - val_distribution_lambda_26_loss: 2.4747 - val_distribution_lambda_27_loss: 1.7882 - val_distribution_lambda_28_loss: 0.5391\n", "Epoch 388/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.8460 - distribution_lambda_26_loss: 2.4883 - distribution_lambda_27_loss: 1.8204 - distribution_lambda_28_loss: 0.5374 - val_loss: 4.7966 - val_distribution_lambda_26_loss: 2.4704 - val_distribution_lambda_27_loss: 1.7873 - val_distribution_lambda_28_loss: 0.5389\n", "Epoch 389/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.8217 - distribution_lambda_26_loss: 2.4830 - distribution_lambda_27_loss: 1.8056 - distribution_lambda_28_loss: 0.5330 - val_loss: 4.7910 - val_distribution_lambda_26_loss: 2.4661 - val_distribution_lambda_27_loss: 1.7860 - val_distribution_lambda_28_loss: 0.5388\n", "Epoch 390/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.8367 - distribution_lambda_26_loss: 2.4830 - distribution_lambda_27_loss: 1.8239 - distribution_lambda_28_loss: 0.5298 - val_loss: 4.7852 - val_distribution_lambda_26_loss: 2.4618 - val_distribution_lambda_27_loss: 1.7849 - val_distribution_lambda_28_loss: 0.5385\n", "Epoch 391/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.8238 - distribution_lambda_26_loss: 2.4754 - distribution_lambda_27_loss: 1.8149 - distribution_lambda_28_loss: 0.5335 - val_loss: 4.7791 - val_distribution_lambda_26_loss: 2.4575 - val_distribution_lambda_27_loss: 1.7832 - val_distribution_lambda_28_loss: 0.5384\n", "Epoch 392/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.8143 - distribution_lambda_26_loss: 2.4698 - distribution_lambda_27_loss: 1.8128 - distribution_lambda_28_loss: 0.5317 - val_loss: 4.7735 - val_distribution_lambda_26_loss: 2.4532 - val_distribution_lambda_27_loss: 1.7820 - val_distribution_lambda_28_loss: 0.5383\n", "Epoch 393/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.8043 - distribution_lambda_26_loss: 2.4658 - distribution_lambda_27_loss: 1.8071 - distribution_lambda_28_loss: 0.5315 - val_loss: 4.7677 - val_distribution_lambda_26_loss: 2.4488 - val_distribution_lambda_27_loss: 1.7807 - val_distribution_lambda_28_loss: 0.5382\n", "Epoch 394/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.8221 - distribution_lambda_26_loss: 2.4639 - distribution_lambda_27_loss: 1.8229 - distribution_lambda_28_loss: 0.5353 - val_loss: 4.7623 - val_distribution_lambda_26_loss: 2.4444 - val_distribution_lambda_27_loss: 1.7799 - val_distribution_lambda_28_loss: 0.5381\n", "Epoch 395/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.8138 - distribution_lambda_26_loss: 2.4583 - distribution_lambda_27_loss: 1.8201 - distribution_lambda_28_loss: 0.5355 - val_loss: 4.7567 - val_distribution_lambda_26_loss: 2.4399 - val_distribution_lambda_27_loss: 1.7788 - val_distribution_lambda_28_loss: 0.5380\n", "Epoch 396/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.7872 - distribution_lambda_26_loss: 2.4529 - distribution_lambda_27_loss: 1.7992 - distribution_lambda_28_loss: 0.5351 - val_loss: 4.7509 - val_distribution_lambda_26_loss: 2.4355 - val_distribution_lambda_27_loss: 1.7776 - val_distribution_lambda_28_loss: 0.5378\n", "Epoch 397/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.8087 - distribution_lambda_26_loss: 2.4509 - distribution_lambda_27_loss: 1.8244 - distribution_lambda_28_loss: 0.5334 - val_loss: 4.7451 - val_distribution_lambda_26_loss: 2.4310 - val_distribution_lambda_27_loss: 1.7763 - val_distribution_lambda_28_loss: 0.5378\n", "Epoch 398/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.7841 - distribution_lambda_26_loss: 2.4440 - distribution_lambda_27_loss: 1.8045 - distribution_lambda_28_loss: 0.5357 - val_loss: 4.7392 - val_distribution_lambda_26_loss: 2.4265 - val_distribution_lambda_27_loss: 1.7750 - val_distribution_lambda_28_loss: 0.5378\n", "Epoch 399/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.7720 - distribution_lambda_26_loss: 2.4408 - distribution_lambda_27_loss: 1.7964 - distribution_lambda_28_loss: 0.5348 - val_loss: 4.7333 - val_distribution_lambda_26_loss: 2.4219 - val_distribution_lambda_27_loss: 1.7738 - val_distribution_lambda_28_loss: 0.5376\n", "Epoch 400/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.7542 - distribution_lambda_26_loss: 2.4348 - distribution_lambda_27_loss: 1.7901 - distribution_lambda_28_loss: 0.5294 - val_loss: 4.7271 - val_distribution_lambda_26_loss: 2.4174 - val_distribution_lambda_27_loss: 1.7724 - val_distribution_lambda_28_loss: 0.5373\n", "Epoch 401/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.7613 - distribution_lambda_26_loss: 2.4307 - distribution_lambda_27_loss: 1.7989 - distribution_lambda_28_loss: 0.5316 - val_loss: 4.7210 - val_distribution_lambda_26_loss: 2.4128 - val_distribution_lambda_27_loss: 1.7712 - val_distribution_lambda_28_loss: 0.5370\n", "Epoch 402/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.7394 - distribution_lambda_26_loss: 2.4253 - distribution_lambda_27_loss: 1.7857 - distribution_lambda_28_loss: 0.5284 - val_loss: 4.7146 - val_distribution_lambda_26_loss: 2.4081 - val_distribution_lambda_27_loss: 1.7696 - val_distribution_lambda_28_loss: 0.5368\n", "Epoch 403/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.7610 - distribution_lambda_26_loss: 2.4215 - distribution_lambda_27_loss: 1.8043 - distribution_lambda_28_loss: 0.5351 - val_loss: 4.7086 - val_distribution_lambda_26_loss: 2.4035 - val_distribution_lambda_27_loss: 1.7684 - val_distribution_lambda_28_loss: 0.5367\n", "Epoch 404/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.7701 - distribution_lambda_26_loss: 2.4158 - distribution_lambda_27_loss: 1.8160 - distribution_lambda_28_loss: 0.5383 - val_loss: 4.7026 - val_distribution_lambda_26_loss: 2.3988 - val_distribution_lambda_27_loss: 1.7673 - val_distribution_lambda_28_loss: 0.5365\n", "Epoch 405/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.7490 - distribution_lambda_26_loss: 2.4133 - distribution_lambda_27_loss: 1.8001 - distribution_lambda_28_loss: 0.5356 - val_loss: 4.6966 - val_distribution_lambda_26_loss: 2.3941 - val_distribution_lambda_27_loss: 1.7660 - val_distribution_lambda_28_loss: 0.5365\n", "Epoch 406/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.7511 - distribution_lambda_26_loss: 2.4078 - distribution_lambda_27_loss: 1.8105 - distribution_lambda_28_loss: 0.5327 - val_loss: 4.6903 - val_distribution_lambda_26_loss: 2.3894 - val_distribution_lambda_27_loss: 1.7646 - val_distribution_lambda_28_loss: 0.5363\n", "Epoch 407/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.7394 - distribution_lambda_26_loss: 2.4045 - distribution_lambda_27_loss: 1.8003 - distribution_lambda_28_loss: 0.5346 - val_loss: 4.6843 - val_distribution_lambda_26_loss: 2.3846 - val_distribution_lambda_27_loss: 1.7635 - val_distribution_lambda_28_loss: 0.5362\n", "Epoch 408/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.7199 - distribution_lambda_26_loss: 2.3991 - distribution_lambda_27_loss: 1.7819 - distribution_lambda_28_loss: 0.5389 - val_loss: 4.6786 - val_distribution_lambda_26_loss: 2.3798 - val_distribution_lambda_27_loss: 1.7626 - val_distribution_lambda_28_loss: 0.5362\n", "Epoch 409/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 4.7379 - distribution_lambda_26_loss: 2.3936 - distribution_lambda_27_loss: 1.8100 - distribution_lambda_28_loss: 0.5343 - val_loss: 4.6725 - val_distribution_lambda_26_loss: 2.3749 - val_distribution_lambda_27_loss: 1.7615 - val_distribution_lambda_28_loss: 0.5361\n", "Epoch 410/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.7207 - distribution_lambda_26_loss: 2.3879 - distribution_lambda_27_loss: 1.8033 - distribution_lambda_28_loss: 0.5296 - val_loss: 4.6660 - val_distribution_lambda_26_loss: 2.3701 - val_distribution_lambda_27_loss: 1.7601 - val_distribution_lambda_28_loss: 0.5359\n", "Epoch 411/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.7330 - distribution_lambda_26_loss: 2.3851 - distribution_lambda_27_loss: 1.8151 - distribution_lambda_28_loss: 0.5328 - val_loss: 4.6598 - val_distribution_lambda_26_loss: 2.3652 - val_distribution_lambda_27_loss: 1.7587 - val_distribution_lambda_28_loss: 0.5358\n", "Epoch 412/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.7031 - distribution_lambda_26_loss: 2.3810 - distribution_lambda_27_loss: 1.7899 - distribution_lambda_28_loss: 0.5322 - val_loss: 4.6537 - val_distribution_lambda_26_loss: 2.3603 - val_distribution_lambda_27_loss: 1.7577 - val_distribution_lambda_28_loss: 0.5358\n", "Epoch 413/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 4.7104 - distribution_lambda_26_loss: 2.3743 - distribution_lambda_27_loss: 1.8026 - distribution_lambda_28_loss: 0.5334 - val_loss: 4.6476 - val_distribution_lambda_26_loss: 2.3554 - val_distribution_lambda_27_loss: 1.7565 - val_distribution_lambda_28_loss: 0.5357\n", "Epoch 414/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.6828 - distribution_lambda_26_loss: 2.3718 - distribution_lambda_27_loss: 1.7819 - distribution_lambda_28_loss: 0.5291 - val_loss: 4.6411 - val_distribution_lambda_26_loss: 2.3504 - val_distribution_lambda_27_loss: 1.7553 - val_distribution_lambda_28_loss: 0.5354\n", "Epoch 415/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.6883 - distribution_lambda_26_loss: 2.3637 - distribution_lambda_27_loss: 1.7936 - distribution_lambda_28_loss: 0.5309 - val_loss: 4.6347 - val_distribution_lambda_26_loss: 2.3454 - val_distribution_lambda_27_loss: 1.7540 - val_distribution_lambda_28_loss: 0.5352\n", "Epoch 416/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.6594 - distribution_lambda_26_loss: 2.3580 - distribution_lambda_27_loss: 1.7730 - distribution_lambda_28_loss: 0.5283 - val_loss: 4.6283 - val_distribution_lambda_26_loss: 2.3404 - val_distribution_lambda_27_loss: 1.7529 - val_distribution_lambda_28_loss: 0.5351\n", "Epoch 417/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.6549 - distribution_lambda_26_loss: 2.3530 - distribution_lambda_27_loss: 1.7720 - distribution_lambda_28_loss: 0.5299 - val_loss: 4.6217 - val_distribution_lambda_26_loss: 2.3353 - val_distribution_lambda_27_loss: 1.7513 - val_distribution_lambda_28_loss: 0.5351\n", "Epoch 418/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.6666 - distribution_lambda_26_loss: 2.3484 - distribution_lambda_27_loss: 1.7871 - distribution_lambda_28_loss: 0.5311 - val_loss: 4.6155 - val_distribution_lambda_26_loss: 2.3302 - val_distribution_lambda_27_loss: 1.7501 - val_distribution_lambda_28_loss: 0.5351\n", "Epoch 419/2500\n", "8/8 [==============================] - 0s 8ms/step - loss: 4.6495 - distribution_lambda_26_loss: 2.3421 - distribution_lambda_27_loss: 1.7747 - distribution_lambda_28_loss: 0.5327 - val_loss: 4.6090 - val_distribution_lambda_26_loss: 2.3251 - val_distribution_lambda_27_loss: 1.7487 - val_distribution_lambda_28_loss: 0.5351\n", "Epoch 420/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.6546 - distribution_lambda_26_loss: 2.3399 - distribution_lambda_27_loss: 1.7841 - distribution_lambda_28_loss: 0.5306 - val_loss: 4.6026 - val_distribution_lambda_26_loss: 2.3200 - val_distribution_lambda_27_loss: 1.7473 - val_distribution_lambda_28_loss: 0.5353\n", "Epoch 421/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.6301 - distribution_lambda_26_loss: 2.3329 - distribution_lambda_27_loss: 1.7675 - distribution_lambda_28_loss: 0.5297 - val_loss: 4.5962 - val_distribution_lambda_26_loss: 2.3148 - val_distribution_lambda_27_loss: 1.7463 - val_distribution_lambda_28_loss: 0.5350\n", "Epoch 422/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.6475 - distribution_lambda_26_loss: 2.3300 - distribution_lambda_27_loss: 1.7871 - distribution_lambda_28_loss: 0.5304 - val_loss: 4.5894 - val_distribution_lambda_26_loss: 2.3097 - val_distribution_lambda_27_loss: 1.7449 - val_distribution_lambda_28_loss: 0.5348\n", "Epoch 423/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.6180 - distribution_lambda_26_loss: 2.3231 - distribution_lambda_27_loss: 1.7596 - distribution_lambda_28_loss: 0.5354 - val_loss: 4.5827 - val_distribution_lambda_26_loss: 2.3044 - val_distribution_lambda_27_loss: 1.7437 - val_distribution_lambda_28_loss: 0.5346\n", "Epoch 424/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.6187 - distribution_lambda_26_loss: 2.3175 - distribution_lambda_27_loss: 1.7740 - distribution_lambda_28_loss: 0.5273 - val_loss: 4.5762 - val_distribution_lambda_26_loss: 2.2992 - val_distribution_lambda_27_loss: 1.7425 - val_distribution_lambda_28_loss: 0.5345\n", "Epoch 425/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.6128 - distribution_lambda_26_loss: 2.3127 - distribution_lambda_27_loss: 1.7682 - distribution_lambda_28_loss: 0.5318 - val_loss: 4.5692 - val_distribution_lambda_26_loss: 2.2939 - val_distribution_lambda_27_loss: 1.7409 - val_distribution_lambda_28_loss: 0.5344\n", "Epoch 426/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.6048 - distribution_lambda_26_loss: 2.3054 - distribution_lambda_27_loss: 1.7687 - distribution_lambda_28_loss: 0.5306 - val_loss: 4.5623 - val_distribution_lambda_26_loss: 2.2886 - val_distribution_lambda_27_loss: 1.7395 - val_distribution_lambda_28_loss: 0.5342\n", "Epoch 427/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.5996 - distribution_lambda_26_loss: 2.3038 - distribution_lambda_27_loss: 1.7670 - distribution_lambda_28_loss: 0.5288 - val_loss: 4.5558 - val_distribution_lambda_26_loss: 2.2833 - val_distribution_lambda_27_loss: 1.7385 - val_distribution_lambda_28_loss: 0.5340\n", "Epoch 428/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.6050 - distribution_lambda_26_loss: 2.2959 - distribution_lambda_27_loss: 1.7772 - distribution_lambda_28_loss: 0.5319 - val_loss: 4.5494 - val_distribution_lambda_26_loss: 2.2779 - val_distribution_lambda_27_loss: 1.7376 - val_distribution_lambda_28_loss: 0.5339\n", "Epoch 429/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.5800 - distribution_lambda_26_loss: 2.2930 - distribution_lambda_27_loss: 1.7584 - distribution_lambda_28_loss: 0.5286 - val_loss: 4.5430 - val_distribution_lambda_26_loss: 2.2725 - val_distribution_lambda_27_loss: 1.7367 - val_distribution_lambda_28_loss: 0.5339\n", "Epoch 430/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.5809 - distribution_lambda_26_loss: 2.2857 - distribution_lambda_27_loss: 1.7628 - distribution_lambda_28_loss: 0.5324 - val_loss: 4.5363 - val_distribution_lambda_26_loss: 2.2671 - val_distribution_lambda_27_loss: 1.7355 - val_distribution_lambda_28_loss: 0.5337\n", "Epoch 431/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.5751 - distribution_lambda_26_loss: 2.2798 - distribution_lambda_27_loss: 1.7713 - distribution_lambda_28_loss: 0.5239 - val_loss: 4.5296 - val_distribution_lambda_26_loss: 2.2617 - val_distribution_lambda_27_loss: 1.7343 - val_distribution_lambda_28_loss: 0.5336\n", "Epoch 432/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.5706 - distribution_lambda_26_loss: 2.2750 - distribution_lambda_27_loss: 1.7633 - distribution_lambda_28_loss: 0.5323 - val_loss: 4.5225 - val_distribution_lambda_26_loss: 2.2562 - val_distribution_lambda_27_loss: 1.7327 - val_distribution_lambda_28_loss: 0.5336\n", "Epoch 433/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 4.5841 - distribution_lambda_26_loss: 2.2714 - distribution_lambda_27_loss: 1.7818 - distribution_lambda_28_loss: 0.5308 - val_loss: 4.5156 - val_distribution_lambda_26_loss: 2.2507 - val_distribution_lambda_27_loss: 1.7314 - val_distribution_lambda_28_loss: 0.5335\n", "Epoch 434/2500\n", "8/8 [==============================] - 0s 8ms/step - loss: 4.5735 - distribution_lambda_26_loss: 2.2679 - distribution_lambda_27_loss: 1.7777 - distribution_lambda_28_loss: 0.5279 - val_loss: 4.5088 - val_distribution_lambda_26_loss: 2.2452 - val_distribution_lambda_27_loss: 1.7302 - val_distribution_lambda_28_loss: 0.5335\n", "Epoch 435/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.5560 - distribution_lambda_26_loss: 2.2618 - distribution_lambda_27_loss: 1.7628 - distribution_lambda_28_loss: 0.5314 - val_loss: 4.5023 - val_distribution_lambda_26_loss: 2.2396 - val_distribution_lambda_27_loss: 1.7291 - val_distribution_lambda_28_loss: 0.5336\n", "Epoch 436/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.5328 - distribution_lambda_26_loss: 2.2522 - distribution_lambda_27_loss: 1.7491 - distribution_lambda_28_loss: 0.5315 - val_loss: 4.4953 - val_distribution_lambda_26_loss: 2.2340 - val_distribution_lambda_27_loss: 1.7278 - val_distribution_lambda_28_loss: 0.5334\n", "Epoch 437/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.5530 - distribution_lambda_26_loss: 2.2464 - distribution_lambda_27_loss: 1.7732 - distribution_lambda_28_loss: 0.5335 - val_loss: 4.4883 - val_distribution_lambda_26_loss: 2.2284 - val_distribution_lambda_27_loss: 1.7264 - val_distribution_lambda_28_loss: 0.5334\n", "Epoch 438/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.5345 - distribution_lambda_26_loss: 2.2401 - distribution_lambda_27_loss: 1.7645 - distribution_lambda_28_loss: 0.5299 - val_loss: 4.4809 - val_distribution_lambda_26_loss: 2.2228 - val_distribution_lambda_27_loss: 1.7249 - val_distribution_lambda_28_loss: 0.5333\n", "Epoch 439/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.5094 - distribution_lambda_26_loss: 2.2349 - distribution_lambda_27_loss: 1.7487 - distribution_lambda_28_loss: 0.5257 - val_loss: 4.4738 - val_distribution_lambda_26_loss: 2.2172 - val_distribution_lambda_27_loss: 1.7236 - val_distribution_lambda_28_loss: 0.5331\n", "Epoch 440/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.5321 - distribution_lambda_26_loss: 2.2308 - distribution_lambda_27_loss: 1.7710 - distribution_lambda_28_loss: 0.5303 - val_loss: 4.4665 - val_distribution_lambda_26_loss: 2.2115 - val_distribution_lambda_27_loss: 1.7221 - val_distribution_lambda_28_loss: 0.5330\n", "Epoch 441/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.5177 - distribution_lambda_26_loss: 2.2263 - distribution_lambda_27_loss: 1.7611 - distribution_lambda_28_loss: 0.5303 - val_loss: 4.4601 - val_distribution_lambda_26_loss: 2.2058 - val_distribution_lambda_27_loss: 1.7214 - val_distribution_lambda_28_loss: 0.5330\n", "Epoch 442/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.5094 - distribution_lambda_26_loss: 2.2190 - distribution_lambda_27_loss: 1.7587 - distribution_lambda_28_loss: 0.5317 - val_loss: 4.4528 - val_distribution_lambda_26_loss: 2.2000 - val_distribution_lambda_27_loss: 1.7197 - val_distribution_lambda_28_loss: 0.5331\n", "Epoch 443/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.5032 - distribution_lambda_26_loss: 2.2137 - distribution_lambda_27_loss: 1.7636 - distribution_lambda_28_loss: 0.5260 - val_loss: 4.4452 - val_distribution_lambda_26_loss: 2.1943 - val_distribution_lambda_27_loss: 1.7180 - val_distribution_lambda_28_loss: 0.5330\n", "Epoch 444/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.4962 - distribution_lambda_26_loss: 2.2068 - distribution_lambda_27_loss: 1.7546 - distribution_lambda_28_loss: 0.5348 - val_loss: 4.4380 - val_distribution_lambda_26_loss: 2.1885 - val_distribution_lambda_27_loss: 1.7166 - val_distribution_lambda_28_loss: 0.5330\n", "Epoch 445/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.4527 - distribution_lambda_26_loss: 2.2011 - distribution_lambda_27_loss: 1.7241 - distribution_lambda_28_loss: 0.5276 - val_loss: 4.4309 - val_distribution_lambda_26_loss: 2.1827 - val_distribution_lambda_27_loss: 1.7153 - val_distribution_lambda_28_loss: 0.5329\n", "Epoch 446/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.4635 - distribution_lambda_26_loss: 2.1961 - distribution_lambda_27_loss: 1.7393 - distribution_lambda_28_loss: 0.5281 - val_loss: 4.4237 - val_distribution_lambda_26_loss: 2.1768 - val_distribution_lambda_27_loss: 1.7140 - val_distribution_lambda_28_loss: 0.5329\n", "Epoch 447/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.4765 - distribution_lambda_26_loss: 2.1903 - distribution_lambda_27_loss: 1.7525 - distribution_lambda_28_loss: 0.5337 - val_loss: 4.4166 - val_distribution_lambda_26_loss: 2.1710 - val_distribution_lambda_27_loss: 1.7128 - val_distribution_lambda_28_loss: 0.5328\n", "Epoch 448/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.4802 - distribution_lambda_26_loss: 2.1864 - distribution_lambda_27_loss: 1.7641 - distribution_lambda_28_loss: 0.5297 - val_loss: 4.4094 - val_distribution_lambda_26_loss: 2.1651 - val_distribution_lambda_27_loss: 1.7115 - val_distribution_lambda_28_loss: 0.5328\n", "Epoch 449/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.4600 - distribution_lambda_26_loss: 2.1774 - distribution_lambda_27_loss: 1.7492 - distribution_lambda_28_loss: 0.5334 - val_loss: 4.4021 - val_distribution_lambda_26_loss: 2.1592 - val_distribution_lambda_27_loss: 1.7102 - val_distribution_lambda_28_loss: 0.5328\n", "Epoch 450/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.4401 - distribution_lambda_26_loss: 2.1730 - distribution_lambda_27_loss: 1.7439 - distribution_lambda_28_loss: 0.5231 - val_loss: 4.3947 - val_distribution_lambda_26_loss: 2.1532 - val_distribution_lambda_27_loss: 1.7089 - val_distribution_lambda_28_loss: 0.5326\n", "Epoch 451/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.4304 - distribution_lambda_26_loss: 2.1650 - distribution_lambda_27_loss: 1.7410 - distribution_lambda_28_loss: 0.5244 - val_loss: 4.3873 - val_distribution_lambda_26_loss: 2.1473 - val_distribution_lambda_27_loss: 1.7074 - val_distribution_lambda_28_loss: 0.5326\n", "Epoch 452/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.4628 - distribution_lambda_26_loss: 2.1640 - distribution_lambda_27_loss: 1.7653 - distribution_lambda_28_loss: 0.5335 - val_loss: 4.3802 - val_distribution_lambda_26_loss: 2.1413 - val_distribution_lambda_27_loss: 1.7062 - val_distribution_lambda_28_loss: 0.5327\n", "Epoch 453/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.4238 - distribution_lambda_26_loss: 2.1551 - distribution_lambda_27_loss: 1.7499 - distribution_lambda_28_loss: 0.5188 - val_loss: 4.3723 - val_distribution_lambda_26_loss: 2.1353 - val_distribution_lambda_27_loss: 1.7043 - val_distribution_lambda_28_loss: 0.5327\n", "Epoch 454/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.3983 - distribution_lambda_26_loss: 2.1490 - distribution_lambda_27_loss: 1.7248 - distribution_lambda_28_loss: 0.5246 - val_loss: 4.3646 - val_distribution_lambda_26_loss: 2.1292 - val_distribution_lambda_27_loss: 1.7026 - val_distribution_lambda_28_loss: 0.5328\n", "Epoch 455/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.3877 - distribution_lambda_26_loss: 2.1420 - distribution_lambda_27_loss: 1.7231 - distribution_lambda_28_loss: 0.5227 - val_loss: 4.3568 - val_distribution_lambda_26_loss: 2.1232 - val_distribution_lambda_27_loss: 1.7010 - val_distribution_lambda_28_loss: 0.5326\n", "Epoch 456/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.4004 - distribution_lambda_26_loss: 2.1380 - distribution_lambda_27_loss: 1.7312 - distribution_lambda_28_loss: 0.5312 - val_loss: 4.3490 - val_distribution_lambda_26_loss: 2.1171 - val_distribution_lambda_27_loss: 1.6994 - val_distribution_lambda_28_loss: 0.5325\n", "Epoch 457/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 7ms/step - loss: 4.3982 - distribution_lambda_26_loss: 2.1316 - distribution_lambda_27_loss: 1.7375 - distribution_lambda_28_loss: 0.5291 - val_loss: 4.3416 - val_distribution_lambda_26_loss: 2.1110 - val_distribution_lambda_27_loss: 1.6982 - val_distribution_lambda_28_loss: 0.5324\n", "Epoch 458/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.3890 - distribution_lambda_26_loss: 2.1236 - distribution_lambda_27_loss: 1.7370 - distribution_lambda_28_loss: 0.5284 - val_loss: 4.3346 - val_distribution_lambda_26_loss: 2.1048 - val_distribution_lambda_27_loss: 1.6972 - val_distribution_lambda_28_loss: 0.5326\n", "Epoch 459/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.3742 - distribution_lambda_26_loss: 2.1210 - distribution_lambda_27_loss: 1.7237 - distribution_lambda_28_loss: 0.5295 - val_loss: 4.3271 - val_distribution_lambda_26_loss: 2.0987 - val_distribution_lambda_27_loss: 1.6957 - val_distribution_lambda_28_loss: 0.5327\n", "Epoch 460/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.3843 - distribution_lambda_26_loss: 2.1140 - distribution_lambda_27_loss: 1.7411 - distribution_lambda_28_loss: 0.5292 - val_loss: 4.3198 - val_distribution_lambda_26_loss: 2.0925 - val_distribution_lambda_27_loss: 1.6945 - val_distribution_lambda_28_loss: 0.5328\n", "Epoch 461/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.3714 - distribution_lambda_26_loss: 2.1067 - distribution_lambda_27_loss: 1.7366 - distribution_lambda_28_loss: 0.5281 - val_loss: 4.3116 - val_distribution_lambda_26_loss: 2.0863 - val_distribution_lambda_27_loss: 1.6928 - val_distribution_lambda_28_loss: 0.5325\n", "Epoch 462/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.3664 - distribution_lambda_26_loss: 2.1000 - distribution_lambda_27_loss: 1.7366 - distribution_lambda_28_loss: 0.5299 - val_loss: 4.3039 - val_distribution_lambda_26_loss: 2.0801 - val_distribution_lambda_27_loss: 1.6914 - val_distribution_lambda_28_loss: 0.5324\n", "Epoch 463/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.3477 - distribution_lambda_26_loss: 2.0933 - distribution_lambda_27_loss: 1.7221 - distribution_lambda_28_loss: 0.5323 - val_loss: 4.2963 - val_distribution_lambda_26_loss: 2.0738 - val_distribution_lambda_27_loss: 1.6903 - val_distribution_lambda_28_loss: 0.5322\n", "Epoch 464/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.3364 - distribution_lambda_26_loss: 2.0868 - distribution_lambda_27_loss: 1.7234 - distribution_lambda_28_loss: 0.5262 - val_loss: 4.2883 - val_distribution_lambda_26_loss: 2.0676 - val_distribution_lambda_27_loss: 1.6886 - val_distribution_lambda_28_loss: 0.5322\n", "Epoch 465/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.3115 - distribution_lambda_26_loss: 2.0819 - distribution_lambda_27_loss: 1.7042 - distribution_lambda_28_loss: 0.5254 - val_loss: 4.2805 - val_distribution_lambda_26_loss: 2.0613 - val_distribution_lambda_27_loss: 1.6871 - val_distribution_lambda_28_loss: 0.5321\n", "Epoch 466/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.3241 - distribution_lambda_26_loss: 2.0734 - distribution_lambda_27_loss: 1.7197 - distribution_lambda_28_loss: 0.5311 - val_loss: 4.2727 - val_distribution_lambda_26_loss: 2.0550 - val_distribution_lambda_27_loss: 1.6856 - val_distribution_lambda_28_loss: 0.5321\n", "Epoch 467/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.3065 - distribution_lambda_26_loss: 2.0677 - distribution_lambda_27_loss: 1.7153 - distribution_lambda_28_loss: 0.5235 - val_loss: 4.2652 - val_distribution_lambda_26_loss: 2.0486 - val_distribution_lambda_27_loss: 1.6845 - val_distribution_lambda_28_loss: 0.5321\n", "Epoch 468/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.3123 - distribution_lambda_26_loss: 2.0610 - distribution_lambda_27_loss: 1.7297 - distribution_lambda_28_loss: 0.5217 - val_loss: 4.2575 - val_distribution_lambda_26_loss: 2.0423 - val_distribution_lambda_27_loss: 1.6831 - val_distribution_lambda_28_loss: 0.5321\n", "Epoch 469/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.3050 - distribution_lambda_26_loss: 2.0557 - distribution_lambda_27_loss: 1.7277 - distribution_lambda_28_loss: 0.5216 - val_loss: 4.2502 - val_distribution_lambda_26_loss: 2.0359 - val_distribution_lambda_27_loss: 1.6821 - val_distribution_lambda_28_loss: 0.5322\n", "Epoch 470/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.2991 - distribution_lambda_26_loss: 2.0487 - distribution_lambda_27_loss: 1.7185 - distribution_lambda_28_loss: 0.5319 - val_loss: 4.2422 - val_distribution_lambda_26_loss: 2.0295 - val_distribution_lambda_27_loss: 1.6806 - val_distribution_lambda_28_loss: 0.5322\n", "Epoch 471/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.2835 - distribution_lambda_26_loss: 2.0415 - distribution_lambda_27_loss: 1.7167 - distribution_lambda_28_loss: 0.5253 - val_loss: 4.2339 - val_distribution_lambda_26_loss: 2.0231 - val_distribution_lambda_27_loss: 1.6787 - val_distribution_lambda_28_loss: 0.5321\n", "Epoch 472/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.2774 - distribution_lambda_26_loss: 2.0396 - distribution_lambda_27_loss: 1.7065 - distribution_lambda_28_loss: 0.5314 - val_loss: 4.2259 - val_distribution_lambda_26_loss: 2.0167 - val_distribution_lambda_27_loss: 1.6772 - val_distribution_lambda_28_loss: 0.5320\n", "Epoch 473/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.2610 - distribution_lambda_26_loss: 2.0294 - distribution_lambda_27_loss: 1.7055 - distribution_lambda_28_loss: 0.5261 - val_loss: 4.2181 - val_distribution_lambda_26_loss: 2.0102 - val_distribution_lambda_27_loss: 1.6758 - val_distribution_lambda_28_loss: 0.5320\n", "Epoch 474/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.2583 - distribution_lambda_26_loss: 2.0230 - distribution_lambda_27_loss: 1.7060 - distribution_lambda_28_loss: 0.5293 - val_loss: 4.2102 - val_distribution_lambda_26_loss: 2.0037 - val_distribution_lambda_27_loss: 1.6744 - val_distribution_lambda_28_loss: 0.5320\n", "Epoch 475/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.2467 - distribution_lambda_26_loss: 2.0170 - distribution_lambda_27_loss: 1.7049 - distribution_lambda_28_loss: 0.5248 - val_loss: 4.2023 - val_distribution_lambda_26_loss: 1.9972 - val_distribution_lambda_27_loss: 1.6730 - val_distribution_lambda_28_loss: 0.5321\n", "Epoch 476/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.2343 - distribution_lambda_26_loss: 2.0099 - distribution_lambda_27_loss: 1.6990 - distribution_lambda_28_loss: 0.5253 - val_loss: 4.1944 - val_distribution_lambda_26_loss: 1.9907 - val_distribution_lambda_27_loss: 1.6716 - val_distribution_lambda_28_loss: 0.5321\n", "Epoch 477/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.2142 - distribution_lambda_26_loss: 2.0026 - distribution_lambda_27_loss: 1.6882 - distribution_lambda_28_loss: 0.5234 - val_loss: 4.1862 - val_distribution_lambda_26_loss: 1.9842 - val_distribution_lambda_27_loss: 1.6698 - val_distribution_lambda_28_loss: 0.5322\n", "Epoch 478/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.2193 - distribution_lambda_26_loss: 1.9995 - distribution_lambda_27_loss: 1.6958 - distribution_lambda_28_loss: 0.5240 - val_loss: 4.1783 - val_distribution_lambda_26_loss: 1.9776 - val_distribution_lambda_27_loss: 1.6684 - val_distribution_lambda_28_loss: 0.5323\n", "Epoch 479/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.1985 - distribution_lambda_26_loss: 1.9897 - distribution_lambda_27_loss: 1.6871 - distribution_lambda_28_loss: 0.5217 - val_loss: 4.1702 - val_distribution_lambda_26_loss: 1.9711 - val_distribution_lambda_27_loss: 1.6670 - val_distribution_lambda_28_loss: 0.5321\n", "Epoch 480/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.2024 - distribution_lambda_26_loss: 1.9831 - distribution_lambda_27_loss: 1.6898 - distribution_lambda_28_loss: 0.5294 - val_loss: 4.1624 - val_distribution_lambda_26_loss: 1.9645 - val_distribution_lambda_27_loss: 1.6656 - val_distribution_lambda_28_loss: 0.5323\n", "Epoch 481/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 4.2002 - distribution_lambda_26_loss: 1.9769 - distribution_lambda_27_loss: 1.7030 - distribution_lambda_28_loss: 0.5203 - val_loss: 4.1541 - val_distribution_lambda_26_loss: 1.9579 - val_distribution_lambda_27_loss: 1.6638 - val_distribution_lambda_28_loss: 0.5325\n", "Epoch 482/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.1873 - distribution_lambda_26_loss: 1.9707 - distribution_lambda_27_loss: 1.6970 - distribution_lambda_28_loss: 0.5196 - val_loss: 4.1460 - val_distribution_lambda_26_loss: 1.9512 - val_distribution_lambda_27_loss: 1.6624 - val_distribution_lambda_28_loss: 0.5324\n", "Epoch 483/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.1798 - distribution_lambda_26_loss: 1.9639 - distribution_lambda_27_loss: 1.6905 - distribution_lambda_28_loss: 0.5255 - val_loss: 4.1380 - val_distribution_lambda_26_loss: 1.9446 - val_distribution_lambda_27_loss: 1.6611 - val_distribution_lambda_28_loss: 0.5324\n", "Epoch 484/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.1692 - distribution_lambda_26_loss: 1.9582 - distribution_lambda_27_loss: 1.6905 - distribution_lambda_28_loss: 0.5205 - val_loss: 4.1294 - val_distribution_lambda_26_loss: 1.9379 - val_distribution_lambda_27_loss: 1.6594 - val_distribution_lambda_28_loss: 0.5321\n", "Epoch 485/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.1587 - distribution_lambda_26_loss: 1.9495 - distribution_lambda_27_loss: 1.6916 - distribution_lambda_28_loss: 0.5177 - val_loss: 4.1209 - val_distribution_lambda_26_loss: 1.9312 - val_distribution_lambda_27_loss: 1.6576 - val_distribution_lambda_28_loss: 0.5321\n", "Epoch 486/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.1396 - distribution_lambda_26_loss: 1.9439 - distribution_lambda_27_loss: 1.6760 - distribution_lambda_28_loss: 0.5197 - val_loss: 4.1121 - val_distribution_lambda_26_loss: 1.9245 - val_distribution_lambda_27_loss: 1.6557 - val_distribution_lambda_28_loss: 0.5319\n", "Epoch 487/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.1448 - distribution_lambda_26_loss: 1.9382 - distribution_lambda_27_loss: 1.6788 - distribution_lambda_28_loss: 0.5277 - val_loss: 4.1042 - val_distribution_lambda_26_loss: 1.9178 - val_distribution_lambda_27_loss: 1.6545 - val_distribution_lambda_28_loss: 0.5319\n", "Epoch 488/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.1433 - distribution_lambda_26_loss: 1.9310 - distribution_lambda_27_loss: 1.6792 - distribution_lambda_28_loss: 0.5330 - val_loss: 4.0960 - val_distribution_lambda_26_loss: 1.9111 - val_distribution_lambda_27_loss: 1.6532 - val_distribution_lambda_28_loss: 0.5318\n", "Epoch 489/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.1147 - distribution_lambda_26_loss: 1.9233 - distribution_lambda_27_loss: 1.6712 - distribution_lambda_28_loss: 0.5203 - val_loss: 4.0876 - val_distribution_lambda_26_loss: 1.9043 - val_distribution_lambda_27_loss: 1.6515 - val_distribution_lambda_28_loss: 0.5318\n", "Epoch 490/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.1142 - distribution_lambda_26_loss: 1.9163 - distribution_lambda_27_loss: 1.6824 - distribution_lambda_28_loss: 0.5155 - val_loss: 4.0793 - val_distribution_lambda_26_loss: 1.8976 - val_distribution_lambda_27_loss: 1.6500 - val_distribution_lambda_28_loss: 0.5317\n", "Epoch 491/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.1075 - distribution_lambda_26_loss: 1.9092 - distribution_lambda_27_loss: 1.6729 - distribution_lambda_28_loss: 0.5254 - val_loss: 4.0710 - val_distribution_lambda_26_loss: 1.8908 - val_distribution_lambda_27_loss: 1.6487 - val_distribution_lambda_28_loss: 0.5315\n", "Epoch 492/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.1042 - distribution_lambda_26_loss: 1.9047 - distribution_lambda_27_loss: 1.6813 - distribution_lambda_28_loss: 0.5181 - val_loss: 4.0628 - val_distribution_lambda_26_loss: 1.8840 - val_distribution_lambda_27_loss: 1.6472 - val_distribution_lambda_28_loss: 0.5316\n", "Epoch 493/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.0889 - distribution_lambda_26_loss: 1.8972 - distribution_lambda_27_loss: 1.6702 - distribution_lambda_28_loss: 0.5215 - val_loss: 4.0547 - val_distribution_lambda_26_loss: 1.8772 - val_distribution_lambda_27_loss: 1.6461 - val_distribution_lambda_28_loss: 0.5314\n", "Epoch 494/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.1028 - distribution_lambda_26_loss: 1.8921 - distribution_lambda_27_loss: 1.6886 - distribution_lambda_28_loss: 0.5220 - val_loss: 4.0468 - val_distribution_lambda_26_loss: 1.8703 - val_distribution_lambda_27_loss: 1.6451 - val_distribution_lambda_28_loss: 0.5314\n", "Epoch 495/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 4.0693 - distribution_lambda_26_loss: 1.8829 - distribution_lambda_27_loss: 1.6642 - distribution_lambda_28_loss: 0.5222 - val_loss: 4.0388 - val_distribution_lambda_26_loss: 1.8635 - val_distribution_lambda_27_loss: 1.6438 - val_distribution_lambda_28_loss: 0.5315\n", "Epoch 496/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.0724 - distribution_lambda_26_loss: 1.8746 - distribution_lambda_27_loss: 1.6727 - distribution_lambda_28_loss: 0.5251 - val_loss: 4.0311 - val_distribution_lambda_26_loss: 1.8566 - val_distribution_lambda_27_loss: 1.6429 - val_distribution_lambda_28_loss: 0.5315\n", "Epoch 497/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.0608 - distribution_lambda_26_loss: 1.8689 - distribution_lambda_27_loss: 1.6681 - distribution_lambda_28_loss: 0.5238 - val_loss: 4.0230 - val_distribution_lambda_26_loss: 1.8498 - val_distribution_lambda_27_loss: 1.6418 - val_distribution_lambda_28_loss: 0.5314\n", "Epoch 498/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.0655 - distribution_lambda_26_loss: 1.8624 - distribution_lambda_27_loss: 1.6802 - distribution_lambda_28_loss: 0.5229 - val_loss: 4.0150 - val_distribution_lambda_26_loss: 1.8429 - val_distribution_lambda_27_loss: 1.6407 - val_distribution_lambda_28_loss: 0.5314\n", "Epoch 499/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.0391 - distribution_lambda_26_loss: 1.8551 - distribution_lambda_27_loss: 1.6593 - distribution_lambda_28_loss: 0.5247 - val_loss: 4.0068 - val_distribution_lambda_26_loss: 1.8360 - val_distribution_lambda_27_loss: 1.6393 - val_distribution_lambda_28_loss: 0.5315\n", "Epoch 500/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.0335 - distribution_lambda_26_loss: 1.8484 - distribution_lambda_27_loss: 1.6629 - distribution_lambda_28_loss: 0.5223 - val_loss: 3.9983 - val_distribution_lambda_26_loss: 1.8290 - val_distribution_lambda_27_loss: 1.6378 - val_distribution_lambda_28_loss: 0.5314\n", "Epoch 501/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.0318 - distribution_lambda_26_loss: 1.8404 - distribution_lambda_27_loss: 1.6713 - distribution_lambda_28_loss: 0.5201 - val_loss: 3.9894 - val_distribution_lambda_26_loss: 1.8221 - val_distribution_lambda_27_loss: 1.6362 - val_distribution_lambda_28_loss: 0.5311\n", "Epoch 502/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.0309 - distribution_lambda_26_loss: 1.8351 - distribution_lambda_27_loss: 1.6706 - distribution_lambda_28_loss: 0.5252 - val_loss: 3.9810 - val_distribution_lambda_26_loss: 1.8152 - val_distribution_lambda_27_loss: 1.6348 - val_distribution_lambda_28_loss: 0.5310\n", "Epoch 503/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.0240 - distribution_lambda_26_loss: 1.8271 - distribution_lambda_27_loss: 1.6739 - distribution_lambda_28_loss: 0.5229 - val_loss: 3.9728 - val_distribution_lambda_26_loss: 1.8082 - val_distribution_lambda_27_loss: 1.6338 - val_distribution_lambda_28_loss: 0.5309\n", "Epoch 504/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.0048 - distribution_lambda_26_loss: 1.8215 - distribution_lambda_27_loss: 1.6624 - distribution_lambda_28_loss: 0.5209 - val_loss: 3.9649 - val_distribution_lambda_26_loss: 1.8012 - val_distribution_lambda_27_loss: 1.6328 - val_distribution_lambda_28_loss: 0.5308\n", "Epoch 505/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 3.9927 - distribution_lambda_26_loss: 1.8123 - distribution_lambda_27_loss: 1.6617 - distribution_lambda_28_loss: 0.5187 - val_loss: 3.9567 - val_distribution_lambda_26_loss: 1.7943 - val_distribution_lambda_27_loss: 1.6319 - val_distribution_lambda_28_loss: 0.5306\n", "Epoch 506/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.9746 - distribution_lambda_26_loss: 1.8061 - distribution_lambda_27_loss: 1.6518 - distribution_lambda_28_loss: 0.5168 - val_loss: 3.9488 - val_distribution_lambda_26_loss: 1.7872 - val_distribution_lambda_27_loss: 1.6309 - val_distribution_lambda_28_loss: 0.5306\n", "Epoch 507/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 3.9792 - distribution_lambda_26_loss: 1.7987 - distribution_lambda_27_loss: 1.6618 - distribution_lambda_28_loss: 0.5187 - val_loss: 3.9408 - val_distribution_lambda_26_loss: 1.7803 - val_distribution_lambda_27_loss: 1.6300 - val_distribution_lambda_28_loss: 0.5305\n", "Epoch 508/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.9693 - distribution_lambda_26_loss: 1.7915 - distribution_lambda_27_loss: 1.6551 - distribution_lambda_28_loss: 0.5228 - val_loss: 3.9326 - val_distribution_lambda_26_loss: 1.7732 - val_distribution_lambda_27_loss: 1.6288 - val_distribution_lambda_28_loss: 0.5305\n", "Epoch 509/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 4.0086 - distribution_lambda_26_loss: 1.7867 - distribution_lambda_27_loss: 1.6975 - distribution_lambda_28_loss: 0.5244 - val_loss: 3.9242 - val_distribution_lambda_26_loss: 1.7662 - val_distribution_lambda_27_loss: 1.6275 - val_distribution_lambda_28_loss: 0.5305\n", "Epoch 510/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.9567 - distribution_lambda_26_loss: 1.7779 - distribution_lambda_27_loss: 1.6550 - distribution_lambda_28_loss: 0.5239 - val_loss: 3.9155 - val_distribution_lambda_26_loss: 1.7592 - val_distribution_lambda_27_loss: 1.6262 - val_distribution_lambda_28_loss: 0.5301\n", "Epoch 511/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.9443 - distribution_lambda_26_loss: 1.7701 - distribution_lambda_27_loss: 1.6564 - distribution_lambda_28_loss: 0.5178 - val_loss: 3.9072 - val_distribution_lambda_26_loss: 1.7521 - val_distribution_lambda_27_loss: 1.6249 - val_distribution_lambda_28_loss: 0.5301\n", "Epoch 512/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.9195 - distribution_lambda_26_loss: 1.7641 - distribution_lambda_27_loss: 1.6420 - distribution_lambda_28_loss: 0.5134 - val_loss: 3.8989 - val_distribution_lambda_26_loss: 1.7451 - val_distribution_lambda_27_loss: 1.6240 - val_distribution_lambda_28_loss: 0.5299\n", "Epoch 513/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.9157 - distribution_lambda_26_loss: 1.7549 - distribution_lambda_27_loss: 1.6427 - distribution_lambda_28_loss: 0.5181 - val_loss: 3.8907 - val_distribution_lambda_26_loss: 1.7380 - val_distribution_lambda_27_loss: 1.6232 - val_distribution_lambda_28_loss: 0.5295\n", "Epoch 514/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.9115 - distribution_lambda_26_loss: 1.7490 - distribution_lambda_27_loss: 1.6525 - distribution_lambda_28_loss: 0.5100 - val_loss: 3.8826 - val_distribution_lambda_26_loss: 1.7310 - val_distribution_lambda_27_loss: 1.6224 - val_distribution_lambda_28_loss: 0.5293\n", "Epoch 515/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.8976 - distribution_lambda_26_loss: 1.7404 - distribution_lambda_27_loss: 1.6408 - distribution_lambda_28_loss: 0.5163 - val_loss: 3.8745 - val_distribution_lambda_26_loss: 1.7239 - val_distribution_lambda_27_loss: 1.6214 - val_distribution_lambda_28_loss: 0.5291\n", "Epoch 516/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.9053 - distribution_lambda_26_loss: 1.7358 - distribution_lambda_27_loss: 1.6499 - distribution_lambda_28_loss: 0.5196 - val_loss: 3.8662 - val_distribution_lambda_26_loss: 1.7168 - val_distribution_lambda_27_loss: 1.6205 - val_distribution_lambda_28_loss: 0.5289\n", "Epoch 517/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 3.8875 - distribution_lambda_26_loss: 1.7269 - distribution_lambda_27_loss: 1.6405 - distribution_lambda_28_loss: 0.5201 - val_loss: 3.8578 - val_distribution_lambda_26_loss: 1.7098 - val_distribution_lambda_27_loss: 1.6193 - val_distribution_lambda_28_loss: 0.5287\n", "Epoch 518/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.8916 - distribution_lambda_26_loss: 1.7206 - distribution_lambda_27_loss: 1.6486 - distribution_lambda_28_loss: 0.5224 - val_loss: 3.8497 - val_distribution_lambda_26_loss: 1.7027 - val_distribution_lambda_27_loss: 1.6186 - val_distribution_lambda_28_loss: 0.5285\n", "Epoch 519/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.8711 - distribution_lambda_26_loss: 1.7140 - distribution_lambda_27_loss: 1.6402 - distribution_lambda_28_loss: 0.5170 - val_loss: 3.8414 - val_distribution_lambda_26_loss: 1.6956 - val_distribution_lambda_27_loss: 1.6176 - val_distribution_lambda_28_loss: 0.5283\n", "Epoch 520/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.8738 - distribution_lambda_26_loss: 1.7071 - distribution_lambda_27_loss: 1.6469 - distribution_lambda_28_loss: 0.5198 - val_loss: 3.8332 - val_distribution_lambda_26_loss: 1.6885 - val_distribution_lambda_27_loss: 1.6165 - val_distribution_lambda_28_loss: 0.5282\n", "Epoch 521/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.8456 - distribution_lambda_26_loss: 1.6979 - distribution_lambda_27_loss: 1.6349 - distribution_lambda_28_loss: 0.5128 - val_loss: 3.8251 - val_distribution_lambda_26_loss: 1.6814 - val_distribution_lambda_27_loss: 1.6155 - val_distribution_lambda_28_loss: 0.5281\n", "Epoch 522/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.8455 - distribution_lambda_26_loss: 1.6907 - distribution_lambda_27_loss: 1.6368 - distribution_lambda_28_loss: 0.5180 - val_loss: 3.8170 - val_distribution_lambda_26_loss: 1.6743 - val_distribution_lambda_27_loss: 1.6145 - val_distribution_lambda_28_loss: 0.5281\n", "Epoch 523/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.8343 - distribution_lambda_26_loss: 1.6828 - distribution_lambda_27_loss: 1.6372 - distribution_lambda_28_loss: 0.5143 - val_loss: 3.8088 - val_distribution_lambda_26_loss: 1.6673 - val_distribution_lambda_27_loss: 1.6137 - val_distribution_lambda_28_loss: 0.5279\n", "Epoch 524/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.8342 - distribution_lambda_26_loss: 1.6766 - distribution_lambda_27_loss: 1.6415 - distribution_lambda_28_loss: 0.5162 - val_loss: 3.8008 - val_distribution_lambda_26_loss: 1.6602 - val_distribution_lambda_27_loss: 1.6129 - val_distribution_lambda_28_loss: 0.5277\n", "Epoch 525/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.8395 - distribution_lambda_26_loss: 1.6698 - distribution_lambda_27_loss: 1.6455 - distribution_lambda_28_loss: 0.5241 - val_loss: 3.7927 - val_distribution_lambda_26_loss: 1.6531 - val_distribution_lambda_27_loss: 1.6119 - val_distribution_lambda_28_loss: 0.5277\n", "Epoch 526/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.8169 - distribution_lambda_26_loss: 1.6625 - distribution_lambda_27_loss: 1.6385 - distribution_lambda_28_loss: 0.5159 - val_loss: 3.7845 - val_distribution_lambda_26_loss: 1.6461 - val_distribution_lambda_27_loss: 1.6109 - val_distribution_lambda_28_loss: 0.5275\n", "Epoch 527/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.8020 - distribution_lambda_26_loss: 1.6538 - distribution_lambda_27_loss: 1.6296 - distribution_lambda_28_loss: 0.5186 - val_loss: 3.7763 - val_distribution_lambda_26_loss: 1.6390 - val_distribution_lambda_27_loss: 1.6099 - val_distribution_lambda_28_loss: 0.5274\n", "Epoch 528/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.7980 - distribution_lambda_26_loss: 1.6486 - distribution_lambda_27_loss: 1.6346 - distribution_lambda_28_loss: 0.5149 - val_loss: 3.7683 - val_distribution_lambda_26_loss: 1.6319 - val_distribution_lambda_27_loss: 1.6092 - val_distribution_lambda_28_loss: 0.5272\n", "Epoch 529/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 3.7921 - distribution_lambda_26_loss: 1.6396 - distribution_lambda_27_loss: 1.6326 - distribution_lambda_28_loss: 0.5198 - val_loss: 3.7603 - val_distribution_lambda_26_loss: 1.6249 - val_distribution_lambda_27_loss: 1.6083 - val_distribution_lambda_28_loss: 0.5271\n", "Epoch 530/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.7948 - distribution_lambda_26_loss: 1.6337 - distribution_lambda_27_loss: 1.6346 - distribution_lambda_28_loss: 0.5265 - val_loss: 3.7523 - val_distribution_lambda_26_loss: 1.6178 - val_distribution_lambda_27_loss: 1.6074 - val_distribution_lambda_28_loss: 0.5271\n", "Epoch 531/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.7784 - distribution_lambda_26_loss: 1.6255 - distribution_lambda_27_loss: 1.6338 - distribution_lambda_28_loss: 0.5191 - val_loss: 3.7441 - val_distribution_lambda_26_loss: 1.6107 - val_distribution_lambda_27_loss: 1.6064 - val_distribution_lambda_28_loss: 0.5270\n", "Epoch 532/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.7735 - distribution_lambda_26_loss: 1.6187 - distribution_lambda_27_loss: 1.6249 - distribution_lambda_28_loss: 0.5299 - val_loss: 3.7363 - val_distribution_lambda_26_loss: 1.6037 - val_distribution_lambda_27_loss: 1.6057 - val_distribution_lambda_28_loss: 0.5269\n", "Epoch 533/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.7618 - distribution_lambda_26_loss: 1.6103 - distribution_lambda_27_loss: 1.6324 - distribution_lambda_28_loss: 0.5191 - val_loss: 3.7285 - val_distribution_lambda_26_loss: 1.5966 - val_distribution_lambda_27_loss: 1.6050 - val_distribution_lambda_28_loss: 0.5269\n", "Epoch 534/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.7337 - distribution_lambda_26_loss: 1.6034 - distribution_lambda_27_loss: 1.6228 - distribution_lambda_28_loss: 0.5075 - val_loss: 3.7203 - val_distribution_lambda_26_loss: 1.5896 - val_distribution_lambda_27_loss: 1.6043 - val_distribution_lambda_28_loss: 0.5264\n", "Epoch 535/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.7657 - distribution_lambda_26_loss: 1.5976 - distribution_lambda_27_loss: 1.6426 - distribution_lambda_28_loss: 0.5255 - val_loss: 3.7126 - val_distribution_lambda_26_loss: 1.5826 - val_distribution_lambda_27_loss: 1.6038 - val_distribution_lambda_28_loss: 0.5263\n", "Epoch 536/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.7397 - distribution_lambda_26_loss: 1.5886 - distribution_lambda_27_loss: 1.6302 - distribution_lambda_28_loss: 0.5210 - val_loss: 3.7047 - val_distribution_lambda_26_loss: 1.5755 - val_distribution_lambda_27_loss: 1.6030 - val_distribution_lambda_28_loss: 0.5263\n", "Epoch 537/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.7278 - distribution_lambda_26_loss: 1.5828 - distribution_lambda_27_loss: 1.6257 - distribution_lambda_28_loss: 0.5193 - val_loss: 3.6968 - val_distribution_lambda_26_loss: 1.5684 - val_distribution_lambda_27_loss: 1.6025 - val_distribution_lambda_28_loss: 0.5259\n", "Epoch 538/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 3.7042 - distribution_lambda_26_loss: 1.5737 - distribution_lambda_27_loss: 1.6124 - distribution_lambda_28_loss: 0.5182 - val_loss: 3.6889 - val_distribution_lambda_26_loss: 1.5614 - val_distribution_lambda_27_loss: 1.6018 - val_distribution_lambda_28_loss: 0.5256\n", "Epoch 539/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 3.6909 - distribution_lambda_26_loss: 1.5671 - distribution_lambda_27_loss: 1.6107 - distribution_lambda_28_loss: 0.5131 - val_loss: 3.6810 - val_distribution_lambda_26_loss: 1.5544 - val_distribution_lambda_27_loss: 1.6011 - val_distribution_lambda_28_loss: 0.5256\n", "Epoch 540/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.6920 - distribution_lambda_26_loss: 1.5601 - distribution_lambda_27_loss: 1.6183 - distribution_lambda_28_loss: 0.5136 - val_loss: 3.6726 - val_distribution_lambda_26_loss: 1.5473 - val_distribution_lambda_27_loss: 1.5998 - val_distribution_lambda_28_loss: 0.5255\n", "Epoch 541/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.6918 - distribution_lambda_26_loss: 1.5541 - distribution_lambda_27_loss: 1.6202 - distribution_lambda_28_loss: 0.5175 - val_loss: 3.6640 - val_distribution_lambda_26_loss: 1.5402 - val_distribution_lambda_27_loss: 1.5985 - val_distribution_lambda_28_loss: 0.5254\n", "Epoch 542/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.6885 - distribution_lambda_26_loss: 1.5446 - distribution_lambda_27_loss: 1.6284 - distribution_lambda_28_loss: 0.5155 - val_loss: 3.6560 - val_distribution_lambda_26_loss: 1.5330 - val_distribution_lambda_27_loss: 1.5975 - val_distribution_lambda_28_loss: 0.5255\n", "Epoch 543/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.6679 - distribution_lambda_26_loss: 1.5389 - distribution_lambda_27_loss: 1.6114 - distribution_lambda_28_loss: 0.5176 - val_loss: 3.6481 - val_distribution_lambda_26_loss: 1.5258 - val_distribution_lambda_27_loss: 1.5971 - val_distribution_lambda_28_loss: 0.5253\n", "Epoch 544/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.6635 - distribution_lambda_26_loss: 1.5300 - distribution_lambda_27_loss: 1.6167 - distribution_lambda_28_loss: 0.5167 - val_loss: 3.6397 - val_distribution_lambda_26_loss: 1.5185 - val_distribution_lambda_27_loss: 1.5964 - val_distribution_lambda_28_loss: 0.5248\n", "Epoch 545/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.6638 - distribution_lambda_26_loss: 1.5233 - distribution_lambda_27_loss: 1.6263 - distribution_lambda_28_loss: 0.5142 - val_loss: 3.6314 - val_distribution_lambda_26_loss: 1.5110 - val_distribution_lambda_27_loss: 1.5957 - val_distribution_lambda_28_loss: 0.5246\n", "Epoch 546/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.6467 - distribution_lambda_26_loss: 1.5142 - distribution_lambda_27_loss: 1.6183 - distribution_lambda_28_loss: 0.5142 - val_loss: 3.6229 - val_distribution_lambda_26_loss: 1.5035 - val_distribution_lambda_27_loss: 1.5951 - val_distribution_lambda_28_loss: 0.5242\n", "Epoch 547/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.6405 - distribution_lambda_26_loss: 1.5073 - distribution_lambda_27_loss: 1.6142 - distribution_lambda_28_loss: 0.5190 - val_loss: 3.6142 - val_distribution_lambda_26_loss: 1.4957 - val_distribution_lambda_27_loss: 1.5942 - val_distribution_lambda_28_loss: 0.5243\n", "Epoch 548/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.6244 - distribution_lambda_26_loss: 1.4968 - distribution_lambda_27_loss: 1.6124 - distribution_lambda_28_loss: 0.5151 - val_loss: 3.6055 - val_distribution_lambda_26_loss: 1.4877 - val_distribution_lambda_27_loss: 1.5936 - val_distribution_lambda_28_loss: 0.5242\n", "Epoch 549/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.6162 - distribution_lambda_26_loss: 1.4882 - distribution_lambda_27_loss: 1.6111 - distribution_lambda_28_loss: 0.5169 - val_loss: 3.5965 - val_distribution_lambda_26_loss: 1.4792 - val_distribution_lambda_27_loss: 1.5934 - val_distribution_lambda_28_loss: 0.5239\n", "Epoch 550/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.5926 - distribution_lambda_26_loss: 1.4800 - distribution_lambda_27_loss: 1.5989 - distribution_lambda_28_loss: 0.5136 - val_loss: 3.5868 - val_distribution_lambda_26_loss: 1.4702 - val_distribution_lambda_27_loss: 1.5929 - val_distribution_lambda_28_loss: 0.5237\n", "Epoch 551/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.5868 - distribution_lambda_26_loss: 1.4705 - distribution_lambda_27_loss: 1.6041 - distribution_lambda_28_loss: 0.5122 - val_loss: 3.5764 - val_distribution_lambda_26_loss: 1.4605 - val_distribution_lambda_27_loss: 1.5923 - val_distribution_lambda_28_loss: 0.5237\n", "Epoch 552/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.5721 - distribution_lambda_26_loss: 1.4605 - distribution_lambda_27_loss: 1.6004 - distribution_lambda_28_loss: 0.5112 - val_loss: 3.5652 - val_distribution_lambda_26_loss: 1.4499 - val_distribution_lambda_27_loss: 1.5918 - val_distribution_lambda_28_loss: 0.5235\n", "Epoch 553/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 3.5595 - distribution_lambda_26_loss: 1.4479 - distribution_lambda_27_loss: 1.6006 - distribution_lambda_28_loss: 0.5110 - val_loss: 3.5528 - val_distribution_lambda_26_loss: 1.4384 - val_distribution_lambda_27_loss: 1.5910 - val_distribution_lambda_28_loss: 0.5234\n", "Epoch 554/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.5528 - distribution_lambda_26_loss: 1.4368 - distribution_lambda_27_loss: 1.6021 - distribution_lambda_28_loss: 0.5138 - val_loss: 3.5397 - val_distribution_lambda_26_loss: 1.4263 - val_distribution_lambda_27_loss: 1.5902 - val_distribution_lambda_28_loss: 0.5232\n", "Epoch 555/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.5345 - distribution_lambda_26_loss: 1.4239 - distribution_lambda_27_loss: 1.5956 - distribution_lambda_28_loss: 0.5150 - val_loss: 3.5265 - val_distribution_lambda_26_loss: 1.4139 - val_distribution_lambda_27_loss: 1.5896 - val_distribution_lambda_28_loss: 0.5230\n", "Epoch 556/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.5375 - distribution_lambda_26_loss: 1.4128 - distribution_lambda_27_loss: 1.6027 - distribution_lambda_28_loss: 0.5220 - val_loss: 3.5138 - val_distribution_lambda_26_loss: 1.4018 - val_distribution_lambda_27_loss: 1.5890 - val_distribution_lambda_28_loss: 0.5230\n", "Epoch 557/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.5352 - distribution_lambda_26_loss: 1.3989 - distribution_lambda_27_loss: 1.6175 - distribution_lambda_28_loss: 0.5188 - val_loss: 3.5016 - val_distribution_lambda_26_loss: 1.3903 - val_distribution_lambda_27_loss: 1.5888 - val_distribution_lambda_28_loss: 0.5225\n", "Epoch 558/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.4994 - distribution_lambda_26_loss: 1.3863 - distribution_lambda_27_loss: 1.5993 - distribution_lambda_28_loss: 0.5137 - val_loss: 3.4900 - val_distribution_lambda_26_loss: 1.3794 - val_distribution_lambda_27_loss: 1.5882 - val_distribution_lambda_28_loss: 0.5224\n", "Epoch 559/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.4897 - distribution_lambda_26_loss: 1.3765 - distribution_lambda_27_loss: 1.5972 - distribution_lambda_28_loss: 0.5159 - val_loss: 3.4787 - val_distribution_lambda_26_loss: 1.3689 - val_distribution_lambda_27_loss: 1.5877 - val_distribution_lambda_28_loss: 0.5220\n", "Epoch 560/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.4799 - distribution_lambda_26_loss: 1.3653 - distribution_lambda_27_loss: 1.6043 - distribution_lambda_28_loss: 0.5103 - val_loss: 3.4678 - val_distribution_lambda_26_loss: 1.3589 - val_distribution_lambda_27_loss: 1.5868 - val_distribution_lambda_28_loss: 0.5221\n", "Epoch 561/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.4626 - distribution_lambda_26_loss: 1.3531 - distribution_lambda_27_loss: 1.5964 - distribution_lambda_28_loss: 0.5131 - val_loss: 3.4573 - val_distribution_lambda_26_loss: 1.3492 - val_distribution_lambda_27_loss: 1.5859 - val_distribution_lambda_28_loss: 0.5222\n", "Epoch 562/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.4564 - distribution_lambda_26_loss: 1.3404 - distribution_lambda_27_loss: 1.6019 - distribution_lambda_28_loss: 0.5141 - val_loss: 3.4472 - val_distribution_lambda_26_loss: 1.3398 - val_distribution_lambda_27_loss: 1.5854 - val_distribution_lambda_28_loss: 0.5220\n", "Epoch 563/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.4366 - distribution_lambda_26_loss: 1.3334 - distribution_lambda_27_loss: 1.5912 - distribution_lambda_28_loss: 0.5120 - val_loss: 3.4373 - val_distribution_lambda_26_loss: 1.3307 - val_distribution_lambda_27_loss: 1.5844 - val_distribution_lambda_28_loss: 0.5222\n", "Epoch 564/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.4407 - distribution_lambda_26_loss: 1.3221 - distribution_lambda_27_loss: 1.6071 - distribution_lambda_28_loss: 0.5114 - val_loss: 3.4276 - val_distribution_lambda_26_loss: 1.3219 - val_distribution_lambda_27_loss: 1.5838 - val_distribution_lambda_28_loss: 0.5219\n", "Epoch 565/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.4186 - distribution_lambda_26_loss: 1.3095 - distribution_lambda_27_loss: 1.5948 - distribution_lambda_28_loss: 0.5142 - val_loss: 3.4181 - val_distribution_lambda_26_loss: 1.3133 - val_distribution_lambda_27_loss: 1.5831 - val_distribution_lambda_28_loss: 0.5217\n", "Epoch 566/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.4184 - distribution_lambda_26_loss: 1.2994 - distribution_lambda_27_loss: 1.6042 - distribution_lambda_28_loss: 0.5148 - val_loss: 3.4091 - val_distribution_lambda_26_loss: 1.3053 - val_distribution_lambda_27_loss: 1.5824 - val_distribution_lambda_28_loss: 0.5215\n", "Epoch 567/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.4069 - distribution_lambda_26_loss: 1.2888 - distribution_lambda_27_loss: 1.6055 - distribution_lambda_28_loss: 0.5126 - val_loss: 3.4004 - val_distribution_lambda_26_loss: 1.2977 - val_distribution_lambda_27_loss: 1.5819 - val_distribution_lambda_28_loss: 0.5209\n", "Epoch 568/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.3927 - distribution_lambda_26_loss: 1.2802 - distribution_lambda_27_loss: 1.6030 - distribution_lambda_28_loss: 0.5095 - val_loss: 3.3927 - val_distribution_lambda_26_loss: 1.2905 - val_distribution_lambda_27_loss: 1.5817 - val_distribution_lambda_28_loss: 0.5205\n", "Epoch 569/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.3787 - distribution_lambda_26_loss: 1.2718 - distribution_lambda_27_loss: 1.5948 - distribution_lambda_28_loss: 0.5121 - val_loss: 3.3858 - val_distribution_lambda_26_loss: 1.2836 - val_distribution_lambda_27_loss: 1.5819 - val_distribution_lambda_28_loss: 0.5204\n", "Epoch 570/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.3512 - distribution_lambda_26_loss: 1.2617 - distribution_lambda_27_loss: 1.5810 - distribution_lambda_28_loss: 0.5085 - val_loss: 3.3785 - val_distribution_lambda_26_loss: 1.2768 - val_distribution_lambda_27_loss: 1.5815 - val_distribution_lambda_28_loss: 0.5202\n", "Epoch 571/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.3673 - distribution_lambda_26_loss: 1.2543 - distribution_lambda_27_loss: 1.5969 - distribution_lambda_28_loss: 0.5160 - val_loss: 3.3713 - val_distribution_lambda_26_loss: 1.2701 - val_distribution_lambda_27_loss: 1.5810 - val_distribution_lambda_28_loss: 0.5203\n", "Epoch 572/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.3369 - distribution_lambda_26_loss: 1.2428 - distribution_lambda_27_loss: 1.5855 - distribution_lambda_28_loss: 0.5085 - val_loss: 3.3637 - val_distribution_lambda_26_loss: 1.2632 - val_distribution_lambda_27_loss: 1.5804 - val_distribution_lambda_28_loss: 0.5202\n", "Epoch 573/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.3348 - distribution_lambda_26_loss: 1.2381 - distribution_lambda_27_loss: 1.5829 - distribution_lambda_28_loss: 0.5138 - val_loss: 3.3560 - val_distribution_lambda_26_loss: 1.2564 - val_distribution_lambda_27_loss: 1.5796 - val_distribution_lambda_28_loss: 0.5201\n", "Epoch 574/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.3420 - distribution_lambda_26_loss: 1.2299 - distribution_lambda_27_loss: 1.5991 - distribution_lambda_28_loss: 0.5130 - val_loss: 3.3490 - val_distribution_lambda_26_loss: 1.2495 - val_distribution_lambda_27_loss: 1.5790 - val_distribution_lambda_28_loss: 0.5205\n", "Epoch 575/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.3073 - distribution_lambda_26_loss: 1.2219 - distribution_lambda_27_loss: 1.5796 - distribution_lambda_28_loss: 0.5058 - val_loss: 3.3413 - val_distribution_lambda_26_loss: 1.2428 - val_distribution_lambda_27_loss: 1.5784 - val_distribution_lambda_28_loss: 0.5201\n", "Epoch 576/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.3291 - distribution_lambda_26_loss: 1.2137 - distribution_lambda_27_loss: 1.5984 - distribution_lambda_28_loss: 0.5169 - val_loss: 3.3334 - val_distribution_lambda_26_loss: 1.2360 - val_distribution_lambda_27_loss: 1.5775 - val_distribution_lambda_28_loss: 0.5199\n", "Epoch 577/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 3.3052 - distribution_lambda_26_loss: 1.2061 - distribution_lambda_27_loss: 1.5867 - distribution_lambda_28_loss: 0.5124 - val_loss: 3.3262 - val_distribution_lambda_26_loss: 1.2293 - val_distribution_lambda_27_loss: 1.5772 - val_distribution_lambda_28_loss: 0.5197\n", "Epoch 578/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.2952 - distribution_lambda_26_loss: 1.2017 - distribution_lambda_27_loss: 1.5789 - distribution_lambda_28_loss: 0.5146 - val_loss: 3.3190 - val_distribution_lambda_26_loss: 1.2226 - val_distribution_lambda_27_loss: 1.5769 - val_distribution_lambda_28_loss: 0.5195\n", "Epoch 579/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.2782 - distribution_lambda_26_loss: 1.1918 - distribution_lambda_27_loss: 1.5804 - distribution_lambda_28_loss: 0.5061 - val_loss: 3.3113 - val_distribution_lambda_26_loss: 1.2159 - val_distribution_lambda_27_loss: 1.5761 - val_distribution_lambda_28_loss: 0.5194\n", "Epoch 580/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.2859 - distribution_lambda_26_loss: 1.1867 - distribution_lambda_27_loss: 1.5919 - distribution_lambda_28_loss: 0.5073 - val_loss: 3.3040 - val_distribution_lambda_26_loss: 1.2092 - val_distribution_lambda_27_loss: 1.5755 - val_distribution_lambda_28_loss: 0.5193\n", "Epoch 581/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.2742 - distribution_lambda_26_loss: 1.1818 - distribution_lambda_27_loss: 1.5796 - distribution_lambda_28_loss: 0.5129 - val_loss: 3.2967 - val_distribution_lambda_26_loss: 1.2026 - val_distribution_lambda_27_loss: 1.5751 - val_distribution_lambda_28_loss: 0.5190\n", "Epoch 582/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.2516 - distribution_lambda_26_loss: 1.1709 - distribution_lambda_27_loss: 1.5780 - distribution_lambda_28_loss: 0.5027 - val_loss: 3.2896 - val_distribution_lambda_26_loss: 1.1960 - val_distribution_lambda_27_loss: 1.5748 - val_distribution_lambda_28_loss: 0.5188\n", "Epoch 583/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.2546 - distribution_lambda_26_loss: 1.1623 - distribution_lambda_27_loss: 1.5780 - distribution_lambda_28_loss: 0.5143 - val_loss: 3.2829 - val_distribution_lambda_26_loss: 1.1897 - val_distribution_lambda_27_loss: 1.5746 - val_distribution_lambda_28_loss: 0.5187\n", "Epoch 584/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.2503 - distribution_lambda_26_loss: 1.1572 - distribution_lambda_27_loss: 1.5774 - distribution_lambda_28_loss: 0.5157 - val_loss: 3.2764 - val_distribution_lambda_26_loss: 1.1833 - val_distribution_lambda_27_loss: 1.5742 - val_distribution_lambda_28_loss: 0.5189\n", "Epoch 585/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.2233 - distribution_lambda_26_loss: 1.1463 - distribution_lambda_27_loss: 1.5707 - distribution_lambda_28_loss: 0.5063 - val_loss: 3.2705 - val_distribution_lambda_26_loss: 1.1772 - val_distribution_lambda_27_loss: 1.5745 - val_distribution_lambda_28_loss: 0.5188\n", "Epoch 586/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.2185 - distribution_lambda_26_loss: 1.1431 - distribution_lambda_27_loss: 1.5702 - distribution_lambda_28_loss: 0.5052 - val_loss: 3.2638 - val_distribution_lambda_26_loss: 1.1710 - val_distribution_lambda_27_loss: 1.5738 - val_distribution_lambda_28_loss: 0.5189\n", "Epoch 587/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.2081 - distribution_lambda_26_loss: 1.1325 - distribution_lambda_27_loss: 1.5709 - distribution_lambda_28_loss: 0.5047 - val_loss: 3.2563 - val_distribution_lambda_26_loss: 1.1645 - val_distribution_lambda_27_loss: 1.5728 - val_distribution_lambda_28_loss: 0.5190\n", "Epoch 588/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.2214 - distribution_lambda_26_loss: 1.1316 - distribution_lambda_27_loss: 1.5826 - distribution_lambda_28_loss: 0.5072 - val_loss: 3.2493 - val_distribution_lambda_26_loss: 1.1584 - val_distribution_lambda_27_loss: 1.5720 - val_distribution_lambda_28_loss: 0.5189\n", "Epoch 589/2500\n", "8/8 [==============================] - 0s 8ms/step - loss: 3.1924 - distribution_lambda_26_loss: 1.1231 - distribution_lambda_27_loss: 1.5671 - distribution_lambda_28_loss: 0.5022 - val_loss: 3.2420 - val_distribution_lambda_26_loss: 1.1523 - val_distribution_lambda_27_loss: 1.5711 - val_distribution_lambda_28_loss: 0.5187\n", "Epoch 590/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.1856 - distribution_lambda_26_loss: 1.1164 - distribution_lambda_27_loss: 1.5642 - distribution_lambda_28_loss: 0.5050 - val_loss: 3.2347 - val_distribution_lambda_26_loss: 1.1460 - val_distribution_lambda_27_loss: 1.5703 - val_distribution_lambda_28_loss: 0.5184\n", "Epoch 591/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.1912 - distribution_lambda_26_loss: 1.1078 - distribution_lambda_27_loss: 1.5759 - distribution_lambda_28_loss: 0.5076 - val_loss: 3.2279 - val_distribution_lambda_26_loss: 1.1399 - val_distribution_lambda_27_loss: 1.5697 - val_distribution_lambda_28_loss: 0.5184\n", "Epoch 592/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.1890 - distribution_lambda_26_loss: 1.1006 - distribution_lambda_27_loss: 1.5800 - distribution_lambda_28_loss: 0.5084 - val_loss: 3.2213 - val_distribution_lambda_26_loss: 1.1340 - val_distribution_lambda_27_loss: 1.5690 - val_distribution_lambda_28_loss: 0.5184\n", "Epoch 593/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.1638 - distribution_lambda_26_loss: 1.0949 - distribution_lambda_27_loss: 1.5654 - distribution_lambda_28_loss: 0.5034 - val_loss: 3.2145 - val_distribution_lambda_26_loss: 1.1282 - val_distribution_lambda_27_loss: 1.5685 - val_distribution_lambda_28_loss: 0.5178\n", "Epoch 594/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.1470 - distribution_lambda_26_loss: 1.0911 - distribution_lambda_27_loss: 1.5586 - distribution_lambda_28_loss: 0.4974 - val_loss: 3.2075 - val_distribution_lambda_26_loss: 1.1224 - val_distribution_lambda_27_loss: 1.5679 - val_distribution_lambda_28_loss: 0.5172\n", "Epoch 595/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.1456 - distribution_lambda_26_loss: 1.0822 - distribution_lambda_27_loss: 1.5614 - distribution_lambda_28_loss: 0.5020 - val_loss: 3.2009 - val_distribution_lambda_26_loss: 1.1168 - val_distribution_lambda_27_loss: 1.5673 - val_distribution_lambda_28_loss: 0.5168\n", "Epoch 596/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.1452 - distribution_lambda_26_loss: 1.0750 - distribution_lambda_27_loss: 1.5665 - distribution_lambda_28_loss: 0.5037 - val_loss: 3.1943 - val_distribution_lambda_26_loss: 1.1108 - val_distribution_lambda_27_loss: 1.5673 - val_distribution_lambda_28_loss: 0.5162\n", "Epoch 597/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 3.1488 - distribution_lambda_26_loss: 1.0705 - distribution_lambda_27_loss: 1.5735 - distribution_lambda_28_loss: 0.5049 - val_loss: 3.1884 - val_distribution_lambda_26_loss: 1.1054 - val_distribution_lambda_27_loss: 1.5670 - val_distribution_lambda_28_loss: 0.5160\n", "Epoch 598/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.1307 - distribution_lambda_26_loss: 1.0615 - distribution_lambda_27_loss: 1.5657 - distribution_lambda_28_loss: 0.5035 - val_loss: 3.1821 - val_distribution_lambda_26_loss: 1.1000 - val_distribution_lambda_27_loss: 1.5665 - val_distribution_lambda_28_loss: 0.5157\n", "Epoch 599/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.1077 - distribution_lambda_26_loss: 1.0517 - distribution_lambda_27_loss: 1.5560 - distribution_lambda_28_loss: 0.5000 - val_loss: 3.1763 - val_distribution_lambda_26_loss: 1.0947 - val_distribution_lambda_27_loss: 1.5660 - val_distribution_lambda_28_loss: 0.5156\n", "Epoch 600/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.1333 - distribution_lambda_26_loss: 1.0508 - distribution_lambda_27_loss: 1.5729 - distribution_lambda_28_loss: 0.5097 - val_loss: 3.1702 - val_distribution_lambda_26_loss: 1.0893 - val_distribution_lambda_27_loss: 1.5655 - val_distribution_lambda_28_loss: 0.5155\n", "Epoch 601/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 3.1230 - distribution_lambda_26_loss: 1.0500 - distribution_lambda_27_loss: 1.5715 - distribution_lambda_28_loss: 0.5016 - val_loss: 3.1637 - val_distribution_lambda_26_loss: 1.0837 - val_distribution_lambda_27_loss: 1.5643 - val_distribution_lambda_28_loss: 0.5156\n", "Epoch 602/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.1024 - distribution_lambda_26_loss: 1.0411 - distribution_lambda_27_loss: 1.5625 - distribution_lambda_28_loss: 0.4988 - val_loss: 3.1578 - val_distribution_lambda_26_loss: 1.0784 - val_distribution_lambda_27_loss: 1.5641 - val_distribution_lambda_28_loss: 0.5153\n", "Epoch 603/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.0967 - distribution_lambda_26_loss: 1.0346 - distribution_lambda_27_loss: 1.5552 - distribution_lambda_28_loss: 0.5069 - val_loss: 3.1513 - val_distribution_lambda_26_loss: 1.0731 - val_distribution_lambda_27_loss: 1.5634 - val_distribution_lambda_28_loss: 0.5148\n", "Epoch 604/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.0993 - distribution_lambda_26_loss: 1.0260 - distribution_lambda_27_loss: 1.5670 - distribution_lambda_28_loss: 0.5064 - val_loss: 3.1459 - val_distribution_lambda_26_loss: 1.0684 - val_distribution_lambda_27_loss: 1.5631 - val_distribution_lambda_28_loss: 0.5144\n", "Epoch 605/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.0905 - distribution_lambda_26_loss: 1.0235 - distribution_lambda_27_loss: 1.5647 - distribution_lambda_28_loss: 0.5023 - val_loss: 3.1404 - val_distribution_lambda_26_loss: 1.0637 - val_distribution_lambda_27_loss: 1.5626 - val_distribution_lambda_28_loss: 0.5140\n", "Epoch 606/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.0841 - distribution_lambda_26_loss: 1.0192 - distribution_lambda_27_loss: 1.5633 - distribution_lambda_28_loss: 0.5017 - val_loss: 3.1358 - val_distribution_lambda_26_loss: 1.0591 - val_distribution_lambda_27_loss: 1.5625 - val_distribution_lambda_28_loss: 0.5142\n", "Epoch 607/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.0787 - distribution_lambda_26_loss: 1.0114 - distribution_lambda_27_loss: 1.5602 - distribution_lambda_28_loss: 0.5070 - val_loss: 3.1315 - val_distribution_lambda_26_loss: 1.0543 - val_distribution_lambda_27_loss: 1.5625 - val_distribution_lambda_28_loss: 0.5147\n", "Epoch 608/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.0686 - distribution_lambda_26_loss: 1.0093 - distribution_lambda_27_loss: 1.5571 - distribution_lambda_28_loss: 0.5023 - val_loss: 3.1268 - val_distribution_lambda_26_loss: 1.0499 - val_distribution_lambda_27_loss: 1.5623 - val_distribution_lambda_28_loss: 0.5146\n", "Epoch 609/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.0497 - distribution_lambda_26_loss: 0.9945 - distribution_lambda_27_loss: 1.5470 - distribution_lambda_28_loss: 0.5081 - val_loss: 3.1216 - val_distribution_lambda_26_loss: 1.0456 - val_distribution_lambda_27_loss: 1.5617 - val_distribution_lambda_28_loss: 0.5144\n", "Epoch 610/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.0671 - distribution_lambda_26_loss: 0.9970 - distribution_lambda_27_loss: 1.5643 - distribution_lambda_28_loss: 0.5058 - val_loss: 3.1166 - val_distribution_lambda_26_loss: 1.0412 - val_distribution_lambda_27_loss: 1.5617 - val_distribution_lambda_28_loss: 0.5137\n", "Epoch 611/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.0435 - distribution_lambda_26_loss: 0.9910 - distribution_lambda_27_loss: 1.5462 - distribution_lambda_28_loss: 0.5063 - val_loss: 3.1100 - val_distribution_lambda_26_loss: 1.0360 - val_distribution_lambda_27_loss: 1.5613 - val_distribution_lambda_28_loss: 0.5128\n", "Epoch 612/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.0467 - distribution_lambda_26_loss: 0.9824 - distribution_lambda_27_loss: 1.5630 - distribution_lambda_28_loss: 0.5013 - val_loss: 3.1050 - val_distribution_lambda_26_loss: 1.0314 - val_distribution_lambda_27_loss: 1.5608 - val_distribution_lambda_28_loss: 0.5128\n", "Epoch 613/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.0163 - distribution_lambda_26_loss: 0.9817 - distribution_lambda_27_loss: 1.5372 - distribution_lambda_28_loss: 0.4974 - val_loss: 3.1000 - val_distribution_lambda_26_loss: 1.0271 - val_distribution_lambda_27_loss: 1.5602 - val_distribution_lambda_28_loss: 0.5128\n", "Epoch 614/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.0513 - distribution_lambda_26_loss: 0.9779 - distribution_lambda_27_loss: 1.5671 - distribution_lambda_28_loss: 0.5063 - val_loss: 3.0947 - val_distribution_lambda_26_loss: 1.0226 - val_distribution_lambda_27_loss: 1.5595 - val_distribution_lambda_28_loss: 0.5126\n", "Epoch 615/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.0457 - distribution_lambda_26_loss: 0.9796 - distribution_lambda_27_loss: 1.5591 - distribution_lambda_28_loss: 0.5070 - val_loss: 3.0906 - val_distribution_lambda_26_loss: 1.0186 - val_distribution_lambda_27_loss: 1.5597 - val_distribution_lambda_28_loss: 0.5123\n", "Epoch 616/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.0280 - distribution_lambda_26_loss: 0.9665 - distribution_lambda_27_loss: 1.5566 - distribution_lambda_28_loss: 0.5049 - val_loss: 3.0864 - val_distribution_lambda_26_loss: 1.0147 - val_distribution_lambda_27_loss: 1.5594 - val_distribution_lambda_28_loss: 0.5124\n", "Epoch 617/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 3.0172 - distribution_lambda_26_loss: 0.9617 - distribution_lambda_27_loss: 1.5488 - distribution_lambda_28_loss: 0.5067 - val_loss: 3.0823 - val_distribution_lambda_26_loss: 1.0111 - val_distribution_lambda_27_loss: 1.5588 - val_distribution_lambda_28_loss: 0.5124\n", "Epoch 618/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.0017 - distribution_lambda_26_loss: 0.9587 - distribution_lambda_27_loss: 1.5401 - distribution_lambda_28_loss: 0.5028 - val_loss: 3.0782 - val_distribution_lambda_26_loss: 1.0076 - val_distribution_lambda_27_loss: 1.5585 - val_distribution_lambda_28_loss: 0.5120\n", "Epoch 619/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9912 - distribution_lambda_26_loss: 0.9560 - distribution_lambda_27_loss: 1.5379 - distribution_lambda_28_loss: 0.4973 - val_loss: 3.0738 - val_distribution_lambda_26_loss: 1.0042 - val_distribution_lambda_27_loss: 1.5580 - val_distribution_lambda_28_loss: 0.5116\n", "Epoch 620/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.0097 - distribution_lambda_26_loss: 0.9543 - distribution_lambda_27_loss: 1.5504 - distribution_lambda_28_loss: 0.5049 - val_loss: 3.0686 - val_distribution_lambda_26_loss: 0.9998 - val_distribution_lambda_27_loss: 1.5574 - val_distribution_lambda_28_loss: 0.5114\n", "Epoch 621/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9945 - distribution_lambda_26_loss: 0.9449 - distribution_lambda_27_loss: 1.5496 - distribution_lambda_28_loss: 0.5000 - val_loss: 3.0648 - val_distribution_lambda_26_loss: 0.9963 - val_distribution_lambda_27_loss: 1.5576 - val_distribution_lambda_28_loss: 0.5108\n", "Epoch 622/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.0016 - distribution_lambda_26_loss: 0.9451 - distribution_lambda_27_loss: 1.5519 - distribution_lambda_28_loss: 0.5046 - val_loss: 3.0605 - val_distribution_lambda_26_loss: 0.9932 - val_distribution_lambda_27_loss: 1.5566 - val_distribution_lambda_28_loss: 0.5108\n", "Epoch 623/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 3.0089 - distribution_lambda_26_loss: 0.9438 - distribution_lambda_27_loss: 1.5615 - distribution_lambda_28_loss: 0.5036 - val_loss: 3.0566 - val_distribution_lambda_26_loss: 0.9895 - val_distribution_lambda_27_loss: 1.5566 - val_distribution_lambda_28_loss: 0.5105\n", "Epoch 624/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9849 - distribution_lambda_26_loss: 0.9323 - distribution_lambda_27_loss: 1.5580 - distribution_lambda_28_loss: 0.4946 - val_loss: 3.0529 - val_distribution_lambda_26_loss: 0.9862 - val_distribution_lambda_27_loss: 1.5565 - val_distribution_lambda_28_loss: 0.5102\n", "Epoch 625/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 5ms/step - loss: 2.9579 - distribution_lambda_26_loss: 0.9310 - distribution_lambda_27_loss: 1.5388 - distribution_lambda_28_loss: 0.4881 - val_loss: 3.0491 - val_distribution_lambda_26_loss: 0.9830 - val_distribution_lambda_27_loss: 1.5552 - val_distribution_lambda_28_loss: 0.5108\n", "Epoch 626/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9962 - distribution_lambda_26_loss: 0.9279 - distribution_lambda_27_loss: 1.5613 - distribution_lambda_28_loss: 0.5070 - val_loss: 3.0454 - val_distribution_lambda_26_loss: 0.9798 - val_distribution_lambda_27_loss: 1.5550 - val_distribution_lambda_28_loss: 0.5106\n", "Epoch 627/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.9596 - distribution_lambda_26_loss: 0.9217 - distribution_lambda_27_loss: 1.5443 - distribution_lambda_28_loss: 0.4937 - val_loss: 3.0415 - val_distribution_lambda_26_loss: 0.9766 - val_distribution_lambda_27_loss: 1.5548 - val_distribution_lambda_28_loss: 0.5101\n", "Epoch 628/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9570 - distribution_lambda_26_loss: 0.9213 - distribution_lambda_27_loss: 1.5374 - distribution_lambda_28_loss: 0.4983 - val_loss: 3.0377 - val_distribution_lambda_26_loss: 0.9737 - val_distribution_lambda_27_loss: 1.5542 - val_distribution_lambda_28_loss: 0.5099\n", "Epoch 629/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9569 - distribution_lambda_26_loss: 0.9195 - distribution_lambda_27_loss: 1.5414 - distribution_lambda_28_loss: 0.4961 - val_loss: 3.0344 - val_distribution_lambda_26_loss: 0.9708 - val_distribution_lambda_27_loss: 1.5543 - val_distribution_lambda_28_loss: 0.5093\n", "Epoch 630/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9440 - distribution_lambda_26_loss: 0.9115 - distribution_lambda_27_loss: 1.5344 - distribution_lambda_28_loss: 0.4980 - val_loss: 3.0309 - val_distribution_lambda_26_loss: 0.9679 - val_distribution_lambda_27_loss: 1.5540 - val_distribution_lambda_28_loss: 0.5091\n", "Epoch 631/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9435 - distribution_lambda_26_loss: 0.9062 - distribution_lambda_27_loss: 1.5354 - distribution_lambda_28_loss: 0.5019 - val_loss: 3.0276 - val_distribution_lambda_26_loss: 0.9649 - val_distribution_lambda_27_loss: 1.5540 - val_distribution_lambda_28_loss: 0.5087\n", "Epoch 632/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9662 - distribution_lambda_26_loss: 0.9184 - distribution_lambda_27_loss: 1.5473 - distribution_lambda_28_loss: 0.5005 - val_loss: 3.0239 - val_distribution_lambda_26_loss: 0.9616 - val_distribution_lambda_27_loss: 1.5534 - val_distribution_lambda_28_loss: 0.5089\n", "Epoch 633/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9580 - distribution_lambda_26_loss: 0.9016 - distribution_lambda_27_loss: 1.5557 - distribution_lambda_28_loss: 0.5007 - val_loss: 3.0205 - val_distribution_lambda_26_loss: 0.9588 - val_distribution_lambda_27_loss: 1.5527 - val_distribution_lambda_28_loss: 0.5089\n", "Epoch 634/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9311 - distribution_lambda_26_loss: 0.8998 - distribution_lambda_27_loss: 1.5366 - distribution_lambda_28_loss: 0.4947 - val_loss: 3.0166 - val_distribution_lambda_26_loss: 0.9560 - val_distribution_lambda_27_loss: 1.5518 - val_distribution_lambda_28_loss: 0.5088\n", "Epoch 635/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9202 - distribution_lambda_26_loss: 0.8921 - distribution_lambda_27_loss: 1.5297 - distribution_lambda_28_loss: 0.4983 - val_loss: 3.0139 - val_distribution_lambda_26_loss: 0.9540 - val_distribution_lambda_27_loss: 1.5517 - val_distribution_lambda_28_loss: 0.5082\n", "Epoch 636/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9287 - distribution_lambda_26_loss: 0.8932 - distribution_lambda_27_loss: 1.5428 - distribution_lambda_28_loss: 0.4927 - val_loss: 3.0106 - val_distribution_lambda_26_loss: 0.9515 - val_distribution_lambda_27_loss: 1.5512 - val_distribution_lambda_28_loss: 0.5079\n", "Epoch 637/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9202 - distribution_lambda_26_loss: 0.8963 - distribution_lambda_27_loss: 1.5306 - distribution_lambda_28_loss: 0.4933 - val_loss: 3.0062 - val_distribution_lambda_26_loss: 0.9478 - val_distribution_lambda_27_loss: 1.5504 - val_distribution_lambda_28_loss: 0.5080\n", "Epoch 638/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8876 - distribution_lambda_26_loss: 0.8771 - distribution_lambda_27_loss: 1.5237 - distribution_lambda_28_loss: 0.4868 - val_loss: 3.0024 - val_distribution_lambda_26_loss: 0.9453 - val_distribution_lambda_27_loss: 1.5501 - val_distribution_lambda_28_loss: 0.5069\n", "Epoch 639/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9114 - distribution_lambda_26_loss: 0.8850 - distribution_lambda_27_loss: 1.5321 - distribution_lambda_28_loss: 0.4942 - val_loss: 2.9985 - val_distribution_lambda_26_loss: 0.9424 - val_distribution_lambda_27_loss: 1.5499 - val_distribution_lambda_28_loss: 0.5062\n", "Epoch 640/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9352 - distribution_lambda_26_loss: 0.8888 - distribution_lambda_27_loss: 1.5463 - distribution_lambda_28_loss: 0.5000 - val_loss: 2.9967 - val_distribution_lambda_26_loss: 0.9405 - val_distribution_lambda_27_loss: 1.5501 - val_distribution_lambda_28_loss: 0.5061\n", "Epoch 641/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.9066 - distribution_lambda_26_loss: 0.8761 - distribution_lambda_27_loss: 1.5365 - distribution_lambda_28_loss: 0.4939 - val_loss: 2.9935 - val_distribution_lambda_26_loss: 0.9373 - val_distribution_lambda_27_loss: 1.5498 - val_distribution_lambda_28_loss: 0.5063\n", "Epoch 642/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8947 - distribution_lambda_26_loss: 0.8823 - distribution_lambda_27_loss: 1.5289 - distribution_lambda_28_loss: 0.4835 - val_loss: 2.9900 - val_distribution_lambda_26_loss: 0.9346 - val_distribution_lambda_27_loss: 1.5492 - val_distribution_lambda_28_loss: 0.5062\n", "Epoch 643/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8938 - distribution_lambda_26_loss: 0.8741 - distribution_lambda_27_loss: 1.5223 - distribution_lambda_28_loss: 0.4974 - val_loss: 2.9869 - val_distribution_lambda_26_loss: 0.9321 - val_distribution_lambda_27_loss: 1.5492 - val_distribution_lambda_28_loss: 0.5057\n", "Epoch 644/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8906 - distribution_lambda_26_loss: 0.8726 - distribution_lambda_27_loss: 1.5283 - distribution_lambda_28_loss: 0.4897 - val_loss: 2.9826 - val_distribution_lambda_26_loss: 0.9286 - val_distribution_lambda_27_loss: 1.5482 - val_distribution_lambda_28_loss: 0.5058\n", "Epoch 645/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.8941 - distribution_lambda_26_loss: 0.8724 - distribution_lambda_27_loss: 1.5278 - distribution_lambda_28_loss: 0.4939 - val_loss: 2.9798 - val_distribution_lambda_26_loss: 0.9268 - val_distribution_lambda_27_loss: 1.5475 - val_distribution_lambda_28_loss: 0.5056\n", "Epoch 646/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8725 - distribution_lambda_26_loss: 0.8627 - distribution_lambda_27_loss: 1.5278 - distribution_lambda_28_loss: 0.4819 - val_loss: 2.9759 - val_distribution_lambda_26_loss: 0.9234 - val_distribution_lambda_27_loss: 1.5467 - val_distribution_lambda_28_loss: 0.5058\n", "Epoch 647/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.9032 - distribution_lambda_26_loss: 0.8691 - distribution_lambda_27_loss: 1.5290 - distribution_lambda_28_loss: 0.5051 - val_loss: 2.9742 - val_distribution_lambda_26_loss: 0.9215 - val_distribution_lambda_27_loss: 1.5473 - val_distribution_lambda_28_loss: 0.5054\n", "Epoch 648/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.8697 - distribution_lambda_26_loss: 0.8566 - distribution_lambda_27_loss: 1.5249 - distribution_lambda_28_loss: 0.4883 - val_loss: 2.9721 - val_distribution_lambda_26_loss: 0.9200 - val_distribution_lambda_27_loss: 1.5469 - val_distribution_lambda_28_loss: 0.5052\n", "Epoch 649/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.8739 - distribution_lambda_26_loss: 0.8636 - distribution_lambda_27_loss: 1.5217 - distribution_lambda_28_loss: 0.4886 - val_loss: 2.9690 - val_distribution_lambda_26_loss: 0.9176 - val_distribution_lambda_27_loss: 1.5459 - val_distribution_lambda_28_loss: 0.5055\n", "Epoch 650/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8704 - distribution_lambda_26_loss: 0.8573 - distribution_lambda_27_loss: 1.5201 - distribution_lambda_28_loss: 0.4929 - val_loss: 2.9661 - val_distribution_lambda_26_loss: 0.9155 - val_distribution_lambda_27_loss: 1.5458 - val_distribution_lambda_28_loss: 0.5048\n", "Epoch 651/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8793 - distribution_lambda_26_loss: 0.8478 - distribution_lambda_27_loss: 1.5385 - distribution_lambda_28_loss: 0.4930 - val_loss: 2.9618 - val_distribution_lambda_26_loss: 0.9124 - val_distribution_lambda_27_loss: 1.5448 - val_distribution_lambda_28_loss: 0.5046\n", "Epoch 652/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8744 - distribution_lambda_26_loss: 0.8542 - distribution_lambda_27_loss: 1.5229 - distribution_lambda_28_loss: 0.4972 - val_loss: 2.9592 - val_distribution_lambda_26_loss: 0.9109 - val_distribution_lambda_27_loss: 1.5440 - val_distribution_lambda_28_loss: 0.5043\n", "Epoch 653/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8660 - distribution_lambda_26_loss: 0.8421 - distribution_lambda_27_loss: 1.5303 - distribution_lambda_28_loss: 0.4937 - val_loss: 2.9565 - val_distribution_lambda_26_loss: 0.9090 - val_distribution_lambda_27_loss: 1.5438 - val_distribution_lambda_28_loss: 0.5036\n", "Epoch 654/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8502 - distribution_lambda_26_loss: 0.8496 - distribution_lambda_27_loss: 1.5180 - distribution_lambda_28_loss: 0.4826 - val_loss: 2.9519 - val_distribution_lambda_26_loss: 0.9058 - val_distribution_lambda_27_loss: 1.5433 - val_distribution_lambda_28_loss: 0.5028\n", "Epoch 655/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8724 - distribution_lambda_26_loss: 0.8477 - distribution_lambda_27_loss: 1.5311 - distribution_lambda_28_loss: 0.4935 - val_loss: 2.9480 - val_distribution_lambda_26_loss: 0.9027 - val_distribution_lambda_27_loss: 1.5425 - val_distribution_lambda_28_loss: 0.5029\n", "Epoch 656/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.8504 - distribution_lambda_26_loss: 0.8406 - distribution_lambda_27_loss: 1.5255 - distribution_lambda_28_loss: 0.4843 - val_loss: 2.9448 - val_distribution_lambda_26_loss: 0.8999 - val_distribution_lambda_27_loss: 1.5418 - val_distribution_lambda_28_loss: 0.5032\n", "Epoch 657/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.8628 - distribution_lambda_26_loss: 0.8347 - distribution_lambda_27_loss: 1.5331 - distribution_lambda_28_loss: 0.4950 - val_loss: 2.9438 - val_distribution_lambda_26_loss: 0.8988 - val_distribution_lambda_27_loss: 1.5416 - val_distribution_lambda_28_loss: 0.5034\n", "Epoch 658/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8397 - distribution_lambda_26_loss: 0.8365 - distribution_lambda_27_loss: 1.5137 - distribution_lambda_28_loss: 0.4895 - val_loss: 2.9421 - val_distribution_lambda_26_loss: 0.8969 - val_distribution_lambda_27_loss: 1.5416 - val_distribution_lambda_28_loss: 0.5037\n", "Epoch 659/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8575 - distribution_lambda_26_loss: 0.8409 - distribution_lambda_27_loss: 1.5271 - distribution_lambda_28_loss: 0.4895 - val_loss: 2.9387 - val_distribution_lambda_26_loss: 0.8939 - val_distribution_lambda_27_loss: 1.5413 - val_distribution_lambda_28_loss: 0.5035\n", "Epoch 660/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8472 - distribution_lambda_26_loss: 0.8415 - distribution_lambda_27_loss: 1.5220 - distribution_lambda_28_loss: 0.4838 - val_loss: 2.9360 - val_distribution_lambda_26_loss: 0.8921 - val_distribution_lambda_27_loss: 1.5411 - val_distribution_lambda_28_loss: 0.5028\n", "Epoch 661/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8429 - distribution_lambda_26_loss: 0.8344 - distribution_lambda_27_loss: 1.5276 - distribution_lambda_28_loss: 0.4809 - val_loss: 2.9320 - val_distribution_lambda_26_loss: 0.8890 - val_distribution_lambda_27_loss: 1.5405 - val_distribution_lambda_28_loss: 0.5025\n", "Epoch 662/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8307 - distribution_lambda_26_loss: 0.8278 - distribution_lambda_27_loss: 1.5151 - distribution_lambda_28_loss: 0.4877 - val_loss: 2.9283 - val_distribution_lambda_26_loss: 0.8858 - val_distribution_lambda_27_loss: 1.5395 - val_distribution_lambda_28_loss: 0.5029\n", "Epoch 663/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8414 - distribution_lambda_26_loss: 0.8311 - distribution_lambda_27_loss: 1.5206 - distribution_lambda_28_loss: 0.4898 - val_loss: 2.9261 - val_distribution_lambda_26_loss: 0.8840 - val_distribution_lambda_27_loss: 1.5390 - val_distribution_lambda_28_loss: 0.5031\n", "Epoch 664/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8277 - distribution_lambda_26_loss: 0.8237 - distribution_lambda_27_loss: 1.5220 - distribution_lambda_28_loss: 0.4820 - val_loss: 2.9239 - val_distribution_lambda_26_loss: 0.8826 - val_distribution_lambda_27_loss: 1.5388 - val_distribution_lambda_28_loss: 0.5024\n", "Epoch 665/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8243 - distribution_lambda_26_loss: 0.8263 - distribution_lambda_27_loss: 1.5154 - distribution_lambda_28_loss: 0.4827 - val_loss: 2.9209 - val_distribution_lambda_26_loss: 0.8802 - val_distribution_lambda_27_loss: 1.5389 - val_distribution_lambda_28_loss: 0.5019\n", "Epoch 666/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8301 - distribution_lambda_26_loss: 0.8256 - distribution_lambda_27_loss: 1.5192 - distribution_lambda_28_loss: 0.4854 - val_loss: 2.9179 - val_distribution_lambda_26_loss: 0.8783 - val_distribution_lambda_27_loss: 1.5383 - val_distribution_lambda_28_loss: 0.5013\n", "Epoch 667/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8377 - distribution_lambda_26_loss: 0.8217 - distribution_lambda_27_loss: 1.5260 - distribution_lambda_28_loss: 0.4900 - val_loss: 2.9136 - val_distribution_lambda_26_loss: 0.8749 - val_distribution_lambda_27_loss: 1.5378 - val_distribution_lambda_28_loss: 0.5008\n", "Epoch 668/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8330 - distribution_lambda_26_loss: 0.8222 - distribution_lambda_27_loss: 1.5300 - distribution_lambda_28_loss: 0.4808 - val_loss: 2.9106 - val_distribution_lambda_26_loss: 0.8726 - val_distribution_lambda_27_loss: 1.5372 - val_distribution_lambda_28_loss: 0.5008\n", "Epoch 669/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8305 - distribution_lambda_26_loss: 0.8158 - distribution_lambda_27_loss: 1.5258 - distribution_lambda_28_loss: 0.4889 - val_loss: 2.9086 - val_distribution_lambda_26_loss: 0.8711 - val_distribution_lambda_27_loss: 1.5369 - val_distribution_lambda_28_loss: 0.5005\n", "Epoch 670/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8246 - distribution_lambda_26_loss: 0.8182 - distribution_lambda_27_loss: 1.5122 - distribution_lambda_28_loss: 0.4942 - val_loss: 2.9058 - val_distribution_lambda_26_loss: 0.8683 - val_distribution_lambda_27_loss: 1.5370 - val_distribution_lambda_28_loss: 0.5005\n", "Epoch 671/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8243 - distribution_lambda_26_loss: 0.8172 - distribution_lambda_27_loss: 1.5230 - distribution_lambda_28_loss: 0.4841 - val_loss: 2.9019 - val_distribution_lambda_26_loss: 0.8640 - val_distribution_lambda_27_loss: 1.5370 - val_distribution_lambda_28_loss: 0.5008\n", "Epoch 672/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8113 - distribution_lambda_26_loss: 0.8025 - distribution_lambda_27_loss: 1.5182 - distribution_lambda_28_loss: 0.4906 - val_loss: 2.8991 - val_distribution_lambda_26_loss: 0.8621 - val_distribution_lambda_27_loss: 1.5361 - val_distribution_lambda_28_loss: 0.5009\n", "Epoch 673/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.8262 - distribution_lambda_26_loss: 0.8144 - distribution_lambda_27_loss: 1.5222 - distribution_lambda_28_loss: 0.4896 - val_loss: 2.8968 - val_distribution_lambda_26_loss: 0.8609 - val_distribution_lambda_27_loss: 1.5357 - val_distribution_lambda_28_loss: 0.5002\n", "Epoch 674/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7994 - distribution_lambda_26_loss: 0.7929 - distribution_lambda_27_loss: 1.5188 - distribution_lambda_28_loss: 0.4878 - val_loss: 2.8951 - val_distribution_lambda_26_loss: 0.8592 - val_distribution_lambda_27_loss: 1.5358 - val_distribution_lambda_28_loss: 0.5001\n", "Epoch 675/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8305 - distribution_lambda_26_loss: 0.8206 - distribution_lambda_27_loss: 1.5255 - distribution_lambda_28_loss: 0.4845 - val_loss: 2.8932 - val_distribution_lambda_26_loss: 0.8572 - val_distribution_lambda_27_loss: 1.5361 - val_distribution_lambda_28_loss: 0.4999\n", "Epoch 676/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7888 - distribution_lambda_26_loss: 0.8008 - distribution_lambda_27_loss: 1.5096 - distribution_lambda_28_loss: 0.4784 - val_loss: 2.8899 - val_distribution_lambda_26_loss: 0.8546 - val_distribution_lambda_27_loss: 1.5348 - val_distribution_lambda_28_loss: 0.5005\n", "Epoch 677/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7864 - distribution_lambda_26_loss: 0.7913 - distribution_lambda_27_loss: 1.5064 - distribution_lambda_28_loss: 0.4886 - val_loss: 2.8883 - val_distribution_lambda_26_loss: 0.8536 - val_distribution_lambda_27_loss: 1.5341 - val_distribution_lambda_28_loss: 0.5007\n", "Epoch 678/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.8152 - distribution_lambda_26_loss: 0.8038 - distribution_lambda_27_loss: 1.5253 - distribution_lambda_28_loss: 0.4861 - val_loss: 2.8864 - val_distribution_lambda_26_loss: 0.8519 - val_distribution_lambda_27_loss: 1.5345 - val_distribution_lambda_28_loss: 0.4999\n", "Epoch 679/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7932 - distribution_lambda_26_loss: 0.7927 - distribution_lambda_27_loss: 1.5103 - distribution_lambda_28_loss: 0.4902 - val_loss: 2.8826 - val_distribution_lambda_26_loss: 0.8486 - val_distribution_lambda_27_loss: 1.5346 - val_distribution_lambda_28_loss: 0.4994\n", "Epoch 680/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7905 - distribution_lambda_26_loss: 0.7831 - distribution_lambda_27_loss: 1.5149 - distribution_lambda_28_loss: 0.4925 - val_loss: 2.8809 - val_distribution_lambda_26_loss: 0.8469 - val_distribution_lambda_27_loss: 1.5344 - val_distribution_lambda_28_loss: 0.4996\n", "Epoch 681/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7726 - distribution_lambda_26_loss: 0.7912 - distribution_lambda_27_loss: 1.5028 - distribution_lambda_28_loss: 0.4786 - val_loss: 2.8753 - val_distribution_lambda_26_loss: 0.8414 - val_distribution_lambda_27_loss: 1.5339 - val_distribution_lambda_28_loss: 0.5000\n", "Epoch 682/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7718 - distribution_lambda_26_loss: 0.7842 - distribution_lambda_27_loss: 1.5118 - distribution_lambda_28_loss: 0.4758 - val_loss: 2.8681 - val_distribution_lambda_26_loss: 0.8352 - val_distribution_lambda_27_loss: 1.5333 - val_distribution_lambda_28_loss: 0.4995\n", "Epoch 683/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7734 - distribution_lambda_26_loss: 0.7756 - distribution_lambda_27_loss: 1.5114 - distribution_lambda_28_loss: 0.4864 - val_loss: 2.8615 - val_distribution_lambda_26_loss: 0.8296 - val_distribution_lambda_27_loss: 1.5332 - val_distribution_lambda_28_loss: 0.4987\n", "Epoch 684/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7645 - distribution_lambda_26_loss: 0.7787 - distribution_lambda_27_loss: 1.5043 - distribution_lambda_28_loss: 0.4815 - val_loss: 2.8597 - val_distribution_lambda_26_loss: 0.8278 - val_distribution_lambda_27_loss: 1.5332 - val_distribution_lambda_28_loss: 0.4987\n", "Epoch 685/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7587 - distribution_lambda_26_loss: 0.7837 - distribution_lambda_27_loss: 1.4983 - distribution_lambda_28_loss: 0.4767 - val_loss: 2.8574 - val_distribution_lambda_26_loss: 0.8262 - val_distribution_lambda_27_loss: 1.5328 - val_distribution_lambda_28_loss: 0.4985\n", "Epoch 686/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7680 - distribution_lambda_26_loss: 0.7784 - distribution_lambda_27_loss: 1.5091 - distribution_lambda_28_loss: 0.4806 - val_loss: 2.8553 - val_distribution_lambda_26_loss: 0.8252 - val_distribution_lambda_27_loss: 1.5320 - val_distribution_lambda_28_loss: 0.4981\n", "Epoch 687/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7611 - distribution_lambda_26_loss: 0.7731 - distribution_lambda_27_loss: 1.5071 - distribution_lambda_28_loss: 0.4809 - val_loss: 2.8493 - val_distribution_lambda_26_loss: 0.8209 - val_distribution_lambda_27_loss: 1.5303 - val_distribution_lambda_28_loss: 0.4982\n", "Epoch 688/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7661 - distribution_lambda_26_loss: 0.7752 - distribution_lambda_27_loss: 1.5071 - distribution_lambda_28_loss: 0.4837 - val_loss: 2.8475 - val_distribution_lambda_26_loss: 0.8199 - val_distribution_lambda_27_loss: 1.5301 - val_distribution_lambda_28_loss: 0.4975\n", "Epoch 689/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7455 - distribution_lambda_26_loss: 0.7723 - distribution_lambda_27_loss: 1.4937 - distribution_lambda_28_loss: 0.4795 - val_loss: 2.8462 - val_distribution_lambda_26_loss: 0.8192 - val_distribution_lambda_27_loss: 1.5299 - val_distribution_lambda_28_loss: 0.4971\n", "Epoch 690/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7388 - distribution_lambda_26_loss: 0.7547 - distribution_lambda_27_loss: 1.5036 - distribution_lambda_28_loss: 0.4805 - val_loss: 2.8427 - val_distribution_lambda_26_loss: 0.8157 - val_distribution_lambda_27_loss: 1.5302 - val_distribution_lambda_28_loss: 0.4968\n", "Epoch 691/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7572 - distribution_lambda_26_loss: 0.7553 - distribution_lambda_27_loss: 1.5154 - distribution_lambda_28_loss: 0.4865 - val_loss: 2.8415 - val_distribution_lambda_26_loss: 0.8142 - val_distribution_lambda_27_loss: 1.5299 - val_distribution_lambda_28_loss: 0.4974\n", "Epoch 692/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7743 - distribution_lambda_26_loss: 0.7819 - distribution_lambda_27_loss: 1.5157 - distribution_lambda_28_loss: 0.4767 - val_loss: 2.8409 - val_distribution_lambda_26_loss: 0.8138 - val_distribution_lambda_27_loss: 1.5294 - val_distribution_lambda_28_loss: 0.4977\n", "Epoch 693/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7274 - distribution_lambda_26_loss: 0.7504 - distribution_lambda_27_loss: 1.5069 - distribution_lambda_28_loss: 0.4701 - val_loss: 2.8374 - val_distribution_lambda_26_loss: 0.8115 - val_distribution_lambda_27_loss: 1.5286 - val_distribution_lambda_28_loss: 0.4973\n", "Epoch 694/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7377 - distribution_lambda_26_loss: 0.7568 - distribution_lambda_27_loss: 1.5033 - distribution_lambda_28_loss: 0.4776 - val_loss: 2.8347 - val_distribution_lambda_26_loss: 0.8094 - val_distribution_lambda_27_loss: 1.5280 - val_distribution_lambda_28_loss: 0.4973\n", "Epoch 695/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7461 - distribution_lambda_26_loss: 0.7540 - distribution_lambda_27_loss: 1.5065 - distribution_lambda_28_loss: 0.4856 - val_loss: 2.8313 - val_distribution_lambda_26_loss: 0.8061 - val_distribution_lambda_27_loss: 1.5286 - val_distribution_lambda_28_loss: 0.4967\n", "Epoch 696/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.7388 - distribution_lambda_26_loss: 0.7565 - distribution_lambda_27_loss: 1.5014 - distribution_lambda_28_loss: 0.4808 - val_loss: 2.8290 - val_distribution_lambda_26_loss: 0.8042 - val_distribution_lambda_27_loss: 1.5286 - val_distribution_lambda_28_loss: 0.4962\n", "Epoch 697/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.7273 - distribution_lambda_26_loss: 0.7661 - distribution_lambda_27_loss: 1.4873 - distribution_lambda_28_loss: 0.4740 - val_loss: 2.8266 - val_distribution_lambda_26_loss: 0.8027 - val_distribution_lambda_27_loss: 1.5280 - val_distribution_lambda_28_loss: 0.4958\n", "Epoch 698/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7556 - distribution_lambda_26_loss: 0.7633 - distribution_lambda_27_loss: 1.5059 - distribution_lambda_28_loss: 0.4863 - val_loss: 2.8234 - val_distribution_lambda_26_loss: 0.7999 - val_distribution_lambda_27_loss: 1.5282 - val_distribution_lambda_28_loss: 0.4954\n", "Epoch 699/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7108 - distribution_lambda_26_loss: 0.7523 - distribution_lambda_27_loss: 1.4889 - distribution_lambda_28_loss: 0.4696 - val_loss: 2.8180 - val_distribution_lambda_26_loss: 0.7955 - val_distribution_lambda_27_loss: 1.5271 - val_distribution_lambda_28_loss: 0.4954\n", "Epoch 700/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.7234 - distribution_lambda_26_loss: 0.7459 - distribution_lambda_27_loss: 1.4995 - distribution_lambda_28_loss: 0.4779 - val_loss: 2.8172 - val_distribution_lambda_26_loss: 0.7946 - val_distribution_lambda_27_loss: 1.5271 - val_distribution_lambda_28_loss: 0.4954\n", "Epoch 701/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7073 - distribution_lambda_26_loss: 0.7364 - distribution_lambda_27_loss: 1.4941 - distribution_lambda_28_loss: 0.4768 - val_loss: 2.8175 - val_distribution_lambda_26_loss: 0.7945 - val_distribution_lambda_27_loss: 1.5278 - val_distribution_lambda_28_loss: 0.4953\n", "Epoch 702/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7214 - distribution_lambda_26_loss: 0.7384 - distribution_lambda_27_loss: 1.4970 - distribution_lambda_28_loss: 0.4860 - val_loss: 2.8177 - val_distribution_lambda_26_loss: 0.7951 - val_distribution_lambda_27_loss: 1.5270 - val_distribution_lambda_28_loss: 0.4955\n", "Epoch 703/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.7025 - distribution_lambda_26_loss: 0.7302 - distribution_lambda_27_loss: 1.4975 - distribution_lambda_28_loss: 0.4748 - val_loss: 2.8157 - val_distribution_lambda_26_loss: 0.7935 - val_distribution_lambda_27_loss: 1.5267 - val_distribution_lambda_28_loss: 0.4955\n", "Epoch 704/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7241 - distribution_lambda_26_loss: 0.7431 - distribution_lambda_27_loss: 1.4983 - distribution_lambda_28_loss: 0.4827 - val_loss: 2.8105 - val_distribution_lambda_26_loss: 0.7885 - val_distribution_lambda_27_loss: 1.5263 - val_distribution_lambda_28_loss: 0.4956\n", "Epoch 705/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7010 - distribution_lambda_26_loss: 0.7342 - distribution_lambda_27_loss: 1.4899 - distribution_lambda_28_loss: 0.4769 - val_loss: 2.8098 - val_distribution_lambda_26_loss: 0.7874 - val_distribution_lambda_27_loss: 1.5267 - val_distribution_lambda_28_loss: 0.4957\n", "Epoch 706/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6910 - distribution_lambda_26_loss: 0.7286 - distribution_lambda_27_loss: 1.4900 - distribution_lambda_28_loss: 0.4723 - val_loss: 2.8107 - val_distribution_lambda_26_loss: 0.7890 - val_distribution_lambda_27_loss: 1.5262 - val_distribution_lambda_28_loss: 0.4956\n", "Epoch 707/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6970 - distribution_lambda_26_loss: 0.7386 - distribution_lambda_27_loss: 1.4889 - distribution_lambda_28_loss: 0.4695 - val_loss: 2.8070 - val_distribution_lambda_26_loss: 0.7861 - val_distribution_lambda_27_loss: 1.5263 - val_distribution_lambda_28_loss: 0.4945\n", "Epoch 708/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.6801 - distribution_lambda_26_loss: 0.7191 - distribution_lambda_27_loss: 1.4888 - distribution_lambda_28_loss: 0.4722 - val_loss: 2.8063 - val_distribution_lambda_26_loss: 0.7857 - val_distribution_lambda_27_loss: 1.5267 - val_distribution_lambda_28_loss: 0.4938\n", "Epoch 709/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.7084 - distribution_lambda_26_loss: 0.7420 - distribution_lambda_27_loss: 1.4900 - distribution_lambda_28_loss: 0.4763 - val_loss: 2.8012 - val_distribution_lambda_26_loss: 0.7810 - val_distribution_lambda_27_loss: 1.5267 - val_distribution_lambda_28_loss: 0.4936\n", "Epoch 710/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7106 - distribution_lambda_26_loss: 0.7374 - distribution_lambda_27_loss: 1.4951 - distribution_lambda_28_loss: 0.4781 - val_loss: 2.7969 - val_distribution_lambda_26_loss: 0.7771 - val_distribution_lambda_27_loss: 1.5262 - val_distribution_lambda_28_loss: 0.4935\n", "Epoch 711/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6914 - distribution_lambda_26_loss: 0.7300 - distribution_lambda_27_loss: 1.4891 - distribution_lambda_28_loss: 0.4723 - val_loss: 2.7940 - val_distribution_lambda_26_loss: 0.7747 - val_distribution_lambda_27_loss: 1.5257 - val_distribution_lambda_28_loss: 0.4936\n", "Epoch 712/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.7162 - distribution_lambda_26_loss: 0.7405 - distribution_lambda_27_loss: 1.5018 - distribution_lambda_28_loss: 0.4739 - val_loss: 2.7927 - val_distribution_lambda_26_loss: 0.7732 - val_distribution_lambda_27_loss: 1.5263 - val_distribution_lambda_28_loss: 0.4932\n", "Epoch 713/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.7005 - distribution_lambda_26_loss: 0.7266 - distribution_lambda_27_loss: 1.5015 - distribution_lambda_28_loss: 0.4725 - val_loss: 2.7943 - val_distribution_lambda_26_loss: 0.7748 - val_distribution_lambda_27_loss: 1.5264 - val_distribution_lambda_28_loss: 0.4931\n", "Epoch 714/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6819 - distribution_lambda_26_loss: 0.7069 - distribution_lambda_27_loss: 1.5039 - distribution_lambda_28_loss: 0.4711 - val_loss: 2.7930 - val_distribution_lambda_26_loss: 0.7742 - val_distribution_lambda_27_loss: 1.5258 - val_distribution_lambda_28_loss: 0.4930\n", "Epoch 715/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6778 - distribution_lambda_26_loss: 0.7151 - distribution_lambda_27_loss: 1.4887 - distribution_lambda_28_loss: 0.4740 - val_loss: 2.7921 - val_distribution_lambda_26_loss: 0.7744 - val_distribution_lambda_27_loss: 1.5248 - val_distribution_lambda_28_loss: 0.4929\n", "Epoch 716/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6849 - distribution_lambda_26_loss: 0.7166 - distribution_lambda_27_loss: 1.4913 - distribution_lambda_28_loss: 0.4770 - val_loss: 2.7898 - val_distribution_lambda_26_loss: 0.7727 - val_distribution_lambda_27_loss: 1.5249 - val_distribution_lambda_28_loss: 0.4922\n", "Epoch 717/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.7142 - distribution_lambda_26_loss: 0.7380 - distribution_lambda_27_loss: 1.5043 - distribution_lambda_28_loss: 0.4719 - val_loss: 2.7860 - val_distribution_lambda_26_loss: 0.7688 - val_distribution_lambda_27_loss: 1.5249 - val_distribution_lambda_28_loss: 0.4922\n", "Epoch 718/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6958 - distribution_lambda_26_loss: 0.7354 - distribution_lambda_27_loss: 1.4865 - distribution_lambda_28_loss: 0.4739 - val_loss: 2.7817 - val_distribution_lambda_26_loss: 0.7649 - val_distribution_lambda_27_loss: 1.5249 - val_distribution_lambda_28_loss: 0.4919\n", "Epoch 719/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6802 - distribution_lambda_26_loss: 0.7285 - distribution_lambda_27_loss: 1.4822 - distribution_lambda_28_loss: 0.4695 - val_loss: 2.7783 - val_distribution_lambda_26_loss: 0.7625 - val_distribution_lambda_27_loss: 1.5245 - val_distribution_lambda_28_loss: 0.4912\n", "Epoch 720/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6696 - distribution_lambda_26_loss: 0.7024 - distribution_lambda_27_loss: 1.4935 - distribution_lambda_28_loss: 0.4738 - val_loss: 2.7770 - val_distribution_lambda_26_loss: 0.7623 - val_distribution_lambda_27_loss: 1.5239 - val_distribution_lambda_28_loss: 0.4907\n", "Epoch 721/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.6852 - distribution_lambda_26_loss: 0.7190 - distribution_lambda_27_loss: 1.4920 - distribution_lambda_28_loss: 0.4742 - val_loss: 2.7751 - val_distribution_lambda_26_loss: 0.7610 - val_distribution_lambda_27_loss: 1.5236 - val_distribution_lambda_28_loss: 0.4905\n", "Epoch 722/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6802 - distribution_lambda_26_loss: 0.7133 - distribution_lambda_27_loss: 1.4960 - distribution_lambda_28_loss: 0.4708 - val_loss: 2.7748 - val_distribution_lambda_26_loss: 0.7611 - val_distribution_lambda_27_loss: 1.5236 - val_distribution_lambda_28_loss: 0.4901\n", "Epoch 723/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6632 - distribution_lambda_26_loss: 0.7058 - distribution_lambda_27_loss: 1.4865 - distribution_lambda_28_loss: 0.4709 - val_loss: 2.7738 - val_distribution_lambda_26_loss: 0.7604 - val_distribution_lambda_27_loss: 1.5234 - val_distribution_lambda_28_loss: 0.4900\n", "Epoch 724/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6454 - distribution_lambda_26_loss: 0.7010 - distribution_lambda_27_loss: 1.4811 - distribution_lambda_28_loss: 0.4633 - val_loss: 2.7699 - val_distribution_lambda_26_loss: 0.7585 - val_distribution_lambda_27_loss: 1.5226 - val_distribution_lambda_28_loss: 0.4888\n", "Epoch 725/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.7022 - distribution_lambda_26_loss: 0.7185 - distribution_lambda_27_loss: 1.5038 - distribution_lambda_28_loss: 0.4799 - val_loss: 2.7673 - val_distribution_lambda_26_loss: 0.7564 - val_distribution_lambda_27_loss: 1.5224 - val_distribution_lambda_28_loss: 0.4884\n", "Epoch 726/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.6619 - distribution_lambda_26_loss: 0.7162 - distribution_lambda_27_loss: 1.4752 - distribution_lambda_28_loss: 0.4706 - val_loss: 2.7650 - val_distribution_lambda_26_loss: 0.7554 - val_distribution_lambda_27_loss: 1.5216 - val_distribution_lambda_28_loss: 0.4880\n", "Epoch 727/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.6781 - distribution_lambda_26_loss: 0.7096 - distribution_lambda_27_loss: 1.4970 - distribution_lambda_28_loss: 0.4715 - val_loss: 2.7634 - val_distribution_lambda_26_loss: 0.7543 - val_distribution_lambda_27_loss: 1.5212 - val_distribution_lambda_28_loss: 0.4879\n", "Epoch 728/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.6797 - distribution_lambda_26_loss: 0.7064 - distribution_lambda_27_loss: 1.4969 - distribution_lambda_28_loss: 0.4764 - val_loss: 2.7626 - val_distribution_lambda_26_loss: 0.7530 - val_distribution_lambda_27_loss: 1.5214 - val_distribution_lambda_28_loss: 0.4882\n", "Epoch 729/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.6631 - distribution_lambda_26_loss: 0.7040 - distribution_lambda_27_loss: 1.4885 - distribution_lambda_28_loss: 0.4707 - val_loss: 2.7621 - val_distribution_lambda_26_loss: 0.7529 - val_distribution_lambda_27_loss: 1.5213 - val_distribution_lambda_28_loss: 0.4879\n", "Epoch 730/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.6754 - distribution_lambda_26_loss: 0.7122 - distribution_lambda_27_loss: 1.4960 - distribution_lambda_28_loss: 0.4671 - val_loss: 2.7601 - val_distribution_lambda_26_loss: 0.7520 - val_distribution_lambda_27_loss: 1.5208 - val_distribution_lambda_28_loss: 0.4874\n", "Epoch 731/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.6367 - distribution_lambda_26_loss: 0.6928 - distribution_lambda_27_loss: 1.4749 - distribution_lambda_28_loss: 0.4691 - val_loss: 2.7576 - val_distribution_lambda_26_loss: 0.7493 - val_distribution_lambda_27_loss: 1.5210 - val_distribution_lambda_28_loss: 0.4872\n", "Epoch 732/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.6613 - distribution_lambda_26_loss: 0.7176 - distribution_lambda_27_loss: 1.4769 - distribution_lambda_28_loss: 0.4668 - val_loss: 2.7530 - val_distribution_lambda_26_loss: 0.7452 - val_distribution_lambda_27_loss: 1.5209 - val_distribution_lambda_28_loss: 0.4868\n", "Epoch 733/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.6636 - distribution_lambda_26_loss: 0.7155 - distribution_lambda_27_loss: 1.4787 - distribution_lambda_28_loss: 0.4693 - val_loss: 2.7489 - val_distribution_lambda_26_loss: 0.7415 - val_distribution_lambda_27_loss: 1.5207 - val_distribution_lambda_28_loss: 0.4866\n", "Epoch 734/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.6476 - distribution_lambda_26_loss: 0.7042 - distribution_lambda_27_loss: 1.4758 - distribution_lambda_28_loss: 0.4677 - val_loss: 2.7461 - val_distribution_lambda_26_loss: 0.7397 - val_distribution_lambda_27_loss: 1.5207 - val_distribution_lambda_28_loss: 0.4857\n", "Epoch 735/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6763 - distribution_lambda_26_loss: 0.6923 - distribution_lambda_27_loss: 1.5018 - distribution_lambda_28_loss: 0.4823 - val_loss: 2.7462 - val_distribution_lambda_26_loss: 0.7393 - val_distribution_lambda_27_loss: 1.5213 - val_distribution_lambda_28_loss: 0.4856\n", "Epoch 736/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6836 - distribution_lambda_26_loss: 0.7144 - distribution_lambda_27_loss: 1.4920 - distribution_lambda_28_loss: 0.4773 - val_loss: 2.7466 - val_distribution_lambda_26_loss: 0.7387 - val_distribution_lambda_27_loss: 1.5222 - val_distribution_lambda_28_loss: 0.4857\n", "Epoch 737/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6407 - distribution_lambda_26_loss: 0.6948 - distribution_lambda_27_loss: 1.4756 - distribution_lambda_28_loss: 0.4703 - val_loss: 2.7443 - val_distribution_lambda_26_loss: 0.7372 - val_distribution_lambda_27_loss: 1.5215 - val_distribution_lambda_28_loss: 0.4856\n", "Epoch 738/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6412 - distribution_lambda_26_loss: 0.6879 - distribution_lambda_27_loss: 1.4892 - distribution_lambda_28_loss: 0.4641 - val_loss: 2.7423 - val_distribution_lambda_26_loss: 0.7363 - val_distribution_lambda_27_loss: 1.5204 - val_distribution_lambda_28_loss: 0.4856\n", "Epoch 739/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6545 - distribution_lambda_26_loss: 0.6918 - distribution_lambda_27_loss: 1.4901 - distribution_lambda_28_loss: 0.4727 - val_loss: 2.7383 - val_distribution_lambda_26_loss: 0.7329 - val_distribution_lambda_27_loss: 1.5201 - val_distribution_lambda_28_loss: 0.4852\n", "Epoch 740/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6640 - distribution_lambda_26_loss: 0.6920 - distribution_lambda_27_loss: 1.4972 - distribution_lambda_28_loss: 0.4747 - val_loss: 2.7369 - val_distribution_lambda_26_loss: 0.7319 - val_distribution_lambda_27_loss: 1.5202 - val_distribution_lambda_28_loss: 0.4849\n", "Epoch 741/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6418 - distribution_lambda_26_loss: 0.6953 - distribution_lambda_27_loss: 1.4834 - distribution_lambda_28_loss: 0.4632 - val_loss: 2.7358 - val_distribution_lambda_26_loss: 0.7311 - val_distribution_lambda_27_loss: 1.5200 - val_distribution_lambda_28_loss: 0.4847\n", "Epoch 742/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6661 - distribution_lambda_26_loss: 0.6886 - distribution_lambda_27_loss: 1.4988 - distribution_lambda_28_loss: 0.4787 - val_loss: 2.7373 - val_distribution_lambda_26_loss: 0.7328 - val_distribution_lambda_27_loss: 1.5198 - val_distribution_lambda_28_loss: 0.4847\n", "Epoch 743/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6449 - distribution_lambda_26_loss: 0.6847 - distribution_lambda_27_loss: 1.4921 - distribution_lambda_28_loss: 0.4681 - val_loss: 2.7372 - val_distribution_lambda_26_loss: 0.7320 - val_distribution_lambda_27_loss: 1.5196 - val_distribution_lambda_28_loss: 0.4856\n", "Epoch 744/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6315 - distribution_lambda_26_loss: 0.6849 - distribution_lambda_27_loss: 1.4812 - distribution_lambda_28_loss: 0.4653 - val_loss: 2.7365 - val_distribution_lambda_26_loss: 0.7307 - val_distribution_lambda_27_loss: 1.5204 - val_distribution_lambda_28_loss: 0.4855\n", "Epoch 745/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.6397 - distribution_lambda_26_loss: 0.6996 - distribution_lambda_27_loss: 1.4775 - distribution_lambda_28_loss: 0.4627 - val_loss: 2.7313 - val_distribution_lambda_26_loss: 0.7265 - val_distribution_lambda_27_loss: 1.5198 - val_distribution_lambda_28_loss: 0.4850\n", "Epoch 746/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6239 - distribution_lambda_26_loss: 0.6704 - distribution_lambda_27_loss: 1.4812 - distribution_lambda_28_loss: 0.4723 - val_loss: 2.7298 - val_distribution_lambda_26_loss: 0.7250 - val_distribution_lambda_27_loss: 1.5194 - val_distribution_lambda_28_loss: 0.4854\n", "Epoch 747/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6120 - distribution_lambda_26_loss: 0.6634 - distribution_lambda_27_loss: 1.4792 - distribution_lambda_28_loss: 0.4694 - val_loss: 2.7294 - val_distribution_lambda_26_loss: 0.7255 - val_distribution_lambda_27_loss: 1.5187 - val_distribution_lambda_28_loss: 0.4852\n", "Epoch 748/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6103 - distribution_lambda_26_loss: 0.6665 - distribution_lambda_27_loss: 1.4850 - distribution_lambda_28_loss: 0.4589 - val_loss: 2.7258 - val_distribution_lambda_26_loss: 0.7231 - val_distribution_lambda_27_loss: 1.5182 - val_distribution_lambda_28_loss: 0.4845\n", "Epoch 749/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6305 - distribution_lambda_26_loss: 0.6869 - distribution_lambda_27_loss: 1.4774 - distribution_lambda_28_loss: 0.4662 - val_loss: 2.7235 - val_distribution_lambda_26_loss: 0.7214 - val_distribution_lambda_27_loss: 1.5182 - val_distribution_lambda_28_loss: 0.4839\n", "Epoch 750/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6271 - distribution_lambda_26_loss: 0.6785 - distribution_lambda_27_loss: 1.4834 - distribution_lambda_28_loss: 0.4652 - val_loss: 2.7234 - val_distribution_lambda_26_loss: 0.7213 - val_distribution_lambda_27_loss: 1.5185 - val_distribution_lambda_28_loss: 0.4836\n", "Epoch 751/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6150 - distribution_lambda_26_loss: 0.6751 - distribution_lambda_27_loss: 1.4770 - distribution_lambda_28_loss: 0.4629 - val_loss: 2.7228 - val_distribution_lambda_26_loss: 0.7202 - val_distribution_lambda_27_loss: 1.5191 - val_distribution_lambda_28_loss: 0.4835\n", "Epoch 752/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6101 - distribution_lambda_26_loss: 0.6757 - distribution_lambda_27_loss: 1.4748 - distribution_lambda_28_loss: 0.4596 - val_loss: 2.7187 - val_distribution_lambda_26_loss: 0.7174 - val_distribution_lambda_27_loss: 1.5178 - val_distribution_lambda_28_loss: 0.4835\n", "Epoch 753/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6273 - distribution_lambda_26_loss: 0.6717 - distribution_lambda_27_loss: 1.4905 - distribution_lambda_28_loss: 0.4650 - val_loss: 2.7181 - val_distribution_lambda_26_loss: 0.7182 - val_distribution_lambda_27_loss: 1.5167 - val_distribution_lambda_28_loss: 0.4832\n", "Epoch 754/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6063 - distribution_lambda_26_loss: 0.6618 - distribution_lambda_27_loss: 1.4812 - distribution_lambda_28_loss: 0.4634 - val_loss: 2.7143 - val_distribution_lambda_26_loss: 0.7150 - val_distribution_lambda_27_loss: 1.5163 - val_distribution_lambda_28_loss: 0.4830\n", "Epoch 755/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6106 - distribution_lambda_26_loss: 0.6677 - distribution_lambda_27_loss: 1.4811 - distribution_lambda_28_loss: 0.4618 - val_loss: 2.7131 - val_distribution_lambda_26_loss: 0.7135 - val_distribution_lambda_27_loss: 1.5167 - val_distribution_lambda_28_loss: 0.4829\n", "Epoch 756/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.5943 - distribution_lambda_26_loss: 0.6575 - distribution_lambda_27_loss: 1.4737 - distribution_lambda_28_loss: 0.4631 - val_loss: 2.7111 - val_distribution_lambda_26_loss: 0.7118 - val_distribution_lambda_27_loss: 1.5170 - val_distribution_lambda_28_loss: 0.4823\n", "Epoch 757/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6160 - distribution_lambda_26_loss: 0.6621 - distribution_lambda_27_loss: 1.4857 - distribution_lambda_28_loss: 0.4682 - val_loss: 2.7114 - val_distribution_lambda_26_loss: 0.7126 - val_distribution_lambda_27_loss: 1.5167 - val_distribution_lambda_28_loss: 0.4822\n", "Epoch 758/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.6339 - distribution_lambda_26_loss: 0.6710 - distribution_lambda_27_loss: 1.4927 - distribution_lambda_28_loss: 0.4703 - val_loss: 2.7098 - val_distribution_lambda_26_loss: 0.7106 - val_distribution_lambda_27_loss: 1.5169 - val_distribution_lambda_28_loss: 0.4823\n", "Epoch 759/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5995 - distribution_lambda_26_loss: 0.6587 - distribution_lambda_27_loss: 1.4786 - distribution_lambda_28_loss: 0.4622 - val_loss: 2.7082 - val_distribution_lambda_26_loss: 0.7089 - val_distribution_lambda_27_loss: 1.5165 - val_distribution_lambda_28_loss: 0.4828\n", "Epoch 760/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6062 - distribution_lambda_26_loss: 0.6591 - distribution_lambda_27_loss: 1.4775 - distribution_lambda_28_loss: 0.4695 - val_loss: 2.7079 - val_distribution_lambda_26_loss: 0.7089 - val_distribution_lambda_27_loss: 1.5170 - val_distribution_lambda_28_loss: 0.4820\n", "Epoch 761/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5925 - distribution_lambda_26_loss: 0.6534 - distribution_lambda_27_loss: 1.4714 - distribution_lambda_28_loss: 0.4676 - val_loss: 2.7076 - val_distribution_lambda_26_loss: 0.7091 - val_distribution_lambda_27_loss: 1.5174 - val_distribution_lambda_28_loss: 0.4812\n", "Epoch 762/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.6056 - distribution_lambda_26_loss: 0.6579 - distribution_lambda_27_loss: 1.4817 - distribution_lambda_28_loss: 0.4660 - val_loss: 2.7063 - val_distribution_lambda_26_loss: 0.7077 - val_distribution_lambda_27_loss: 1.5170 - val_distribution_lambda_28_loss: 0.4816\n", "Epoch 763/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5775 - distribution_lambda_26_loss: 0.6431 - distribution_lambda_27_loss: 1.4713 - distribution_lambda_28_loss: 0.4631 - val_loss: 2.7023 - val_distribution_lambda_26_loss: 0.7052 - val_distribution_lambda_27_loss: 1.5155 - val_distribution_lambda_28_loss: 0.4816\n", "Epoch 764/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5836 - distribution_lambda_26_loss: 0.6555 - distribution_lambda_27_loss: 1.4633 - distribution_lambda_28_loss: 0.4648 - val_loss: 2.6993 - val_distribution_lambda_26_loss: 0.7028 - val_distribution_lambda_27_loss: 1.5155 - val_distribution_lambda_28_loss: 0.4810\n", "Epoch 765/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.5998 - distribution_lambda_26_loss: 0.6532 - distribution_lambda_27_loss: 1.4815 - distribution_lambda_28_loss: 0.4652 - val_loss: 2.6990 - val_distribution_lambda_26_loss: 0.7035 - val_distribution_lambda_27_loss: 1.5155 - val_distribution_lambda_28_loss: 0.4799\n", "Epoch 766/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.5662 - distribution_lambda_26_loss: 0.6505 - distribution_lambda_27_loss: 1.4632 - distribution_lambda_28_loss: 0.4526 - val_loss: 2.7001 - val_distribution_lambda_26_loss: 0.7043 - val_distribution_lambda_27_loss: 1.5158 - val_distribution_lambda_28_loss: 0.4800\n", "Epoch 767/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5794 - distribution_lambda_26_loss: 0.6445 - distribution_lambda_27_loss: 1.4747 - distribution_lambda_28_loss: 0.4602 - val_loss: 2.6993 - val_distribution_lambda_26_loss: 0.7034 - val_distribution_lambda_27_loss: 1.5159 - val_distribution_lambda_28_loss: 0.4800\n", "Epoch 768/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5672 - distribution_lambda_26_loss: 0.6411 - distribution_lambda_27_loss: 1.4690 - distribution_lambda_28_loss: 0.4572 - val_loss: 2.7010 - val_distribution_lambda_26_loss: 0.7048 - val_distribution_lambda_27_loss: 1.5165 - val_distribution_lambda_28_loss: 0.4797\n", "Epoch 769/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 7ms/step - loss: 2.5793 - distribution_lambda_26_loss: 0.6397 - distribution_lambda_27_loss: 1.4757 - distribution_lambda_28_loss: 0.4639 - val_loss: 2.6967 - val_distribution_lambda_26_loss: 0.7024 - val_distribution_lambda_27_loss: 1.5155 - val_distribution_lambda_28_loss: 0.4787\n", "Epoch 770/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5799 - distribution_lambda_26_loss: 0.6542 - distribution_lambda_27_loss: 1.4677 - distribution_lambda_28_loss: 0.4580 - val_loss: 2.6955 - val_distribution_lambda_26_loss: 0.7014 - val_distribution_lambda_27_loss: 1.5154 - val_distribution_lambda_28_loss: 0.4787\n", "Epoch 771/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.5684 - distribution_lambda_26_loss: 0.6328 - distribution_lambda_27_loss: 1.4726 - distribution_lambda_28_loss: 0.4630 - val_loss: 2.6930 - val_distribution_lambda_26_loss: 0.6994 - val_distribution_lambda_27_loss: 1.5152 - val_distribution_lambda_28_loss: 0.4785\n", "Epoch 772/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5933 - distribution_lambda_26_loss: 0.6495 - distribution_lambda_27_loss: 1.4790 - distribution_lambda_28_loss: 0.4649 - val_loss: 2.6912 - val_distribution_lambda_26_loss: 0.6975 - val_distribution_lambda_27_loss: 1.5154 - val_distribution_lambda_28_loss: 0.4783\n", "Epoch 773/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5863 - distribution_lambda_26_loss: 0.6485 - distribution_lambda_27_loss: 1.4773 - distribution_lambda_28_loss: 0.4604 - val_loss: 2.6909 - val_distribution_lambda_26_loss: 0.6979 - val_distribution_lambda_27_loss: 1.5155 - val_distribution_lambda_28_loss: 0.4776\n", "Epoch 774/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5719 - distribution_lambda_26_loss: 0.6368 - distribution_lambda_27_loss: 1.4767 - distribution_lambda_28_loss: 0.4584 - val_loss: 2.6927 - val_distribution_lambda_26_loss: 0.6990 - val_distribution_lambda_27_loss: 1.5158 - val_distribution_lambda_28_loss: 0.4778\n", "Epoch 775/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.5655 - distribution_lambda_26_loss: 0.6352 - distribution_lambda_27_loss: 1.4726 - distribution_lambda_28_loss: 0.4577 - val_loss: 2.6893 - val_distribution_lambda_26_loss: 0.6972 - val_distribution_lambda_27_loss: 1.5144 - val_distribution_lambda_28_loss: 0.4777\n", "Epoch 776/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5233 - distribution_lambda_26_loss: 0.6247 - distribution_lambda_27_loss: 1.4499 - distribution_lambda_28_loss: 0.4486 - val_loss: 2.6895 - val_distribution_lambda_26_loss: 0.6979 - val_distribution_lambda_27_loss: 1.5142 - val_distribution_lambda_28_loss: 0.4774\n", "Epoch 777/2500\n", "8/8 [==============================] - 0s 8ms/step - loss: 2.5580 - distribution_lambda_26_loss: 0.6375 - distribution_lambda_27_loss: 1.4672 - distribution_lambda_28_loss: 0.4532 - val_loss: 2.6865 - val_distribution_lambda_26_loss: 0.6956 - val_distribution_lambda_27_loss: 1.5143 - val_distribution_lambda_28_loss: 0.4767\n", "Epoch 778/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.5427 - distribution_lambda_26_loss: 0.6329 - distribution_lambda_27_loss: 1.4640 - distribution_lambda_28_loss: 0.4458 - val_loss: 2.6815 - val_distribution_lambda_26_loss: 0.6912 - val_distribution_lambda_27_loss: 1.5144 - val_distribution_lambda_28_loss: 0.4759\n", "Epoch 779/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.5735 - distribution_lambda_26_loss: 0.6481 - distribution_lambda_27_loss: 1.4684 - distribution_lambda_28_loss: 0.4570 - val_loss: 2.6782 - val_distribution_lambda_26_loss: 0.6888 - val_distribution_lambda_27_loss: 1.5141 - val_distribution_lambda_28_loss: 0.4753\n", "Epoch 780/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5287 - distribution_lambda_26_loss: 0.6214 - distribution_lambda_27_loss: 1.4537 - distribution_lambda_28_loss: 0.4536 - val_loss: 2.6785 - val_distribution_lambda_26_loss: 0.6889 - val_distribution_lambda_27_loss: 1.5139 - val_distribution_lambda_28_loss: 0.4757\n", "Epoch 781/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.5750 - distribution_lambda_26_loss: 0.6491 - distribution_lambda_27_loss: 1.4679 - distribution_lambda_28_loss: 0.4580 - val_loss: 2.6796 - val_distribution_lambda_26_loss: 0.6888 - val_distribution_lambda_27_loss: 1.5148 - val_distribution_lambda_28_loss: 0.4760\n", "Epoch 782/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.5380 - distribution_lambda_26_loss: 0.6256 - distribution_lambda_27_loss: 1.4599 - distribution_lambda_28_loss: 0.4524 - val_loss: 2.6823 - val_distribution_lambda_26_loss: 0.6910 - val_distribution_lambda_27_loss: 1.5153 - val_distribution_lambda_28_loss: 0.4759\n", "Epoch 783/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5499 - distribution_lambda_26_loss: 0.6282 - distribution_lambda_27_loss: 1.4662 - distribution_lambda_28_loss: 0.4555 - val_loss: 2.6799 - val_distribution_lambda_26_loss: 0.6885 - val_distribution_lambda_27_loss: 1.5157 - val_distribution_lambda_28_loss: 0.4758\n", "Epoch 784/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.5428 - distribution_lambda_26_loss: 0.6221 - distribution_lambda_27_loss: 1.4644 - distribution_lambda_28_loss: 0.4563 - val_loss: 2.6815 - val_distribution_lambda_26_loss: 0.6889 - val_distribution_lambda_27_loss: 1.5165 - val_distribution_lambda_28_loss: 0.4760\n", "Epoch 785/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.5342 - distribution_lambda_26_loss: 0.6298 - distribution_lambda_27_loss: 1.4596 - distribution_lambda_28_loss: 0.4448 - val_loss: 2.6823 - val_distribution_lambda_26_loss: 0.6901 - val_distribution_lambda_27_loss: 1.5167 - val_distribution_lambda_28_loss: 0.4755\n", "Epoch 786/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5553 - distribution_lambda_26_loss: 0.6151 - distribution_lambda_27_loss: 1.4792 - distribution_lambda_28_loss: 0.4611 - val_loss: 2.6811 - val_distribution_lambda_26_loss: 0.6896 - val_distribution_lambda_27_loss: 1.5162 - val_distribution_lambda_28_loss: 0.4753\n", "Epoch 787/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5580 - distribution_lambda_26_loss: 0.6363 - distribution_lambda_27_loss: 1.4667 - distribution_lambda_28_loss: 0.4550 - val_loss: 2.6800 - val_distribution_lambda_26_loss: 0.6885 - val_distribution_lambda_27_loss: 1.5165 - val_distribution_lambda_28_loss: 0.4750\n", "Epoch 788/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.5607 - distribution_lambda_26_loss: 0.6435 - distribution_lambda_27_loss: 1.4634 - distribution_lambda_28_loss: 0.4538 - val_loss: 2.6753 - val_distribution_lambda_26_loss: 0.6852 - val_distribution_lambda_27_loss: 1.5156 - val_distribution_lambda_28_loss: 0.4745\n", "Epoch 789/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.5495 - distribution_lambda_26_loss: 0.6206 - distribution_lambda_27_loss: 1.4707 - distribution_lambda_28_loss: 0.4583 - val_loss: 2.6764 - val_distribution_lambda_26_loss: 0.6864 - val_distribution_lambda_27_loss: 1.5152 - val_distribution_lambda_28_loss: 0.4748\n", "Epoch 790/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5651 - distribution_lambda_26_loss: 0.6289 - distribution_lambda_27_loss: 1.4743 - distribution_lambda_28_loss: 0.4619 - val_loss: 2.6763 - val_distribution_lambda_26_loss: 0.6863 - val_distribution_lambda_27_loss: 1.5149 - val_distribution_lambda_28_loss: 0.4751\n", "Epoch 791/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5263 - distribution_lambda_26_loss: 0.6294 - distribution_lambda_27_loss: 1.4499 - distribution_lambda_28_loss: 0.4469 - val_loss: 2.6755 - val_distribution_lambda_26_loss: 0.6859 - val_distribution_lambda_27_loss: 1.5142 - val_distribution_lambda_28_loss: 0.4754\n", "Epoch 792/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5288 - distribution_lambda_26_loss: 0.6270 - distribution_lambda_27_loss: 1.4517 - distribution_lambda_28_loss: 0.4501 - val_loss: 2.6757 - val_distribution_lambda_26_loss: 0.6864 - val_distribution_lambda_27_loss: 1.5150 - val_distribution_lambda_28_loss: 0.4744\n", "Epoch 793/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.5491 - distribution_lambda_26_loss: 0.6229 - distribution_lambda_27_loss: 1.4740 - distribution_lambda_28_loss: 0.4522 - val_loss: 2.6728 - val_distribution_lambda_26_loss: 0.6840 - val_distribution_lambda_27_loss: 1.5148 - val_distribution_lambda_28_loss: 0.4740\n", "Epoch 794/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.5448 - distribution_lambda_26_loss: 0.6205 - distribution_lambda_27_loss: 1.4692 - distribution_lambda_28_loss: 0.4551 - val_loss: 2.6692 - val_distribution_lambda_26_loss: 0.6809 - val_distribution_lambda_27_loss: 1.5143 - val_distribution_lambda_28_loss: 0.4739\n", "Epoch 795/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5156 - distribution_lambda_26_loss: 0.6125 - distribution_lambda_27_loss: 1.4556 - distribution_lambda_28_loss: 0.4476 - val_loss: 2.6674 - val_distribution_lambda_26_loss: 0.6814 - val_distribution_lambda_27_loss: 1.5133 - val_distribution_lambda_28_loss: 0.4726\n", "Epoch 796/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5490 - distribution_lambda_26_loss: 0.6236 - distribution_lambda_27_loss: 1.4699 - distribution_lambda_28_loss: 0.4555 - val_loss: 2.6685 - val_distribution_lambda_26_loss: 0.6832 - val_distribution_lambda_27_loss: 1.5131 - val_distribution_lambda_28_loss: 0.4722\n", "Epoch 797/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5455 - distribution_lambda_26_loss: 0.6210 - distribution_lambda_27_loss: 1.4661 - distribution_lambda_28_loss: 0.4585 - val_loss: 2.6692 - val_distribution_lambda_26_loss: 0.6837 - val_distribution_lambda_27_loss: 1.5133 - val_distribution_lambda_28_loss: 0.4722\n", "Epoch 798/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5374 - distribution_lambda_26_loss: 0.6170 - distribution_lambda_27_loss: 1.4653 - distribution_lambda_28_loss: 0.4550 - val_loss: 2.6688 - val_distribution_lambda_26_loss: 0.6829 - val_distribution_lambda_27_loss: 1.5140 - val_distribution_lambda_28_loss: 0.4719\n", "Epoch 799/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5198 - distribution_lambda_26_loss: 0.6165 - distribution_lambda_27_loss: 1.4530 - distribution_lambda_28_loss: 0.4503 - val_loss: 2.6655 - val_distribution_lambda_26_loss: 0.6808 - val_distribution_lambda_27_loss: 1.5123 - val_distribution_lambda_28_loss: 0.4724\n", "Epoch 800/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5179 - distribution_lambda_26_loss: 0.6121 - distribution_lambda_27_loss: 1.4548 - distribution_lambda_28_loss: 0.4510 - val_loss: 2.6636 - val_distribution_lambda_26_loss: 0.6791 - val_distribution_lambda_27_loss: 1.5120 - val_distribution_lambda_28_loss: 0.4725\n", "Epoch 801/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5543 - distribution_lambda_26_loss: 0.6215 - distribution_lambda_27_loss: 1.4705 - distribution_lambda_28_loss: 0.4623 - val_loss: 2.6621 - val_distribution_lambda_26_loss: 0.6788 - val_distribution_lambda_27_loss: 1.5119 - val_distribution_lambda_28_loss: 0.4714\n", "Epoch 802/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5405 - distribution_lambda_26_loss: 0.6240 - distribution_lambda_27_loss: 1.4641 - distribution_lambda_28_loss: 0.4524 - val_loss: 2.6575 - val_distribution_lambda_26_loss: 0.6748 - val_distribution_lambda_27_loss: 1.5122 - val_distribution_lambda_28_loss: 0.4705\n", "Epoch 803/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5171 - distribution_lambda_26_loss: 0.6146 - distribution_lambda_27_loss: 1.4589 - distribution_lambda_28_loss: 0.4436 - val_loss: 2.6556 - val_distribution_lambda_26_loss: 0.6730 - val_distribution_lambda_27_loss: 1.5119 - val_distribution_lambda_28_loss: 0.4707\n", "Epoch 804/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5211 - distribution_lambda_26_loss: 0.6134 - distribution_lambda_27_loss: 1.4596 - distribution_lambda_28_loss: 0.4481 - val_loss: 2.6560 - val_distribution_lambda_26_loss: 0.6722 - val_distribution_lambda_27_loss: 1.5123 - val_distribution_lambda_28_loss: 0.4714\n", "Epoch 805/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5259 - distribution_lambda_26_loss: 0.6153 - distribution_lambda_27_loss: 1.4614 - distribution_lambda_28_loss: 0.4492 - val_loss: 2.6568 - val_distribution_lambda_26_loss: 0.6730 - val_distribution_lambda_27_loss: 1.5125 - val_distribution_lambda_28_loss: 0.4714\n", "Epoch 806/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5282 - distribution_lambda_26_loss: 0.6194 - distribution_lambda_27_loss: 1.4620 - distribution_lambda_28_loss: 0.4467 - val_loss: 2.6566 - val_distribution_lambda_26_loss: 0.6731 - val_distribution_lambda_27_loss: 1.5128 - val_distribution_lambda_28_loss: 0.4707\n", "Epoch 807/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5248 - distribution_lambda_26_loss: 0.6321 - distribution_lambda_27_loss: 1.4505 - distribution_lambda_28_loss: 0.4422 - val_loss: 2.6558 - val_distribution_lambda_26_loss: 0.6722 - val_distribution_lambda_27_loss: 1.5130 - val_distribution_lambda_28_loss: 0.4706\n", "Epoch 808/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5061 - distribution_lambda_26_loss: 0.6022 - distribution_lambda_27_loss: 1.4614 - distribution_lambda_28_loss: 0.4425 - val_loss: 2.6547 - val_distribution_lambda_26_loss: 0.6717 - val_distribution_lambda_27_loss: 1.5123 - val_distribution_lambda_28_loss: 0.4707\n", "Epoch 809/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5277 - distribution_lambda_26_loss: 0.6195 - distribution_lambda_27_loss: 1.4602 - distribution_lambda_28_loss: 0.4480 - val_loss: 2.6532 - val_distribution_lambda_26_loss: 0.6715 - val_distribution_lambda_27_loss: 1.5111 - val_distribution_lambda_28_loss: 0.4706\n", "Epoch 810/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5401 - distribution_lambda_26_loss: 0.6365 - distribution_lambda_27_loss: 1.4577 - distribution_lambda_28_loss: 0.4459 - val_loss: 2.6497 - val_distribution_lambda_26_loss: 0.6679 - val_distribution_lambda_27_loss: 1.5114 - val_distribution_lambda_28_loss: 0.4704\n", "Epoch 811/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5051 - distribution_lambda_26_loss: 0.6101 - distribution_lambda_27_loss: 1.4510 - distribution_lambda_28_loss: 0.4440 - val_loss: 2.6494 - val_distribution_lambda_26_loss: 0.6687 - val_distribution_lambda_27_loss: 1.5097 - val_distribution_lambda_28_loss: 0.4709\n", "Epoch 812/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5127 - distribution_lambda_26_loss: 0.6221 - distribution_lambda_27_loss: 1.4453 - distribution_lambda_28_loss: 0.4453 - val_loss: 2.6491 - val_distribution_lambda_26_loss: 0.6693 - val_distribution_lambda_27_loss: 1.5090 - val_distribution_lambda_28_loss: 0.4708\n", "Epoch 813/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4967 - distribution_lambda_26_loss: 0.6011 - distribution_lambda_27_loss: 1.4532 - distribution_lambda_28_loss: 0.4423 - val_loss: 2.6491 - val_distribution_lambda_26_loss: 0.6702 - val_distribution_lambda_27_loss: 1.5091 - val_distribution_lambda_28_loss: 0.4699\n", "Epoch 814/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4721 - distribution_lambda_26_loss: 0.6078 - distribution_lambda_27_loss: 1.4307 - distribution_lambda_28_loss: 0.4337 - val_loss: 2.6479 - val_distribution_lambda_26_loss: 0.6687 - val_distribution_lambda_27_loss: 1.5091 - val_distribution_lambda_28_loss: 0.4702\n", "Epoch 815/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4890 - distribution_lambda_26_loss: 0.6004 - distribution_lambda_27_loss: 1.4405 - distribution_lambda_28_loss: 0.4481 - val_loss: 2.6487 - val_distribution_lambda_26_loss: 0.6699 - val_distribution_lambda_27_loss: 1.5098 - val_distribution_lambda_28_loss: 0.4691\n", "Epoch 816/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5284 - distribution_lambda_26_loss: 0.6107 - distribution_lambda_27_loss: 1.4669 - distribution_lambda_28_loss: 0.4509 - val_loss: 2.6440 - val_distribution_lambda_26_loss: 0.6664 - val_distribution_lambda_27_loss: 1.5085 - val_distribution_lambda_28_loss: 0.4691\n", "Epoch 817/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.5089 - distribution_lambda_26_loss: 0.6090 - distribution_lambda_27_loss: 1.4527 - distribution_lambda_28_loss: 0.4473 - val_loss: 2.6435 - val_distribution_lambda_26_loss: 0.6646 - val_distribution_lambda_27_loss: 1.5091 - val_distribution_lambda_28_loss: 0.4697\n", "Epoch 818/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5015 - distribution_lambda_26_loss: 0.6080 - distribution_lambda_27_loss: 1.4465 - distribution_lambda_28_loss: 0.4470 - val_loss: 2.6447 - val_distribution_lambda_26_loss: 0.6654 - val_distribution_lambda_27_loss: 1.5090 - val_distribution_lambda_28_loss: 0.4703\n", "Epoch 819/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5171 - distribution_lambda_26_loss: 0.6076 - distribution_lambda_27_loss: 1.4678 - distribution_lambda_28_loss: 0.4418 - val_loss: 2.6434 - val_distribution_lambda_26_loss: 0.6650 - val_distribution_lambda_27_loss: 1.5090 - val_distribution_lambda_28_loss: 0.4694\n", "Epoch 820/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5133 - distribution_lambda_26_loss: 0.6077 - distribution_lambda_27_loss: 1.4570 - distribution_lambda_28_loss: 0.4486 - val_loss: 2.6452 - val_distribution_lambda_26_loss: 0.6669 - val_distribution_lambda_27_loss: 1.5085 - val_distribution_lambda_28_loss: 0.4698\n", "Epoch 821/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5073 - distribution_lambda_26_loss: 0.6011 - distribution_lambda_27_loss: 1.4601 - distribution_lambda_28_loss: 0.4462 - val_loss: 2.6454 - val_distribution_lambda_26_loss: 0.6680 - val_distribution_lambda_27_loss: 1.5071 - val_distribution_lambda_28_loss: 0.4703\n", "Epoch 822/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4966 - distribution_lambda_26_loss: 0.6175 - distribution_lambda_27_loss: 1.4436 - distribution_lambda_28_loss: 0.4355 - val_loss: 2.6450 - val_distribution_lambda_26_loss: 0.6678 - val_distribution_lambda_27_loss: 1.5070 - val_distribution_lambda_28_loss: 0.4701\n", "Epoch 823/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4959 - distribution_lambda_26_loss: 0.5980 - distribution_lambda_27_loss: 1.4599 - distribution_lambda_28_loss: 0.4380 - val_loss: 2.6453 - val_distribution_lambda_26_loss: 0.6675 - val_distribution_lambda_27_loss: 1.5087 - val_distribution_lambda_28_loss: 0.4691\n", "Epoch 824/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5039 - distribution_lambda_26_loss: 0.6123 - distribution_lambda_27_loss: 1.4455 - distribution_lambda_28_loss: 0.4461 - val_loss: 2.6423 - val_distribution_lambda_26_loss: 0.6649 - val_distribution_lambda_27_loss: 1.5083 - val_distribution_lambda_28_loss: 0.4692\n", "Epoch 825/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4956 - distribution_lambda_26_loss: 0.6000 - distribution_lambda_27_loss: 1.4505 - distribution_lambda_28_loss: 0.4451 - val_loss: 2.6420 - val_distribution_lambda_26_loss: 0.6645 - val_distribution_lambda_27_loss: 1.5086 - val_distribution_lambda_28_loss: 0.4689\n", "Epoch 826/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4924 - distribution_lambda_26_loss: 0.6074 - distribution_lambda_27_loss: 1.4451 - distribution_lambda_28_loss: 0.4398 - val_loss: 2.6410 - val_distribution_lambda_26_loss: 0.6634 - val_distribution_lambda_27_loss: 1.5078 - val_distribution_lambda_28_loss: 0.4698\n", "Epoch 827/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5016 - distribution_lambda_26_loss: 0.5998 - distribution_lambda_27_loss: 1.4545 - distribution_lambda_28_loss: 0.4473 - val_loss: 2.6386 - val_distribution_lambda_26_loss: 0.6620 - val_distribution_lambda_27_loss: 1.5069 - val_distribution_lambda_28_loss: 0.4697\n", "Epoch 828/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4790 - distribution_lambda_26_loss: 0.5971 - distribution_lambda_27_loss: 1.4420 - distribution_lambda_28_loss: 0.4398 - val_loss: 2.6411 - val_distribution_lambda_26_loss: 0.6643 - val_distribution_lambda_27_loss: 1.5069 - val_distribution_lambda_28_loss: 0.4700\n", "Epoch 829/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4725 - distribution_lambda_26_loss: 0.5937 - distribution_lambda_27_loss: 1.4403 - distribution_lambda_28_loss: 0.4385 - val_loss: 2.6371 - val_distribution_lambda_26_loss: 0.6630 - val_distribution_lambda_27_loss: 1.5047 - val_distribution_lambda_28_loss: 0.4695\n", "Epoch 830/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4952 - distribution_lambda_26_loss: 0.5973 - distribution_lambda_27_loss: 1.4541 - distribution_lambda_28_loss: 0.4438 - val_loss: 2.6343 - val_distribution_lambda_26_loss: 0.6611 - val_distribution_lambda_27_loss: 1.5041 - val_distribution_lambda_28_loss: 0.4691\n", "Epoch 831/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5039 - distribution_lambda_26_loss: 0.6067 - distribution_lambda_27_loss: 1.4503 - distribution_lambda_28_loss: 0.4469 - val_loss: 2.6357 - val_distribution_lambda_26_loss: 0.6611 - val_distribution_lambda_27_loss: 1.5055 - val_distribution_lambda_28_loss: 0.4691\n", "Epoch 832/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.4923 - distribution_lambda_26_loss: 0.6111 - distribution_lambda_27_loss: 1.4433 - distribution_lambda_28_loss: 0.4378 - val_loss: 2.6342 - val_distribution_lambda_26_loss: 0.6590 - val_distribution_lambda_27_loss: 1.5067 - val_distribution_lambda_28_loss: 0.4686\n", "Epoch 833/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4948 - distribution_lambda_26_loss: 0.6131 - distribution_lambda_27_loss: 1.4449 - distribution_lambda_28_loss: 0.4368 - val_loss: 2.6342 - val_distribution_lambda_26_loss: 0.6579 - val_distribution_lambda_27_loss: 1.5072 - val_distribution_lambda_28_loss: 0.4691\n", "Epoch 834/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5126 - distribution_lambda_26_loss: 0.5998 - distribution_lambda_27_loss: 1.4661 - distribution_lambda_28_loss: 0.4467 - val_loss: 2.6322 - val_distribution_lambda_26_loss: 0.6584 - val_distribution_lambda_27_loss: 1.5062 - val_distribution_lambda_28_loss: 0.4676\n", "Epoch 835/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4927 - distribution_lambda_26_loss: 0.5915 - distribution_lambda_27_loss: 1.4554 - distribution_lambda_28_loss: 0.4457 - val_loss: 2.6320 - val_distribution_lambda_26_loss: 0.6583 - val_distribution_lambda_27_loss: 1.5069 - val_distribution_lambda_28_loss: 0.4669\n", "Epoch 836/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4705 - distribution_lambda_26_loss: 0.5918 - distribution_lambda_27_loss: 1.4413 - distribution_lambda_28_loss: 0.4375 - val_loss: 2.6320 - val_distribution_lambda_26_loss: 0.6581 - val_distribution_lambda_27_loss: 1.5068 - val_distribution_lambda_28_loss: 0.4671\n", "Epoch 837/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4718 - distribution_lambda_26_loss: 0.5895 - distribution_lambda_27_loss: 1.4444 - distribution_lambda_28_loss: 0.4378 - val_loss: 2.6332 - val_distribution_lambda_26_loss: 0.6600 - val_distribution_lambda_27_loss: 1.5068 - val_distribution_lambda_28_loss: 0.4663\n", "Epoch 838/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4824 - distribution_lambda_26_loss: 0.6021 - distribution_lambda_27_loss: 1.4467 - distribution_lambda_28_loss: 0.4336 - val_loss: 2.6318 - val_distribution_lambda_26_loss: 0.6598 - val_distribution_lambda_27_loss: 1.5064 - val_distribution_lambda_28_loss: 0.4657\n", "Epoch 839/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4768 - distribution_lambda_26_loss: 0.5906 - distribution_lambda_27_loss: 1.4456 - distribution_lambda_28_loss: 0.4406 - val_loss: 2.6303 - val_distribution_lambda_26_loss: 0.6588 - val_distribution_lambda_27_loss: 1.5056 - val_distribution_lambda_28_loss: 0.4659\n", "Epoch 840/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4689 - distribution_lambda_26_loss: 0.5978 - distribution_lambda_27_loss: 1.4403 - distribution_lambda_28_loss: 0.4308 - val_loss: 2.6251 - val_distribution_lambda_26_loss: 0.6547 - val_distribution_lambda_27_loss: 1.5050 - val_distribution_lambda_28_loss: 0.4654\n", "Epoch 841/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.4989 - distribution_lambda_26_loss: 0.5956 - distribution_lambda_27_loss: 1.4605 - distribution_lambda_28_loss: 0.4428 - val_loss: 2.6211 - val_distribution_lambda_26_loss: 0.6526 - val_distribution_lambda_27_loss: 1.5025 - val_distribution_lambda_28_loss: 0.4660\n", "Epoch 842/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.5009 - distribution_lambda_26_loss: 0.5980 - distribution_lambda_27_loss: 1.4551 - distribution_lambda_28_loss: 0.4478 - val_loss: 2.6206 - val_distribution_lambda_26_loss: 0.6524 - val_distribution_lambda_27_loss: 1.5028 - val_distribution_lambda_28_loss: 0.4653\n", "Epoch 843/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4821 - distribution_lambda_26_loss: 0.6004 - distribution_lambda_27_loss: 1.4437 - distribution_lambda_28_loss: 0.4380 - val_loss: 2.6222 - val_distribution_lambda_26_loss: 0.6539 - val_distribution_lambda_27_loss: 1.5021 - val_distribution_lambda_28_loss: 0.4662\n", "Epoch 844/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4828 - distribution_lambda_26_loss: 0.5959 - distribution_lambda_27_loss: 1.4414 - distribution_lambda_28_loss: 0.4455 - val_loss: 2.6240 - val_distribution_lambda_26_loss: 0.6547 - val_distribution_lambda_27_loss: 1.5034 - val_distribution_lambda_28_loss: 0.4659\n", "Epoch 845/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4732 - distribution_lambda_26_loss: 0.5879 - distribution_lambda_27_loss: 1.4523 - distribution_lambda_28_loss: 0.4329 - val_loss: 2.6266 - val_distribution_lambda_26_loss: 0.6549 - val_distribution_lambda_27_loss: 1.5058 - val_distribution_lambda_28_loss: 0.4659\n", "Epoch 846/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4642 - distribution_lambda_26_loss: 0.5853 - distribution_lambda_27_loss: 1.4435 - distribution_lambda_28_loss: 0.4354 - val_loss: 2.6273 - val_distribution_lambda_26_loss: 0.6546 - val_distribution_lambda_27_loss: 1.5061 - val_distribution_lambda_28_loss: 0.4666\n", "Epoch 847/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4930 - distribution_lambda_26_loss: 0.5997 - distribution_lambda_27_loss: 1.4460 - distribution_lambda_28_loss: 0.4473 - val_loss: 2.6262 - val_distribution_lambda_26_loss: 0.6544 - val_distribution_lambda_27_loss: 1.5055 - val_distribution_lambda_28_loss: 0.4664\n", "Epoch 848/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4470 - distribution_lambda_26_loss: 0.5795 - distribution_lambda_27_loss: 1.4394 - distribution_lambda_28_loss: 0.4281 - val_loss: 2.6290 - val_distribution_lambda_26_loss: 0.6572 - val_distribution_lambda_27_loss: 1.5052 - val_distribution_lambda_28_loss: 0.4665\n", "Epoch 849/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4728 - distribution_lambda_26_loss: 0.5907 - distribution_lambda_27_loss: 1.4442 - distribution_lambda_28_loss: 0.4379 - val_loss: 2.6247 - val_distribution_lambda_26_loss: 0.6549 - val_distribution_lambda_27_loss: 1.5044 - val_distribution_lambda_28_loss: 0.4654\n", "Epoch 850/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4658 - distribution_lambda_26_loss: 0.5916 - distribution_lambda_27_loss: 1.4419 - distribution_lambda_28_loss: 0.4323 - val_loss: 2.6198 - val_distribution_lambda_26_loss: 0.6501 - val_distribution_lambda_27_loss: 1.5044 - val_distribution_lambda_28_loss: 0.4652\n", "Epoch 851/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4700 - distribution_lambda_26_loss: 0.5891 - distribution_lambda_27_loss: 1.4425 - distribution_lambda_28_loss: 0.4385 - val_loss: 2.6199 - val_distribution_lambda_26_loss: 0.6503 - val_distribution_lambda_27_loss: 1.5044 - val_distribution_lambda_28_loss: 0.4652\n", "Epoch 852/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4721 - distribution_lambda_26_loss: 0.5969 - distribution_lambda_27_loss: 1.4362 - distribution_lambda_28_loss: 0.4390 - val_loss: 2.6179 - val_distribution_lambda_26_loss: 0.6489 - val_distribution_lambda_27_loss: 1.5035 - val_distribution_lambda_28_loss: 0.4655\n", "Epoch 853/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4714 - distribution_lambda_26_loss: 0.5929 - distribution_lambda_27_loss: 1.4419 - distribution_lambda_28_loss: 0.4367 - val_loss: 2.6172 - val_distribution_lambda_26_loss: 0.6484 - val_distribution_lambda_27_loss: 1.5031 - val_distribution_lambda_28_loss: 0.4657\n", "Epoch 854/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4688 - distribution_lambda_26_loss: 0.5852 - distribution_lambda_27_loss: 1.4423 - distribution_lambda_28_loss: 0.4413 - val_loss: 2.6201 - val_distribution_lambda_26_loss: 0.6493 - val_distribution_lambda_27_loss: 1.5044 - val_distribution_lambda_28_loss: 0.4664\n", "Epoch 855/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.4568 - distribution_lambda_26_loss: 0.5824 - distribution_lambda_27_loss: 1.4437 - distribution_lambda_28_loss: 0.4307 - val_loss: 2.6202 - val_distribution_lambda_26_loss: 0.6508 - val_distribution_lambda_27_loss: 1.5031 - val_distribution_lambda_28_loss: 0.4663\n", "Epoch 856/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4852 - distribution_lambda_26_loss: 0.5772 - distribution_lambda_27_loss: 1.4619 - distribution_lambda_28_loss: 0.4461 - val_loss: 2.6235 - val_distribution_lambda_26_loss: 0.6545 - val_distribution_lambda_27_loss: 1.5016 - val_distribution_lambda_28_loss: 0.4674\n", "Epoch 857/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4661 - distribution_lambda_26_loss: 0.5795 - distribution_lambda_27_loss: 1.4473 - distribution_lambda_28_loss: 0.4393 - val_loss: 2.6216 - val_distribution_lambda_26_loss: 0.6529 - val_distribution_lambda_27_loss: 1.5020 - val_distribution_lambda_28_loss: 0.4667\n", "Epoch 858/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4640 - distribution_lambda_26_loss: 0.5841 - distribution_lambda_27_loss: 1.4425 - distribution_lambda_28_loss: 0.4374 - val_loss: 2.6178 - val_distribution_lambda_26_loss: 0.6493 - val_distribution_lambda_27_loss: 1.5019 - val_distribution_lambda_28_loss: 0.4666\n", "Epoch 859/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4533 - distribution_lambda_26_loss: 0.5842 - distribution_lambda_27_loss: 1.4374 - distribution_lambda_28_loss: 0.4316 - val_loss: 2.6131 - val_distribution_lambda_26_loss: 0.6453 - val_distribution_lambda_27_loss: 1.5016 - val_distribution_lambda_28_loss: 0.4662\n", "Epoch 860/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4688 - distribution_lambda_26_loss: 0.5766 - distribution_lambda_27_loss: 1.4479 - distribution_lambda_28_loss: 0.4443 - val_loss: 2.6148 - val_distribution_lambda_26_loss: 0.6466 - val_distribution_lambda_27_loss: 1.5015 - val_distribution_lambda_28_loss: 0.4667\n", "Epoch 861/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4628 - distribution_lambda_26_loss: 0.5776 - distribution_lambda_27_loss: 1.4431 - distribution_lambda_28_loss: 0.4421 - val_loss: 2.6146 - val_distribution_lambda_26_loss: 0.6465 - val_distribution_lambda_27_loss: 1.5017 - val_distribution_lambda_28_loss: 0.4664\n", "Epoch 862/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4443 - distribution_lambda_26_loss: 0.5755 - distribution_lambda_27_loss: 1.4379 - distribution_lambda_28_loss: 0.4309 - val_loss: 2.6169 - val_distribution_lambda_26_loss: 0.6489 - val_distribution_lambda_27_loss: 1.5011 - val_distribution_lambda_28_loss: 0.4669\n", "Epoch 863/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4441 - distribution_lambda_26_loss: 0.5825 - distribution_lambda_27_loss: 1.4301 - distribution_lambda_28_loss: 0.4315 - val_loss: 2.6155 - val_distribution_lambda_26_loss: 0.6476 - val_distribution_lambda_27_loss: 1.5011 - val_distribution_lambda_28_loss: 0.4668\n", "Epoch 864/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4331 - distribution_lambda_26_loss: 0.5738 - distribution_lambda_27_loss: 1.4301 - distribution_lambda_28_loss: 0.4291 - val_loss: 2.6150 - val_distribution_lambda_26_loss: 0.6474 - val_distribution_lambda_27_loss: 1.5006 - val_distribution_lambda_28_loss: 0.4669\n", "Epoch 865/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.4468 - distribution_lambda_26_loss: 0.5820 - distribution_lambda_27_loss: 1.4369 - distribution_lambda_28_loss: 0.4279 - val_loss: 2.6103 - val_distribution_lambda_26_loss: 0.6432 - val_distribution_lambda_27_loss: 1.5009 - val_distribution_lambda_28_loss: 0.4662\n", "Epoch 866/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4492 - distribution_lambda_26_loss: 0.5648 - distribution_lambda_27_loss: 1.4482 - distribution_lambda_28_loss: 0.4361 - val_loss: 2.6102 - val_distribution_lambda_26_loss: 0.6435 - val_distribution_lambda_27_loss: 1.5010 - val_distribution_lambda_28_loss: 0.4657\n", "Epoch 867/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4296 - distribution_lambda_26_loss: 0.5668 - distribution_lambda_27_loss: 1.4294 - distribution_lambda_28_loss: 0.4333 - val_loss: 2.6126 - val_distribution_lambda_26_loss: 0.6455 - val_distribution_lambda_27_loss: 1.5014 - val_distribution_lambda_28_loss: 0.4657\n", "Epoch 868/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.4516 - distribution_lambda_26_loss: 0.5892 - distribution_lambda_27_loss: 1.4291 - distribution_lambda_28_loss: 0.4332 - val_loss: 2.6128 - val_distribution_lambda_26_loss: 0.6474 - val_distribution_lambda_27_loss: 1.4994 - val_distribution_lambda_28_loss: 0.4659\n", "Epoch 869/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4740 - distribution_lambda_26_loss: 0.5923 - distribution_lambda_27_loss: 1.4418 - distribution_lambda_28_loss: 0.4399 - val_loss: 2.6136 - val_distribution_lambda_26_loss: 0.6481 - val_distribution_lambda_27_loss: 1.4991 - val_distribution_lambda_28_loss: 0.4663\n", "Epoch 870/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.4376 - distribution_lambda_26_loss: 0.5752 - distribution_lambda_27_loss: 1.4317 - distribution_lambda_28_loss: 0.4307 - val_loss: 2.6093 - val_distribution_lambda_26_loss: 0.6439 - val_distribution_lambda_27_loss: 1.4991 - val_distribution_lambda_28_loss: 0.4664\n", "Epoch 871/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4429 - distribution_lambda_26_loss: 0.5755 - distribution_lambda_27_loss: 1.4339 - distribution_lambda_28_loss: 0.4335 - val_loss: 2.6108 - val_distribution_lambda_26_loss: 0.6442 - val_distribution_lambda_27_loss: 1.5000 - val_distribution_lambda_28_loss: 0.4666\n", "Epoch 872/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4233 - distribution_lambda_26_loss: 0.5643 - distribution_lambda_27_loss: 1.4288 - distribution_lambda_28_loss: 0.4302 - val_loss: 2.6108 - val_distribution_lambda_26_loss: 0.6447 - val_distribution_lambda_27_loss: 1.4990 - val_distribution_lambda_28_loss: 0.4671\n", "Epoch 873/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4389 - distribution_lambda_26_loss: 0.5703 - distribution_lambda_27_loss: 1.4379 - distribution_lambda_28_loss: 0.4306 - val_loss: 2.6113 - val_distribution_lambda_26_loss: 0.6455 - val_distribution_lambda_27_loss: 1.4984 - val_distribution_lambda_28_loss: 0.4674\n", "Epoch 874/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4632 - distribution_lambda_26_loss: 0.5866 - distribution_lambda_27_loss: 1.4408 - distribution_lambda_28_loss: 0.4359 - val_loss: 2.6086 - val_distribution_lambda_26_loss: 0.6418 - val_distribution_lambda_27_loss: 1.4981 - val_distribution_lambda_28_loss: 0.4687\n", "Epoch 875/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4662 - distribution_lambda_26_loss: 0.5668 - distribution_lambda_27_loss: 1.4611 - distribution_lambda_28_loss: 0.4382 - val_loss: 2.6113 - val_distribution_lambda_26_loss: 0.6434 - val_distribution_lambda_27_loss: 1.4996 - val_distribution_lambda_28_loss: 0.4683\n", "Epoch 876/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4433 - distribution_lambda_26_loss: 0.5864 - distribution_lambda_27_loss: 1.4301 - distribution_lambda_28_loss: 0.4268 - val_loss: 2.6091 - val_distribution_lambda_26_loss: 0.6409 - val_distribution_lambda_27_loss: 1.5006 - val_distribution_lambda_28_loss: 0.4675\n", "Epoch 877/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4471 - distribution_lambda_26_loss: 0.5741 - distribution_lambda_27_loss: 1.4340 - distribution_lambda_28_loss: 0.4390 - val_loss: 2.6072 - val_distribution_lambda_26_loss: 0.6411 - val_distribution_lambda_27_loss: 1.4986 - val_distribution_lambda_28_loss: 0.4675\n", "Epoch 878/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4264 - distribution_lambda_26_loss: 0.5681 - distribution_lambda_27_loss: 1.4295 - distribution_lambda_28_loss: 0.4289 - val_loss: 2.6031 - val_distribution_lambda_26_loss: 0.6390 - val_distribution_lambda_27_loss: 1.4968 - val_distribution_lambda_28_loss: 0.4672\n", "Epoch 879/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.4123 - distribution_lambda_26_loss: 0.5719 - distribution_lambda_27_loss: 1.4199 - distribution_lambda_28_loss: 0.4205 - val_loss: 2.5972 - val_distribution_lambda_26_loss: 0.6357 - val_distribution_lambda_27_loss: 1.4951 - val_distribution_lambda_28_loss: 0.4664\n", "Epoch 880/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4502 - distribution_lambda_26_loss: 0.5756 - distribution_lambda_27_loss: 1.4393 - distribution_lambda_28_loss: 0.4353 - val_loss: 2.5971 - val_distribution_lambda_26_loss: 0.6352 - val_distribution_lambda_27_loss: 1.4955 - val_distribution_lambda_28_loss: 0.4665\n", "Epoch 881/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4525 - distribution_lambda_26_loss: 0.5618 - distribution_lambda_27_loss: 1.4544 - distribution_lambda_28_loss: 0.4363 - val_loss: 2.6029 - val_distribution_lambda_26_loss: 0.6391 - val_distribution_lambda_27_loss: 1.4968 - val_distribution_lambda_28_loss: 0.4669\n", "Epoch 882/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4030 - distribution_lambda_26_loss: 0.5666 - distribution_lambda_27_loss: 1.4160 - distribution_lambda_28_loss: 0.4204 - val_loss: 2.6014 - val_distribution_lambda_26_loss: 0.6372 - val_distribution_lambda_27_loss: 1.4968 - val_distribution_lambda_28_loss: 0.4674\n", "Epoch 883/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4166 - distribution_lambda_26_loss: 0.5631 - distribution_lambda_27_loss: 1.4261 - distribution_lambda_28_loss: 0.4273 - val_loss: 2.5995 - val_distribution_lambda_26_loss: 0.6364 - val_distribution_lambda_27_loss: 1.4967 - val_distribution_lambda_28_loss: 0.4664\n", "Epoch 884/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4268 - distribution_lambda_26_loss: 0.5704 - distribution_lambda_27_loss: 1.4294 - distribution_lambda_28_loss: 0.4270 - val_loss: 2.5945 - val_distribution_lambda_26_loss: 0.6331 - val_distribution_lambda_27_loss: 1.4950 - val_distribution_lambda_28_loss: 0.4663\n", "Epoch 885/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4383 - distribution_lambda_26_loss: 0.5829 - distribution_lambda_27_loss: 1.4294 - distribution_lambda_28_loss: 0.4260 - val_loss: 2.5929 - val_distribution_lambda_26_loss: 0.6308 - val_distribution_lambda_27_loss: 1.4956 - val_distribution_lambda_28_loss: 0.4666\n", "Epoch 886/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4215 - distribution_lambda_26_loss: 0.5693 - distribution_lambda_27_loss: 1.4273 - distribution_lambda_28_loss: 0.4249 - val_loss: 2.5959 - val_distribution_lambda_26_loss: 0.6332 - val_distribution_lambda_27_loss: 1.4959 - val_distribution_lambda_28_loss: 0.4668\n", "Epoch 887/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4011 - distribution_lambda_26_loss: 0.5651 - distribution_lambda_27_loss: 1.4150 - distribution_lambda_28_loss: 0.4210 - val_loss: 2.5962 - val_distribution_lambda_26_loss: 0.6350 - val_distribution_lambda_27_loss: 1.4948 - val_distribution_lambda_28_loss: 0.4664\n", "Epoch 888/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4370 - distribution_lambda_26_loss: 0.5785 - distribution_lambda_27_loss: 1.4335 - distribution_lambda_28_loss: 0.4250 - val_loss: 2.5977 - val_distribution_lambda_26_loss: 0.6354 - val_distribution_lambda_27_loss: 1.4952 - val_distribution_lambda_28_loss: 0.4670\n", "Epoch 889/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.4248 - distribution_lambda_26_loss: 0.5627 - distribution_lambda_27_loss: 1.4288 - distribution_lambda_28_loss: 0.4333 - val_loss: 2.5958 - val_distribution_lambda_26_loss: 0.6334 - val_distribution_lambda_27_loss: 1.4956 - val_distribution_lambda_28_loss: 0.4668\n", "Epoch 890/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4127 - distribution_lambda_26_loss: 0.5621 - distribution_lambda_27_loss: 1.4276 - distribution_lambda_28_loss: 0.4230 - val_loss: 2.5956 - val_distribution_lambda_26_loss: 0.6333 - val_distribution_lambda_27_loss: 1.4945 - val_distribution_lambda_28_loss: 0.4678\n", "Epoch 891/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4044 - distribution_lambda_26_loss: 0.5599 - distribution_lambda_27_loss: 1.4227 - distribution_lambda_28_loss: 0.4218 - val_loss: 2.5946 - val_distribution_lambda_26_loss: 0.6335 - val_distribution_lambda_27_loss: 1.4925 - val_distribution_lambda_28_loss: 0.4686\n", "Epoch 892/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4252 - distribution_lambda_26_loss: 0.5692 - distribution_lambda_27_loss: 1.4284 - distribution_lambda_28_loss: 0.4276 - val_loss: 2.5965 - val_distribution_lambda_26_loss: 0.6335 - val_distribution_lambda_27_loss: 1.4938 - val_distribution_lambda_28_loss: 0.4691\n", "Epoch 893/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4101 - distribution_lambda_26_loss: 0.5550 - distribution_lambda_27_loss: 1.4266 - distribution_lambda_28_loss: 0.4285 - val_loss: 2.5945 - val_distribution_lambda_26_loss: 0.6310 - val_distribution_lambda_27_loss: 1.4950 - val_distribution_lambda_28_loss: 0.4685\n", "Epoch 894/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4217 - distribution_lambda_26_loss: 0.5645 - distribution_lambda_27_loss: 1.4305 - distribution_lambda_28_loss: 0.4268 - val_loss: 2.5959 - val_distribution_lambda_26_loss: 0.6315 - val_distribution_lambda_27_loss: 1.4956 - val_distribution_lambda_28_loss: 0.4688\n", "Epoch 895/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4368 - distribution_lambda_26_loss: 0.5688 - distribution_lambda_27_loss: 1.4352 - distribution_lambda_28_loss: 0.4329 - val_loss: 2.5925 - val_distribution_lambda_26_loss: 0.6289 - val_distribution_lambda_27_loss: 1.4949 - val_distribution_lambda_28_loss: 0.4686\n", "Epoch 896/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3888 - distribution_lambda_26_loss: 0.5528 - distribution_lambda_27_loss: 1.4174 - distribution_lambda_28_loss: 0.4186 - val_loss: 2.5947 - val_distribution_lambda_26_loss: 0.6304 - val_distribution_lambda_27_loss: 1.4959 - val_distribution_lambda_28_loss: 0.4684\n", "Epoch 897/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3920 - distribution_lambda_26_loss: 0.5735 - distribution_lambda_27_loss: 1.4097 - distribution_lambda_28_loss: 0.4088 - val_loss: 2.5942 - val_distribution_lambda_26_loss: 0.6290 - val_distribution_lambda_27_loss: 1.4967 - val_distribution_lambda_28_loss: 0.4685\n", "Epoch 898/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3885 - distribution_lambda_26_loss: 0.5441 - distribution_lambda_27_loss: 1.4134 - distribution_lambda_28_loss: 0.4311 - val_loss: 2.5927 - val_distribution_lambda_26_loss: 0.6286 - val_distribution_lambda_27_loss: 1.4959 - val_distribution_lambda_28_loss: 0.4682\n", "Epoch 899/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4157 - distribution_lambda_26_loss: 0.5569 - distribution_lambda_27_loss: 1.4277 - distribution_lambda_28_loss: 0.4311 - val_loss: 2.5923 - val_distribution_lambda_26_loss: 0.6292 - val_distribution_lambda_27_loss: 1.4955 - val_distribution_lambda_28_loss: 0.4676\n", "Epoch 900/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4135 - distribution_lambda_26_loss: 0.5593 - distribution_lambda_27_loss: 1.4301 - distribution_lambda_28_loss: 0.4242 - val_loss: 2.5925 - val_distribution_lambda_26_loss: 0.6298 - val_distribution_lambda_27_loss: 1.4956 - val_distribution_lambda_28_loss: 0.4671\n", "Epoch 901/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3827 - distribution_lambda_26_loss: 0.5397 - distribution_lambda_27_loss: 1.4201 - distribution_lambda_28_loss: 0.4229 - val_loss: 2.5943 - val_distribution_lambda_26_loss: 0.6297 - val_distribution_lambda_27_loss: 1.4971 - val_distribution_lambda_28_loss: 0.4676\n", "Epoch 902/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3958 - distribution_lambda_26_loss: 0.5649 - distribution_lambda_27_loss: 1.4202 - distribution_lambda_28_loss: 0.4108 - val_loss: 2.5916 - val_distribution_lambda_26_loss: 0.6267 - val_distribution_lambda_27_loss: 1.4971 - val_distribution_lambda_28_loss: 0.4678\n", "Epoch 903/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3612 - distribution_lambda_26_loss: 0.5478 - distribution_lambda_27_loss: 1.4002 - distribution_lambda_28_loss: 0.4132 - val_loss: 2.5906 - val_distribution_lambda_26_loss: 0.6257 - val_distribution_lambda_27_loss: 1.4974 - val_distribution_lambda_28_loss: 0.4674\n", "Epoch 904/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3962 - distribution_lambda_26_loss: 0.5416 - distribution_lambda_27_loss: 1.4252 - distribution_lambda_28_loss: 0.4294 - val_loss: 2.5910 - val_distribution_lambda_26_loss: 0.6270 - val_distribution_lambda_27_loss: 1.4967 - val_distribution_lambda_28_loss: 0.4673\n", "Epoch 905/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3791 - distribution_lambda_26_loss: 0.5471 - distribution_lambda_27_loss: 1.4192 - distribution_lambda_28_loss: 0.4127 - val_loss: 2.5919 - val_distribution_lambda_26_loss: 0.6271 - val_distribution_lambda_27_loss: 1.4974 - val_distribution_lambda_28_loss: 0.4674\n", "Epoch 906/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3775 - distribution_lambda_26_loss: 0.5477 - distribution_lambda_27_loss: 1.4127 - distribution_lambda_28_loss: 0.4171 - val_loss: 2.5915 - val_distribution_lambda_26_loss: 0.6265 - val_distribution_lambda_27_loss: 1.4974 - val_distribution_lambda_28_loss: 0.4677\n", "Epoch 907/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4084 - distribution_lambda_26_loss: 0.5687 - distribution_lambda_27_loss: 1.4161 - distribution_lambda_28_loss: 0.4236 - val_loss: 2.5905 - val_distribution_lambda_26_loss: 0.6247 - val_distribution_lambda_27_loss: 1.4985 - val_distribution_lambda_28_loss: 0.4673\n", "Epoch 908/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3880 - distribution_lambda_26_loss: 0.5433 - distribution_lambda_27_loss: 1.4244 - distribution_lambda_28_loss: 0.4203 - val_loss: 2.5860 - val_distribution_lambda_26_loss: 0.6233 - val_distribution_lambda_27_loss: 1.4957 - val_distribution_lambda_28_loss: 0.4671\n", "Epoch 909/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3762 - distribution_lambda_26_loss: 0.5474 - distribution_lambda_27_loss: 1.4111 - distribution_lambda_28_loss: 0.4177 - val_loss: 2.5877 - val_distribution_lambda_26_loss: 0.6250 - val_distribution_lambda_27_loss: 1.4944 - val_distribution_lambda_28_loss: 0.4683\n", "Epoch 910/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3826 - distribution_lambda_26_loss: 0.5369 - distribution_lambda_27_loss: 1.4295 - distribution_lambda_28_loss: 0.4162 - val_loss: 2.5882 - val_distribution_lambda_26_loss: 0.6252 - val_distribution_lambda_27_loss: 1.4937 - val_distribution_lambda_28_loss: 0.4693\n", "Epoch 911/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3885 - distribution_lambda_26_loss: 0.5486 - distribution_lambda_27_loss: 1.4230 - distribution_lambda_28_loss: 0.4169 - val_loss: 2.5896 - val_distribution_lambda_26_loss: 0.6249 - val_distribution_lambda_27_loss: 1.4950 - val_distribution_lambda_28_loss: 0.4696\n", "Epoch 912/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3849 - distribution_lambda_26_loss: 0.5494 - distribution_lambda_27_loss: 1.4196 - distribution_lambda_28_loss: 0.4160 - val_loss: 2.5866 - val_distribution_lambda_26_loss: 0.6215 - val_distribution_lambda_27_loss: 1.4952 - val_distribution_lambda_28_loss: 0.4699\n", "Epoch 913/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 7ms/step - loss: 2.3889 - distribution_lambda_26_loss: 0.5446 - distribution_lambda_27_loss: 1.4280 - distribution_lambda_28_loss: 0.4163 - val_loss: 2.5868 - val_distribution_lambda_26_loss: 0.6209 - val_distribution_lambda_27_loss: 1.4957 - val_distribution_lambda_28_loss: 0.4702\n", "Epoch 914/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4040 - distribution_lambda_26_loss: 0.5545 - distribution_lambda_27_loss: 1.4302 - distribution_lambda_28_loss: 0.4193 - val_loss: 2.5798 - val_distribution_lambda_26_loss: 0.6163 - val_distribution_lambda_27_loss: 1.4931 - val_distribution_lambda_28_loss: 0.4704\n", "Epoch 915/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3946 - distribution_lambda_26_loss: 0.5479 - distribution_lambda_27_loss: 1.4218 - distribution_lambda_28_loss: 0.4249 - val_loss: 2.5777 - val_distribution_lambda_26_loss: 0.6149 - val_distribution_lambda_27_loss: 1.4925 - val_distribution_lambda_28_loss: 0.4702\n", "Epoch 916/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3908 - distribution_lambda_26_loss: 0.5395 - distribution_lambda_27_loss: 1.4222 - distribution_lambda_28_loss: 0.4291 - val_loss: 2.5788 - val_distribution_lambda_26_loss: 0.6168 - val_distribution_lambda_27_loss: 1.4917 - val_distribution_lambda_28_loss: 0.4703\n", "Epoch 917/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3720 - distribution_lambda_26_loss: 0.5401 - distribution_lambda_27_loss: 1.4235 - distribution_lambda_28_loss: 0.4085 - val_loss: 2.5772 - val_distribution_lambda_26_loss: 0.6149 - val_distribution_lambda_27_loss: 1.4922 - val_distribution_lambda_28_loss: 0.4701\n", "Epoch 918/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.3988 - distribution_lambda_26_loss: 0.5431 - distribution_lambda_27_loss: 1.4244 - distribution_lambda_28_loss: 0.4313 - val_loss: 2.5765 - val_distribution_lambda_26_loss: 0.6155 - val_distribution_lambda_27_loss: 1.4909 - val_distribution_lambda_28_loss: 0.4701\n", "Epoch 919/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3910 - distribution_lambda_26_loss: 0.5453 - distribution_lambda_27_loss: 1.4267 - distribution_lambda_28_loss: 0.4190 - val_loss: 2.5793 - val_distribution_lambda_26_loss: 0.6179 - val_distribution_lambda_27_loss: 1.4916 - val_distribution_lambda_28_loss: 0.4699\n", "Epoch 920/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.4018 - distribution_lambda_26_loss: 0.5384 - distribution_lambda_27_loss: 1.4383 - distribution_lambda_28_loss: 0.4250 - val_loss: 2.5775 - val_distribution_lambda_26_loss: 0.6179 - val_distribution_lambda_27_loss: 1.4894 - val_distribution_lambda_28_loss: 0.4702\n", "Epoch 921/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3742 - distribution_lambda_26_loss: 0.5450 - distribution_lambda_27_loss: 1.4108 - distribution_lambda_28_loss: 0.4184 - val_loss: 2.5690 - val_distribution_lambda_26_loss: 0.6096 - val_distribution_lambda_27_loss: 1.4895 - val_distribution_lambda_28_loss: 0.4698\n", "Epoch 922/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3837 - distribution_lambda_26_loss: 0.5360 - distribution_lambda_27_loss: 1.4214 - distribution_lambda_28_loss: 0.4263 - val_loss: 2.5682 - val_distribution_lambda_26_loss: 0.6066 - val_distribution_lambda_27_loss: 1.4917 - val_distribution_lambda_28_loss: 0.4700\n", "Epoch 923/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3751 - distribution_lambda_26_loss: 0.5273 - distribution_lambda_27_loss: 1.4298 - distribution_lambda_28_loss: 0.4180 - val_loss: 2.5686 - val_distribution_lambda_26_loss: 0.6062 - val_distribution_lambda_27_loss: 1.4926 - val_distribution_lambda_28_loss: 0.4698\n", "Epoch 924/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3543 - distribution_lambda_26_loss: 0.5334 - distribution_lambda_27_loss: 1.4068 - distribution_lambda_28_loss: 0.4140 - val_loss: 2.5687 - val_distribution_lambda_26_loss: 0.6072 - val_distribution_lambda_27_loss: 1.4913 - val_distribution_lambda_28_loss: 0.4703\n", "Epoch 925/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3777 - distribution_lambda_26_loss: 0.5338 - distribution_lambda_27_loss: 1.4206 - distribution_lambda_28_loss: 0.4233 - val_loss: 2.5615 - val_distribution_lambda_26_loss: 0.6023 - val_distribution_lambda_27_loss: 1.4902 - val_distribution_lambda_28_loss: 0.4689\n", "Epoch 926/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3557 - distribution_lambda_26_loss: 0.5294 - distribution_lambda_27_loss: 1.4057 - distribution_lambda_28_loss: 0.4205 - val_loss: 2.5622 - val_distribution_lambda_26_loss: 0.6037 - val_distribution_lambda_27_loss: 1.4901 - val_distribution_lambda_28_loss: 0.4685\n", "Epoch 927/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3582 - distribution_lambda_26_loss: 0.5321 - distribution_lambda_27_loss: 1.4189 - distribution_lambda_28_loss: 0.4072 - val_loss: 2.5610 - val_distribution_lambda_26_loss: 0.6033 - val_distribution_lambda_27_loss: 1.4895 - val_distribution_lambda_28_loss: 0.4683\n", "Epoch 928/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3382 - distribution_lambda_26_loss: 0.5152 - distribution_lambda_27_loss: 1.4097 - distribution_lambda_28_loss: 0.4132 - val_loss: 2.5579 - val_distribution_lambda_26_loss: 0.6013 - val_distribution_lambda_27_loss: 1.4890 - val_distribution_lambda_28_loss: 0.4676\n", "Epoch 929/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3163 - distribution_lambda_26_loss: 0.5112 - distribution_lambda_27_loss: 1.4055 - distribution_lambda_28_loss: 0.3997 - val_loss: 2.5547 - val_distribution_lambda_26_loss: 0.5996 - val_distribution_lambda_27_loss: 1.4877 - val_distribution_lambda_28_loss: 0.4675\n", "Epoch 930/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3581 - distribution_lambda_26_loss: 0.5170 - distribution_lambda_27_loss: 1.4170 - distribution_lambda_28_loss: 0.4241 - val_loss: 2.5549 - val_distribution_lambda_26_loss: 0.6001 - val_distribution_lambda_27_loss: 1.4871 - val_distribution_lambda_28_loss: 0.4677\n", "Epoch 931/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3624 - distribution_lambda_26_loss: 0.5315 - distribution_lambda_27_loss: 1.4101 - distribution_lambda_28_loss: 0.4208 - val_loss: 2.5524 - val_distribution_lambda_26_loss: 0.5991 - val_distribution_lambda_27_loss: 1.4860 - val_distribution_lambda_28_loss: 0.4673\n", "Epoch 932/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3550 - distribution_lambda_26_loss: 0.5230 - distribution_lambda_27_loss: 1.4199 - distribution_lambda_28_loss: 0.4121 - val_loss: 2.5518 - val_distribution_lambda_26_loss: 0.5969 - val_distribution_lambda_27_loss: 1.4874 - val_distribution_lambda_28_loss: 0.4675\n", "Epoch 933/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3401 - distribution_lambda_26_loss: 0.5282 - distribution_lambda_27_loss: 1.4080 - distribution_lambda_28_loss: 0.4039 - val_loss: 2.5529 - val_distribution_lambda_26_loss: 0.5983 - val_distribution_lambda_27_loss: 1.4867 - val_distribution_lambda_28_loss: 0.4679\n", "Epoch 934/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3800 - distribution_lambda_26_loss: 0.5371 - distribution_lambda_27_loss: 1.4241 - distribution_lambda_28_loss: 0.4188 - val_loss: 2.5470 - val_distribution_lambda_26_loss: 0.5944 - val_distribution_lambda_27_loss: 1.4857 - val_distribution_lambda_28_loss: 0.4668\n", "Epoch 935/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3346 - distribution_lambda_26_loss: 0.5209 - distribution_lambda_27_loss: 1.4080 - distribution_lambda_28_loss: 0.4057 - val_loss: 2.5440 - val_distribution_lambda_26_loss: 0.5940 - val_distribution_lambda_27_loss: 1.4843 - val_distribution_lambda_28_loss: 0.4657\n", "Epoch 936/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3559 - distribution_lambda_26_loss: 0.5238 - distribution_lambda_27_loss: 1.4207 - distribution_lambda_28_loss: 0.4114 - val_loss: 2.5480 - val_distribution_lambda_26_loss: 0.5954 - val_distribution_lambda_27_loss: 1.4869 - val_distribution_lambda_28_loss: 0.4657\n", "Epoch 937/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.3400 - distribution_lambda_26_loss: 0.5231 - distribution_lambda_27_loss: 1.3996 - distribution_lambda_28_loss: 0.4174 - val_loss: 2.5477 - val_distribution_lambda_26_loss: 0.5954 - val_distribution_lambda_27_loss: 1.4868 - val_distribution_lambda_28_loss: 0.4655\n", "Epoch 938/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3600 - distribution_lambda_26_loss: 0.5188 - distribution_lambda_27_loss: 1.4231 - distribution_lambda_28_loss: 0.4181 - val_loss: 2.5440 - val_distribution_lambda_26_loss: 0.5916 - val_distribution_lambda_27_loss: 1.4868 - val_distribution_lambda_28_loss: 0.4656\n", "Epoch 939/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3269 - distribution_lambda_26_loss: 0.5169 - distribution_lambda_27_loss: 1.4070 - distribution_lambda_28_loss: 0.4031 - val_loss: 2.5398 - val_distribution_lambda_26_loss: 0.5895 - val_distribution_lambda_27_loss: 1.4851 - val_distribution_lambda_28_loss: 0.4652\n", "Epoch 940/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3415 - distribution_lambda_26_loss: 0.5203 - distribution_lambda_27_loss: 1.4117 - distribution_lambda_28_loss: 0.4095 - val_loss: 2.5330 - val_distribution_lambda_26_loss: 0.5840 - val_distribution_lambda_27_loss: 1.4838 - val_distribution_lambda_28_loss: 0.4653\n", "Epoch 941/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3412 - distribution_lambda_26_loss: 0.5129 - distribution_lambda_27_loss: 1.4091 - distribution_lambda_28_loss: 0.4192 - val_loss: 2.5313 - val_distribution_lambda_26_loss: 0.5855 - val_distribution_lambda_27_loss: 1.4809 - val_distribution_lambda_28_loss: 0.4649\n", "Epoch 942/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3422 - distribution_lambda_26_loss: 0.4984 - distribution_lambda_27_loss: 1.4279 - distribution_lambda_28_loss: 0.4160 - val_loss: 2.5339 - val_distribution_lambda_26_loss: 0.5911 - val_distribution_lambda_27_loss: 1.4782 - val_distribution_lambda_28_loss: 0.4646\n", "Epoch 943/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3276 - distribution_lambda_26_loss: 0.5207 - distribution_lambda_27_loss: 1.4048 - distribution_lambda_28_loss: 0.4021 - val_loss: 2.5355 - val_distribution_lambda_26_loss: 0.5917 - val_distribution_lambda_27_loss: 1.4796 - val_distribution_lambda_28_loss: 0.4642\n", "Epoch 944/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3114 - distribution_lambda_26_loss: 0.5094 - distribution_lambda_27_loss: 1.3996 - distribution_lambda_28_loss: 0.4024 - val_loss: 2.5310 - val_distribution_lambda_26_loss: 0.5872 - val_distribution_lambda_27_loss: 1.4796 - val_distribution_lambda_28_loss: 0.4642\n", "Epoch 945/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.3253 - distribution_lambda_26_loss: 0.5180 - distribution_lambda_27_loss: 1.3958 - distribution_lambda_28_loss: 0.4115 - val_loss: 2.5250 - val_distribution_lambda_26_loss: 0.5846 - val_distribution_lambda_27_loss: 1.4768 - val_distribution_lambda_28_loss: 0.4637\n", "Epoch 946/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3107 - distribution_lambda_26_loss: 0.4924 - distribution_lambda_27_loss: 1.4045 - distribution_lambda_28_loss: 0.4137 - val_loss: 2.5252 - val_distribution_lambda_26_loss: 0.5848 - val_distribution_lambda_27_loss: 1.4773 - val_distribution_lambda_28_loss: 0.4631\n", "Epoch 947/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3036 - distribution_lambda_26_loss: 0.5025 - distribution_lambda_27_loss: 1.3984 - distribution_lambda_28_loss: 0.4027 - val_loss: 2.5253 - val_distribution_lambda_26_loss: 0.5844 - val_distribution_lambda_27_loss: 1.4776 - val_distribution_lambda_28_loss: 0.4633\n", "Epoch 948/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3009 - distribution_lambda_26_loss: 0.5019 - distribution_lambda_27_loss: 1.3935 - distribution_lambda_28_loss: 0.4054 - val_loss: 2.5234 - val_distribution_lambda_26_loss: 0.5831 - val_distribution_lambda_27_loss: 1.4773 - val_distribution_lambda_28_loss: 0.4630\n", "Epoch 949/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3004 - distribution_lambda_26_loss: 0.4988 - distribution_lambda_27_loss: 1.3933 - distribution_lambda_28_loss: 0.4083 - val_loss: 2.5230 - val_distribution_lambda_26_loss: 0.5839 - val_distribution_lambda_27_loss: 1.4764 - val_distribution_lambda_28_loss: 0.4627\n", "Epoch 950/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3013 - distribution_lambda_26_loss: 0.5042 - distribution_lambda_27_loss: 1.4008 - distribution_lambda_28_loss: 0.3963 - val_loss: 2.5188 - val_distribution_lambda_26_loss: 0.5808 - val_distribution_lambda_27_loss: 1.4758 - val_distribution_lambda_28_loss: 0.4622\n", "Epoch 951/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3286 - distribution_lambda_26_loss: 0.5127 - distribution_lambda_27_loss: 1.4128 - distribution_lambda_28_loss: 0.4032 - val_loss: 2.5217 - val_distribution_lambda_26_loss: 0.5835 - val_distribution_lambda_27_loss: 1.4761 - val_distribution_lambda_28_loss: 0.4622\n", "Epoch 952/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3162 - distribution_lambda_26_loss: 0.5110 - distribution_lambda_27_loss: 1.4044 - distribution_lambda_28_loss: 0.4008 - val_loss: 2.5206 - val_distribution_lambda_26_loss: 0.5817 - val_distribution_lambda_27_loss: 1.4762 - val_distribution_lambda_28_loss: 0.4627\n", "Epoch 953/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3241 - distribution_lambda_26_loss: 0.5184 - distribution_lambda_27_loss: 1.3982 - distribution_lambda_28_loss: 0.4074 - val_loss: 2.5130 - val_distribution_lambda_26_loss: 0.5740 - val_distribution_lambda_27_loss: 1.4761 - val_distribution_lambda_28_loss: 0.4630\n", "Epoch 954/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3175 - distribution_lambda_26_loss: 0.5135 - distribution_lambda_27_loss: 1.4056 - distribution_lambda_28_loss: 0.3984 - val_loss: 2.5142 - val_distribution_lambda_26_loss: 0.5750 - val_distribution_lambda_27_loss: 1.4768 - val_distribution_lambda_28_loss: 0.4624\n", "Epoch 955/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3237 - distribution_lambda_26_loss: 0.5062 - distribution_lambda_27_loss: 1.4072 - distribution_lambda_28_loss: 0.4104 - val_loss: 2.5129 - val_distribution_lambda_26_loss: 0.5746 - val_distribution_lambda_27_loss: 1.4770 - val_distribution_lambda_28_loss: 0.4613\n", "Epoch 956/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2991 - distribution_lambda_26_loss: 0.5011 - distribution_lambda_27_loss: 1.3974 - distribution_lambda_28_loss: 0.4006 - val_loss: 2.5130 - val_distribution_lambda_26_loss: 0.5746 - val_distribution_lambda_27_loss: 1.4774 - val_distribution_lambda_28_loss: 0.4610\n", "Epoch 957/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3367 - distribution_lambda_26_loss: 0.5112 - distribution_lambda_27_loss: 1.4139 - distribution_lambda_28_loss: 0.4116 - val_loss: 2.5104 - val_distribution_lambda_26_loss: 0.5732 - val_distribution_lambda_27_loss: 1.4767 - val_distribution_lambda_28_loss: 0.4606\n", "Epoch 958/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3025 - distribution_lambda_26_loss: 0.5077 - distribution_lambda_27_loss: 1.3884 - distribution_lambda_28_loss: 0.4064 - val_loss: 2.5141 - val_distribution_lambda_26_loss: 0.5734 - val_distribution_lambda_27_loss: 1.4793 - val_distribution_lambda_28_loss: 0.4614\n", "Epoch 959/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3073 - distribution_lambda_26_loss: 0.5122 - distribution_lambda_27_loss: 1.3883 - distribution_lambda_28_loss: 0.4067 - val_loss: 2.5144 - val_distribution_lambda_26_loss: 0.5748 - val_distribution_lambda_27_loss: 1.4787 - val_distribution_lambda_28_loss: 0.4609\n", "Epoch 960/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2804 - distribution_lambda_26_loss: 0.4939 - distribution_lambda_27_loss: 1.3893 - distribution_lambda_28_loss: 0.3972 - val_loss: 2.5089 - val_distribution_lambda_26_loss: 0.5734 - val_distribution_lambda_27_loss: 1.4753 - val_distribution_lambda_28_loss: 0.4602\n", "Epoch 961/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 7ms/step - loss: 2.3002 - distribution_lambda_26_loss: 0.4973 - distribution_lambda_27_loss: 1.4026 - distribution_lambda_28_loss: 0.4003 - val_loss: 2.5081 - val_distribution_lambda_26_loss: 0.5718 - val_distribution_lambda_27_loss: 1.4763 - val_distribution_lambda_28_loss: 0.4599\n", "Epoch 962/2500\n", "8/8 [==============================] - 0s 8ms/step - loss: 2.2906 - distribution_lambda_26_loss: 0.4969 - distribution_lambda_27_loss: 1.3905 - distribution_lambda_28_loss: 0.4032 - val_loss: 2.5068 - val_distribution_lambda_26_loss: 0.5682 - val_distribution_lambda_27_loss: 1.4788 - val_distribution_lambda_28_loss: 0.4598\n", "Epoch 963/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3213 - distribution_lambda_26_loss: 0.5033 - distribution_lambda_27_loss: 1.4069 - distribution_lambda_28_loss: 0.4111 - val_loss: 2.5001 - val_distribution_lambda_26_loss: 0.5638 - val_distribution_lambda_27_loss: 1.4774 - val_distribution_lambda_28_loss: 0.4589\n", "Epoch 964/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2717 - distribution_lambda_26_loss: 0.4773 - distribution_lambda_27_loss: 1.3961 - distribution_lambda_28_loss: 0.3983 - val_loss: 2.5042 - val_distribution_lambda_26_loss: 0.5671 - val_distribution_lambda_27_loss: 1.4781 - val_distribution_lambda_28_loss: 0.4590\n", "Epoch 965/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2919 - distribution_lambda_26_loss: 0.4937 - distribution_lambda_27_loss: 1.3928 - distribution_lambda_28_loss: 0.4053 - val_loss: 2.5031 - val_distribution_lambda_26_loss: 0.5682 - val_distribution_lambda_27_loss: 1.4769 - val_distribution_lambda_28_loss: 0.4581\n", "Epoch 966/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3143 - distribution_lambda_26_loss: 0.4956 - distribution_lambda_27_loss: 1.4156 - distribution_lambda_28_loss: 0.4031 - val_loss: 2.5013 - val_distribution_lambda_26_loss: 0.5678 - val_distribution_lambda_27_loss: 1.4766 - val_distribution_lambda_28_loss: 0.4569\n", "Epoch 967/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3235 - distribution_lambda_26_loss: 0.5006 - distribution_lambda_27_loss: 1.4075 - distribution_lambda_28_loss: 0.4154 - val_loss: 2.5023 - val_distribution_lambda_26_loss: 0.5695 - val_distribution_lambda_27_loss: 1.4762 - val_distribution_lambda_28_loss: 0.4567\n", "Epoch 968/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2808 - distribution_lambda_26_loss: 0.4934 - distribution_lambda_27_loss: 1.3889 - distribution_lambda_28_loss: 0.3986 - val_loss: 2.4993 - val_distribution_lambda_26_loss: 0.5682 - val_distribution_lambda_27_loss: 1.4749 - val_distribution_lambda_28_loss: 0.4562\n", "Epoch 969/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2682 - distribution_lambda_26_loss: 0.4974 - distribution_lambda_27_loss: 1.3838 - distribution_lambda_28_loss: 0.3871 - val_loss: 2.4988 - val_distribution_lambda_26_loss: 0.5654 - val_distribution_lambda_27_loss: 1.4765 - val_distribution_lambda_28_loss: 0.4568\n", "Epoch 970/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2952 - distribution_lambda_26_loss: 0.4875 - distribution_lambda_27_loss: 1.4011 - distribution_lambda_28_loss: 0.4066 - val_loss: 2.4955 - val_distribution_lambda_26_loss: 0.5629 - val_distribution_lambda_27_loss: 1.4754 - val_distribution_lambda_28_loss: 0.4573\n", "Epoch 971/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3139 - distribution_lambda_26_loss: 0.4959 - distribution_lambda_27_loss: 1.4097 - distribution_lambda_28_loss: 0.4083 - val_loss: 2.4970 - val_distribution_lambda_26_loss: 0.5625 - val_distribution_lambda_27_loss: 1.4779 - val_distribution_lambda_28_loss: 0.4566\n", "Epoch 972/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2787 - distribution_lambda_26_loss: 0.4875 - distribution_lambda_27_loss: 1.3935 - distribution_lambda_28_loss: 0.3977 - val_loss: 2.4927 - val_distribution_lambda_26_loss: 0.5580 - val_distribution_lambda_27_loss: 1.4777 - val_distribution_lambda_28_loss: 0.4570\n", "Epoch 973/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2963 - distribution_lambda_26_loss: 0.4931 - distribution_lambda_27_loss: 1.4095 - distribution_lambda_28_loss: 0.3937 - val_loss: 2.4906 - val_distribution_lambda_26_loss: 0.5594 - val_distribution_lambda_27_loss: 1.4757 - val_distribution_lambda_28_loss: 0.4555\n", "Epoch 974/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2986 - distribution_lambda_26_loss: 0.4895 - distribution_lambda_27_loss: 1.4028 - distribution_lambda_28_loss: 0.4063 - val_loss: 2.4838 - val_distribution_lambda_26_loss: 0.5574 - val_distribution_lambda_27_loss: 1.4717 - val_distribution_lambda_28_loss: 0.4547\n", "Epoch 975/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2937 - distribution_lambda_26_loss: 0.4996 - distribution_lambda_27_loss: 1.3893 - distribution_lambda_28_loss: 0.4047 - val_loss: 2.4798 - val_distribution_lambda_26_loss: 0.5539 - val_distribution_lambda_27_loss: 1.4714 - val_distribution_lambda_28_loss: 0.4545\n", "Epoch 976/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.3242 - distribution_lambda_26_loss: 0.4898 - distribution_lambda_27_loss: 1.4196 - distribution_lambda_28_loss: 0.4149 - val_loss: 2.4863 - val_distribution_lambda_26_loss: 0.5547 - val_distribution_lambda_27_loss: 1.4761 - val_distribution_lambda_28_loss: 0.4554\n", "Epoch 977/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2743 - distribution_lambda_26_loss: 0.4858 - distribution_lambda_27_loss: 1.3902 - distribution_lambda_28_loss: 0.3983 - val_loss: 2.4913 - val_distribution_lambda_26_loss: 0.5605 - val_distribution_lambda_27_loss: 1.4748 - val_distribution_lambda_28_loss: 0.4560\n", "Epoch 978/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2518 - distribution_lambda_26_loss: 0.4865 - distribution_lambda_27_loss: 1.3771 - distribution_lambda_28_loss: 0.3882 - val_loss: 2.4849 - val_distribution_lambda_26_loss: 0.5561 - val_distribution_lambda_27_loss: 1.4728 - val_distribution_lambda_28_loss: 0.4560\n", "Epoch 979/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2695 - distribution_lambda_26_loss: 0.4807 - distribution_lambda_27_loss: 1.3897 - distribution_lambda_28_loss: 0.3990 - val_loss: 2.4753 - val_distribution_lambda_26_loss: 0.5490 - val_distribution_lambda_27_loss: 1.4709 - val_distribution_lambda_28_loss: 0.4554\n", "Epoch 980/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2833 - distribution_lambda_26_loss: 0.4969 - distribution_lambda_27_loss: 1.3953 - distribution_lambda_28_loss: 0.3911 - val_loss: 2.4729 - val_distribution_lambda_26_loss: 0.5445 - val_distribution_lambda_27_loss: 1.4744 - val_distribution_lambda_28_loss: 0.4540\n", "Epoch 981/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2748 - distribution_lambda_26_loss: 0.4737 - distribution_lambda_27_loss: 1.3904 - distribution_lambda_28_loss: 0.4107 - val_loss: 2.4703 - val_distribution_lambda_26_loss: 0.5465 - val_distribution_lambda_27_loss: 1.4717 - val_distribution_lambda_28_loss: 0.4521\n", "Epoch 982/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2723 - distribution_lambda_26_loss: 0.4740 - distribution_lambda_27_loss: 1.3898 - distribution_lambda_28_loss: 0.4085 - val_loss: 2.4676 - val_distribution_lambda_26_loss: 0.5483 - val_distribution_lambda_27_loss: 1.4685 - val_distribution_lambda_28_loss: 0.4508\n", "Epoch 983/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2768 - distribution_lambda_26_loss: 0.4804 - distribution_lambda_27_loss: 1.4038 - distribution_lambda_28_loss: 0.3926 - val_loss: 2.4677 - val_distribution_lambda_26_loss: 0.5469 - val_distribution_lambda_27_loss: 1.4697 - val_distribution_lambda_28_loss: 0.4511\n", "Epoch 984/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2604 - distribution_lambda_26_loss: 0.4765 - distribution_lambda_27_loss: 1.3889 - distribution_lambda_28_loss: 0.3950 - val_loss: 2.4679 - val_distribution_lambda_26_loss: 0.5446 - val_distribution_lambda_27_loss: 1.4721 - val_distribution_lambda_28_loss: 0.4512\n", "Epoch 985/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.2841 - distribution_lambda_26_loss: 0.4794 - distribution_lambda_27_loss: 1.4026 - distribution_lambda_28_loss: 0.4021 - val_loss: 2.4705 - val_distribution_lambda_26_loss: 0.5461 - val_distribution_lambda_27_loss: 1.4726 - val_distribution_lambda_28_loss: 0.4518\n", "Epoch 986/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2596 - distribution_lambda_26_loss: 0.4690 - distribution_lambda_27_loss: 1.3893 - distribution_lambda_28_loss: 0.4013 - val_loss: 2.4741 - val_distribution_lambda_26_loss: 0.5513 - val_distribution_lambda_27_loss: 1.4716 - val_distribution_lambda_28_loss: 0.4512\n", "Epoch 987/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2575 - distribution_lambda_26_loss: 0.4785 - distribution_lambda_27_loss: 1.3902 - distribution_lambda_28_loss: 0.3888 - val_loss: 2.4693 - val_distribution_lambda_26_loss: 0.5479 - val_distribution_lambda_27_loss: 1.4704 - val_distribution_lambda_28_loss: 0.4509\n", "Epoch 988/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2654 - distribution_lambda_26_loss: 0.4724 - distribution_lambda_27_loss: 1.3921 - distribution_lambda_28_loss: 0.4009 - val_loss: 2.4574 - val_distribution_lambda_26_loss: 0.5413 - val_distribution_lambda_27_loss: 1.4662 - val_distribution_lambda_28_loss: 0.4498\n", "Epoch 989/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2386 - distribution_lambda_26_loss: 0.4657 - distribution_lambda_27_loss: 1.3826 - distribution_lambda_28_loss: 0.3903 - val_loss: 2.4552 - val_distribution_lambda_26_loss: 0.5421 - val_distribution_lambda_27_loss: 1.4641 - val_distribution_lambda_28_loss: 0.4490\n", "Epoch 990/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2531 - distribution_lambda_26_loss: 0.4808 - distribution_lambda_27_loss: 1.3834 - distribution_lambda_28_loss: 0.3889 - val_loss: 2.4585 - val_distribution_lambda_26_loss: 0.5453 - val_distribution_lambda_27_loss: 1.4641 - val_distribution_lambda_28_loss: 0.4491\n", "Epoch 991/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2643 - distribution_lambda_26_loss: 0.4650 - distribution_lambda_27_loss: 1.3939 - distribution_lambda_28_loss: 0.4054 - val_loss: 2.4703 - val_distribution_lambda_26_loss: 0.5522 - val_distribution_lambda_27_loss: 1.4687 - val_distribution_lambda_28_loss: 0.4494\n", "Epoch 992/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2329 - distribution_lambda_26_loss: 0.4723 - distribution_lambda_27_loss: 1.3776 - distribution_lambda_28_loss: 0.3831 - val_loss: 2.4690 - val_distribution_lambda_26_loss: 0.5492 - val_distribution_lambda_27_loss: 1.4701 - val_distribution_lambda_28_loss: 0.4496\n", "Epoch 993/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2718 - distribution_lambda_26_loss: 0.4894 - distribution_lambda_27_loss: 1.3856 - distribution_lambda_28_loss: 0.3968 - val_loss: 2.4564 - val_distribution_lambda_26_loss: 0.5388 - val_distribution_lambda_27_loss: 1.4684 - val_distribution_lambda_28_loss: 0.4493\n", "Epoch 994/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2524 - distribution_lambda_26_loss: 0.4711 - distribution_lambda_27_loss: 1.3905 - distribution_lambda_28_loss: 0.3909 - val_loss: 2.4492 - val_distribution_lambda_26_loss: 0.5341 - val_distribution_lambda_27_loss: 1.4661 - val_distribution_lambda_28_loss: 0.4490\n", "Epoch 995/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2633 - distribution_lambda_26_loss: 0.4755 - distribution_lambda_27_loss: 1.3918 - distribution_lambda_28_loss: 0.3961 - val_loss: 2.4503 - val_distribution_lambda_26_loss: 0.5353 - val_distribution_lambda_27_loss: 1.4666 - val_distribution_lambda_28_loss: 0.4484\n", "Epoch 996/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2323 - distribution_lambda_26_loss: 0.4680 - distribution_lambda_27_loss: 1.3798 - distribution_lambda_28_loss: 0.3845 - val_loss: 2.4534 - val_distribution_lambda_26_loss: 0.5399 - val_distribution_lambda_27_loss: 1.4656 - val_distribution_lambda_28_loss: 0.4480\n", "Epoch 997/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2250 - distribution_lambda_26_loss: 0.4662 - distribution_lambda_27_loss: 1.3673 - distribution_lambda_28_loss: 0.3915 - val_loss: 2.4501 - val_distribution_lambda_26_loss: 0.5390 - val_distribution_lambda_27_loss: 1.4643 - val_distribution_lambda_28_loss: 0.4468\n", "Epoch 998/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2369 - distribution_lambda_26_loss: 0.4653 - distribution_lambda_27_loss: 1.3895 - distribution_lambda_28_loss: 0.3821 - val_loss: 2.4467 - val_distribution_lambda_26_loss: 0.5364 - val_distribution_lambda_27_loss: 1.4639 - val_distribution_lambda_28_loss: 0.4464\n", "Epoch 999/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2530 - distribution_lambda_26_loss: 0.4741 - distribution_lambda_27_loss: 1.3792 - distribution_lambda_28_loss: 0.3997 - val_loss: 2.4496 - val_distribution_lambda_26_loss: 0.5402 - val_distribution_lambda_27_loss: 1.4630 - val_distribution_lambda_28_loss: 0.4464\n", "Epoch 1000/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2453 - distribution_lambda_26_loss: 0.4689 - distribution_lambda_27_loss: 1.3805 - distribution_lambda_28_loss: 0.3959 - val_loss: 2.4494 - val_distribution_lambda_26_loss: 0.5397 - val_distribution_lambda_27_loss: 1.4629 - val_distribution_lambda_28_loss: 0.4468\n", "Epoch 1001/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2115 - distribution_lambda_26_loss: 0.4511 - distribution_lambda_27_loss: 1.3802 - distribution_lambda_28_loss: 0.3802 - val_loss: 2.4482 - val_distribution_lambda_26_loss: 0.5365 - val_distribution_lambda_27_loss: 1.4644 - val_distribution_lambda_28_loss: 0.4472\n", "Epoch 1002/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2280 - distribution_lambda_26_loss: 0.4570 - distribution_lambda_27_loss: 1.3787 - distribution_lambda_28_loss: 0.3924 - val_loss: 2.4443 - val_distribution_lambda_26_loss: 0.5325 - val_distribution_lambda_27_loss: 1.4642 - val_distribution_lambda_28_loss: 0.4476\n", "Epoch 1003/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2234 - distribution_lambda_26_loss: 0.4747 - distribution_lambda_27_loss: 1.3706 - distribution_lambda_28_loss: 0.3781 - val_loss: 2.4414 - val_distribution_lambda_26_loss: 0.5293 - val_distribution_lambda_27_loss: 1.4649 - val_distribution_lambda_28_loss: 0.4472\n", "Epoch 1004/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2259 - distribution_lambda_26_loss: 0.4693 - distribution_lambda_27_loss: 1.3777 - distribution_lambda_28_loss: 0.3788 - val_loss: 2.4449 - val_distribution_lambda_26_loss: 0.5287 - val_distribution_lambda_27_loss: 1.4681 - val_distribution_lambda_28_loss: 0.4481\n", "Epoch 1005/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2257 - distribution_lambda_26_loss: 0.4645 - distribution_lambda_27_loss: 1.3827 - distribution_lambda_28_loss: 0.3786 - val_loss: 2.4491 - val_distribution_lambda_26_loss: 0.5305 - val_distribution_lambda_27_loss: 1.4700 - val_distribution_lambda_28_loss: 0.4486\n", "Epoch 1006/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2522 - distribution_lambda_26_loss: 0.4683 - distribution_lambda_27_loss: 1.3906 - distribution_lambda_28_loss: 0.3933 - val_loss: 2.4435 - val_distribution_lambda_26_loss: 0.5269 - val_distribution_lambda_27_loss: 1.4690 - val_distribution_lambda_28_loss: 0.4477\n", "Epoch 1007/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2219 - distribution_lambda_26_loss: 0.4639 - distribution_lambda_27_loss: 1.3684 - distribution_lambda_28_loss: 0.3897 - val_loss: 2.4410 - val_distribution_lambda_26_loss: 0.5278 - val_distribution_lambda_27_loss: 1.4668 - val_distribution_lambda_28_loss: 0.4464\n", "Epoch 1008/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.1910 - distribution_lambda_26_loss: 0.4636 - distribution_lambda_27_loss: 1.3599 - distribution_lambda_28_loss: 0.3674 - val_loss: 2.4410 - val_distribution_lambda_26_loss: 0.5271 - val_distribution_lambda_27_loss: 1.4685 - val_distribution_lambda_28_loss: 0.4454\n", "Epoch 1009/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.2303 - distribution_lambda_26_loss: 0.4566 - distribution_lambda_27_loss: 1.3820 - distribution_lambda_28_loss: 0.3917 - val_loss: 2.4384 - val_distribution_lambda_26_loss: 0.5254 - val_distribution_lambda_27_loss: 1.4678 - val_distribution_lambda_28_loss: 0.4452\n", "Epoch 1010/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2228 - distribution_lambda_26_loss: 0.4704 - distribution_lambda_27_loss: 1.3720 - distribution_lambda_28_loss: 0.3804 - val_loss: 2.4355 - val_distribution_lambda_26_loss: 0.5250 - val_distribution_lambda_27_loss: 1.4662 - val_distribution_lambda_28_loss: 0.4444\n", "Epoch 1011/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2329 - distribution_lambda_26_loss: 0.4521 - distribution_lambda_27_loss: 1.4026 - distribution_lambda_28_loss: 0.3782 - val_loss: 2.4367 - val_distribution_lambda_26_loss: 0.5281 - val_distribution_lambda_27_loss: 1.4652 - val_distribution_lambda_28_loss: 0.4434\n", "Epoch 1012/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2154 - distribution_lambda_26_loss: 0.4571 - distribution_lambda_27_loss: 1.3721 - distribution_lambda_28_loss: 0.3863 - val_loss: 2.4367 - val_distribution_lambda_26_loss: 0.5278 - val_distribution_lambda_27_loss: 1.4671 - val_distribution_lambda_28_loss: 0.4417\n", "Epoch 1013/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2141 - distribution_lambda_26_loss: 0.4547 - distribution_lambda_27_loss: 1.3726 - distribution_lambda_28_loss: 0.3867 - val_loss: 2.4294 - val_distribution_lambda_26_loss: 0.5219 - val_distribution_lambda_27_loss: 1.4664 - val_distribution_lambda_28_loss: 0.4411\n", "Epoch 1014/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2185 - distribution_lambda_26_loss: 0.4500 - distribution_lambda_27_loss: 1.3776 - distribution_lambda_28_loss: 0.3909 - val_loss: 2.4305 - val_distribution_lambda_26_loss: 0.5245 - val_distribution_lambda_27_loss: 1.4658 - val_distribution_lambda_28_loss: 0.4402\n", "Epoch 1015/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2447 - distribution_lambda_26_loss: 0.4570 - distribution_lambda_27_loss: 1.3960 - distribution_lambda_28_loss: 0.3917 - val_loss: 2.4310 - val_distribution_lambda_26_loss: 0.5265 - val_distribution_lambda_27_loss: 1.4654 - val_distribution_lambda_28_loss: 0.4392\n", "Epoch 1016/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2074 - distribution_lambda_26_loss: 0.4519 - distribution_lambda_27_loss: 1.3767 - distribution_lambda_28_loss: 0.3788 - val_loss: 2.4281 - val_distribution_lambda_26_loss: 0.5266 - val_distribution_lambda_27_loss: 1.4622 - val_distribution_lambda_28_loss: 0.4393\n", "Epoch 1017/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1969 - distribution_lambda_26_loss: 0.4606 - distribution_lambda_27_loss: 1.3609 - distribution_lambda_28_loss: 0.3754 - val_loss: 2.4238 - val_distribution_lambda_26_loss: 0.5248 - val_distribution_lambda_27_loss: 1.4590 - val_distribution_lambda_28_loss: 0.4400\n", "Epoch 1018/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1825 - distribution_lambda_26_loss: 0.4507 - distribution_lambda_27_loss: 1.3588 - distribution_lambda_28_loss: 0.3731 - val_loss: 2.4186 - val_distribution_lambda_26_loss: 0.5200 - val_distribution_lambda_27_loss: 1.4591 - val_distribution_lambda_28_loss: 0.4396\n", "Epoch 1019/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2089 - distribution_lambda_26_loss: 0.4512 - distribution_lambda_27_loss: 1.3721 - distribution_lambda_28_loss: 0.3856 - val_loss: 2.4200 - val_distribution_lambda_26_loss: 0.5200 - val_distribution_lambda_27_loss: 1.4614 - val_distribution_lambda_28_loss: 0.4387\n", "Epoch 1020/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2085 - distribution_lambda_26_loss: 0.4531 - distribution_lambda_27_loss: 1.3722 - distribution_lambda_28_loss: 0.3832 - val_loss: 2.4214 - val_distribution_lambda_26_loss: 0.5188 - val_distribution_lambda_27_loss: 1.4637 - val_distribution_lambda_28_loss: 0.4390\n", "Epoch 1021/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1860 - distribution_lambda_26_loss: 0.4363 - distribution_lambda_27_loss: 1.3719 - distribution_lambda_28_loss: 0.3778 - val_loss: 2.4259 - val_distribution_lambda_26_loss: 0.5224 - val_distribution_lambda_27_loss: 1.4646 - val_distribution_lambda_28_loss: 0.4389\n", "Epoch 1022/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1737 - distribution_lambda_26_loss: 0.4524 - distribution_lambda_27_loss: 1.3516 - distribution_lambda_28_loss: 0.3696 - val_loss: 2.4269 - val_distribution_lambda_26_loss: 0.5208 - val_distribution_lambda_27_loss: 1.4670 - val_distribution_lambda_28_loss: 0.4391\n", "Epoch 1023/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1598 - distribution_lambda_26_loss: 0.4318 - distribution_lambda_27_loss: 1.3558 - distribution_lambda_28_loss: 0.3723 - val_loss: 2.4189 - val_distribution_lambda_26_loss: 0.5162 - val_distribution_lambda_27_loss: 1.4638 - val_distribution_lambda_28_loss: 0.4389\n", "Epoch 1024/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.1848 - distribution_lambda_26_loss: 0.4468 - distribution_lambda_27_loss: 1.3682 - distribution_lambda_28_loss: 0.3697 - val_loss: 2.4132 - val_distribution_lambda_26_loss: 0.5126 - val_distribution_lambda_27_loss: 1.4630 - val_distribution_lambda_28_loss: 0.4376\n", "Epoch 1025/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1620 - distribution_lambda_26_loss: 0.4393 - distribution_lambda_27_loss: 1.3541 - distribution_lambda_28_loss: 0.3686 - val_loss: 2.4152 - val_distribution_lambda_26_loss: 0.5168 - val_distribution_lambda_27_loss: 1.4615 - val_distribution_lambda_28_loss: 0.4369\n", "Epoch 1026/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1964 - distribution_lambda_26_loss: 0.4474 - distribution_lambda_27_loss: 1.3626 - distribution_lambda_28_loss: 0.3864 - val_loss: 2.4223 - val_distribution_lambda_26_loss: 0.5232 - val_distribution_lambda_27_loss: 1.4612 - val_distribution_lambda_28_loss: 0.4379\n", "Epoch 1027/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.2291 - distribution_lambda_26_loss: 0.4550 - distribution_lambda_27_loss: 1.3881 - distribution_lambda_28_loss: 0.3859 - val_loss: 2.4144 - val_distribution_lambda_26_loss: 0.5159 - val_distribution_lambda_27_loss: 1.4605 - val_distribution_lambda_28_loss: 0.4381\n", "Epoch 1028/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1639 - distribution_lambda_26_loss: 0.4285 - distribution_lambda_27_loss: 1.3621 - distribution_lambda_28_loss: 0.3734 - val_loss: 2.4086 - val_distribution_lambda_26_loss: 0.5085 - val_distribution_lambda_27_loss: 1.4618 - val_distribution_lambda_28_loss: 0.4382\n", "Epoch 1029/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1901 - distribution_lambda_26_loss: 0.4355 - distribution_lambda_27_loss: 1.3805 - distribution_lambda_28_loss: 0.3741 - val_loss: 2.4069 - val_distribution_lambda_26_loss: 0.5075 - val_distribution_lambda_27_loss: 1.4618 - val_distribution_lambda_28_loss: 0.4375\n", "Epoch 1030/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1547 - distribution_lambda_26_loss: 0.4399 - distribution_lambda_27_loss: 1.3515 - distribution_lambda_28_loss: 0.3634 - val_loss: 2.4064 - val_distribution_lambda_26_loss: 0.5073 - val_distribution_lambda_27_loss: 1.4620 - val_distribution_lambda_28_loss: 0.4371\n", "Epoch 1031/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1956 - distribution_lambda_26_loss: 0.4369 - distribution_lambda_27_loss: 1.3772 - distribution_lambda_28_loss: 0.3815 - val_loss: 2.4134 - val_distribution_lambda_26_loss: 0.5118 - val_distribution_lambda_27_loss: 1.4644 - val_distribution_lambda_28_loss: 0.4372\n", "Epoch 1032/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1557 - distribution_lambda_26_loss: 0.4254 - distribution_lambda_27_loss: 1.3614 - distribution_lambda_28_loss: 0.3690 - val_loss: 2.4064 - val_distribution_lambda_26_loss: 0.5085 - val_distribution_lambda_27_loss: 1.4620 - val_distribution_lambda_28_loss: 0.4358\n", "Epoch 1033/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.1790 - distribution_lambda_26_loss: 0.4348 - distribution_lambda_27_loss: 1.3635 - distribution_lambda_28_loss: 0.3808 - val_loss: 2.4017 - val_distribution_lambda_26_loss: 0.5060 - val_distribution_lambda_27_loss: 1.4609 - val_distribution_lambda_28_loss: 0.4347\n", "Epoch 1034/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1783 - distribution_lambda_26_loss: 0.4344 - distribution_lambda_27_loss: 1.3619 - distribution_lambda_28_loss: 0.3820 - val_loss: 2.3957 - val_distribution_lambda_26_loss: 0.5030 - val_distribution_lambda_27_loss: 1.4592 - val_distribution_lambda_28_loss: 0.4334\n", "Epoch 1035/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1788 - distribution_lambda_26_loss: 0.4383 - distribution_lambda_27_loss: 1.3693 - distribution_lambda_28_loss: 0.3712 - val_loss: 2.3995 - val_distribution_lambda_26_loss: 0.5051 - val_distribution_lambda_27_loss: 1.4608 - val_distribution_lambda_28_loss: 0.4337\n", "Epoch 1036/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1634 - distribution_lambda_26_loss: 0.4283 - distribution_lambda_27_loss: 1.3625 - distribution_lambda_28_loss: 0.3725 - val_loss: 2.4049 - val_distribution_lambda_26_loss: 0.5089 - val_distribution_lambda_27_loss: 1.4615 - val_distribution_lambda_28_loss: 0.4346\n", "Epoch 1037/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1352 - distribution_lambda_26_loss: 0.4192 - distribution_lambda_27_loss: 1.3527 - distribution_lambda_28_loss: 0.3634 - val_loss: 2.4051 - val_distribution_lambda_26_loss: 0.5103 - val_distribution_lambda_27_loss: 1.4613 - val_distribution_lambda_28_loss: 0.4335\n", "Epoch 1038/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1827 - distribution_lambda_26_loss: 0.4345 - distribution_lambda_27_loss: 1.3660 - distribution_lambda_28_loss: 0.3822 - val_loss: 2.3966 - val_distribution_lambda_26_loss: 0.5063 - val_distribution_lambda_27_loss: 1.4596 - val_distribution_lambda_28_loss: 0.4308\n", "Epoch 1039/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1700 - distribution_lambda_26_loss: 0.4281 - distribution_lambda_27_loss: 1.3600 - distribution_lambda_28_loss: 0.3818 - val_loss: 2.3949 - val_distribution_lambda_26_loss: 0.5051 - val_distribution_lambda_27_loss: 1.4590 - val_distribution_lambda_28_loss: 0.4308\n", "Epoch 1040/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1415 - distribution_lambda_26_loss: 0.4357 - distribution_lambda_27_loss: 1.3405 - distribution_lambda_28_loss: 0.3653 - val_loss: 2.3999 - val_distribution_lambda_26_loss: 0.5098 - val_distribution_lambda_27_loss: 1.4588 - val_distribution_lambda_28_loss: 0.4313\n", "Epoch 1041/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1511 - distribution_lambda_26_loss: 0.4201 - distribution_lambda_27_loss: 1.3576 - distribution_lambda_28_loss: 0.3734 - val_loss: 2.3899 - val_distribution_lambda_26_loss: 0.5026 - val_distribution_lambda_27_loss: 1.4582 - val_distribution_lambda_28_loss: 0.4291\n", "Epoch 1042/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1913 - distribution_lambda_26_loss: 0.4503 - distribution_lambda_27_loss: 1.3654 - distribution_lambda_28_loss: 0.3755 - val_loss: 2.3850 - val_distribution_lambda_26_loss: 0.4979 - val_distribution_lambda_27_loss: 1.4590 - val_distribution_lambda_28_loss: 0.4281\n", "Epoch 1043/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1825 - distribution_lambda_26_loss: 0.4532 - distribution_lambda_27_loss: 1.3554 - distribution_lambda_28_loss: 0.3740 - val_loss: 2.3927 - val_distribution_lambda_26_loss: 0.5037 - val_distribution_lambda_27_loss: 1.4604 - val_distribution_lambda_28_loss: 0.4285\n", "Epoch 1044/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1976 - distribution_lambda_26_loss: 0.4401 - distribution_lambda_27_loss: 1.3744 - distribution_lambda_28_loss: 0.3831 - val_loss: 2.3944 - val_distribution_lambda_26_loss: 0.5050 - val_distribution_lambda_27_loss: 1.4599 - val_distribution_lambda_28_loss: 0.4294\n", "Epoch 1045/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1431 - distribution_lambda_26_loss: 0.4293 - distribution_lambda_27_loss: 1.3414 - distribution_lambda_28_loss: 0.3724 - val_loss: 2.3926 - val_distribution_lambda_26_loss: 0.5039 - val_distribution_lambda_27_loss: 1.4590 - val_distribution_lambda_28_loss: 0.4297\n", "Epoch 1046/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1763 - distribution_lambda_26_loss: 0.4401 - distribution_lambda_27_loss: 1.3606 - distribution_lambda_28_loss: 0.3757 - val_loss: 2.3993 - val_distribution_lambda_26_loss: 0.5096 - val_distribution_lambda_27_loss: 1.4600 - val_distribution_lambda_28_loss: 0.4297\n", "Epoch 1047/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1388 - distribution_lambda_26_loss: 0.4304 - distribution_lambda_27_loss: 1.3428 - distribution_lambda_28_loss: 0.3656 - val_loss: 2.3863 - val_distribution_lambda_26_loss: 0.4992 - val_distribution_lambda_27_loss: 1.4577 - val_distribution_lambda_28_loss: 0.4294\n", "Epoch 1048/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1666 - distribution_lambda_26_loss: 0.4184 - distribution_lambda_27_loss: 1.3664 - distribution_lambda_28_loss: 0.3818 - val_loss: 2.3807 - val_distribution_lambda_26_loss: 0.4941 - val_distribution_lambda_27_loss: 1.4570 - val_distribution_lambda_28_loss: 0.4296\n", "Epoch 1049/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1856 - distribution_lambda_26_loss: 0.4416 - distribution_lambda_27_loss: 1.3668 - distribution_lambda_28_loss: 0.3773 - val_loss: 2.3798 - val_distribution_lambda_26_loss: 0.4928 - val_distribution_lambda_27_loss: 1.4573 - val_distribution_lambda_28_loss: 0.4298\n", "Epoch 1050/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1498 - distribution_lambda_26_loss: 0.4322 - distribution_lambda_27_loss: 1.3486 - distribution_lambda_28_loss: 0.3690 - val_loss: 2.3781 - val_distribution_lambda_26_loss: 0.4936 - val_distribution_lambda_27_loss: 1.4547 - val_distribution_lambda_28_loss: 0.4299\n", "Epoch 1051/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1494 - distribution_lambda_26_loss: 0.4397 - distribution_lambda_27_loss: 1.3477 - distribution_lambda_28_loss: 0.3619 - val_loss: 2.3673 - val_distribution_lambda_26_loss: 0.4872 - val_distribution_lambda_27_loss: 1.4514 - val_distribution_lambda_28_loss: 0.4287\n", "Epoch 1052/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1659 - distribution_lambda_26_loss: 0.4328 - distribution_lambda_27_loss: 1.3660 - distribution_lambda_28_loss: 0.3671 - val_loss: 2.3723 - val_distribution_lambda_26_loss: 0.4937 - val_distribution_lambda_27_loss: 1.4499 - val_distribution_lambda_28_loss: 0.4287\n", "Epoch 1053/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1446 - distribution_lambda_26_loss: 0.4298 - distribution_lambda_27_loss: 1.3446 - distribution_lambda_28_loss: 0.3703 - val_loss: 2.3733 - val_distribution_lambda_26_loss: 0.4896 - val_distribution_lambda_27_loss: 1.4544 - val_distribution_lambda_28_loss: 0.4293\n", "Epoch 1054/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1466 - distribution_lambda_26_loss: 0.4278 - distribution_lambda_27_loss: 1.3602 - distribution_lambda_28_loss: 0.3587 - val_loss: 2.3720 - val_distribution_lambda_26_loss: 0.4860 - val_distribution_lambda_27_loss: 1.4554 - val_distribution_lambda_28_loss: 0.4306\n", "Epoch 1055/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1386 - distribution_lambda_26_loss: 0.4246 - distribution_lambda_27_loss: 1.3487 - distribution_lambda_28_loss: 0.3653 - val_loss: 2.3679 - val_distribution_lambda_26_loss: 0.4842 - val_distribution_lambda_27_loss: 1.4543 - val_distribution_lambda_28_loss: 0.4294\n", "Epoch 1056/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1191 - distribution_lambda_26_loss: 0.4192 - distribution_lambda_27_loss: 1.3412 - distribution_lambda_28_loss: 0.3586 - val_loss: 2.3680 - val_distribution_lambda_26_loss: 0.4874 - val_distribution_lambda_27_loss: 1.4523 - val_distribution_lambda_28_loss: 0.4283\n", "Epoch 1057/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.1578 - distribution_lambda_26_loss: 0.4307 - distribution_lambda_27_loss: 1.3566 - distribution_lambda_28_loss: 0.3705 - val_loss: 2.3642 - val_distribution_lambda_26_loss: 0.4841 - val_distribution_lambda_27_loss: 1.4535 - val_distribution_lambda_28_loss: 0.4266\n", "Epoch 1058/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0747 - distribution_lambda_26_loss: 0.4017 - distribution_lambda_27_loss: 1.3294 - distribution_lambda_28_loss: 0.3437 - val_loss: 2.3556 - val_distribution_lambda_26_loss: 0.4776 - val_distribution_lambda_27_loss: 1.4517 - val_distribution_lambda_28_loss: 0.4263\n", "Epoch 1059/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1157 - distribution_lambda_26_loss: 0.4121 - distribution_lambda_27_loss: 1.3473 - distribution_lambda_28_loss: 0.3563 - val_loss: 2.3588 - val_distribution_lambda_26_loss: 0.4806 - val_distribution_lambda_27_loss: 1.4516 - val_distribution_lambda_28_loss: 0.4267\n", "Epoch 1060/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1303 - distribution_lambda_26_loss: 0.4168 - distribution_lambda_27_loss: 1.3491 - distribution_lambda_28_loss: 0.3644 - val_loss: 2.3555 - val_distribution_lambda_26_loss: 0.4814 - val_distribution_lambda_27_loss: 1.4487 - val_distribution_lambda_28_loss: 0.4254\n", "Epoch 1061/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1425 - distribution_lambda_26_loss: 0.4263 - distribution_lambda_27_loss: 1.3482 - distribution_lambda_28_loss: 0.3681 - val_loss: 2.3515 - val_distribution_lambda_26_loss: 0.4793 - val_distribution_lambda_27_loss: 1.4468 - val_distribution_lambda_28_loss: 0.4254\n", "Epoch 1062/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0962 - distribution_lambda_26_loss: 0.4073 - distribution_lambda_27_loss: 1.3377 - distribution_lambda_28_loss: 0.3512 - val_loss: 2.3557 - val_distribution_lambda_26_loss: 0.4815 - val_distribution_lambda_27_loss: 1.4490 - val_distribution_lambda_28_loss: 0.4252\n", "Epoch 1063/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1073 - distribution_lambda_26_loss: 0.3925 - distribution_lambda_27_loss: 1.3492 - distribution_lambda_28_loss: 0.3656 - val_loss: 2.3606 - val_distribution_lambda_26_loss: 0.4852 - val_distribution_lambda_27_loss: 1.4497 - val_distribution_lambda_28_loss: 0.4257\n", "Epoch 1064/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1184 - distribution_lambda_26_loss: 0.4124 - distribution_lambda_27_loss: 1.3360 - distribution_lambda_28_loss: 0.3700 - val_loss: 2.3492 - val_distribution_lambda_26_loss: 0.4805 - val_distribution_lambda_27_loss: 1.4445 - val_distribution_lambda_28_loss: 0.4242\n", "Epoch 1065/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1069 - distribution_lambda_26_loss: 0.4144 - distribution_lambda_27_loss: 1.3446 - distribution_lambda_28_loss: 0.3479 - val_loss: 2.3517 - val_distribution_lambda_26_loss: 0.4798 - val_distribution_lambda_27_loss: 1.4471 - val_distribution_lambda_28_loss: 0.4248\n", "Epoch 1066/2500\n", "8/8 [==============================] - 0s 9ms/step - loss: 2.1263 - distribution_lambda_26_loss: 0.4141 - distribution_lambda_27_loss: 1.3526 - distribution_lambda_28_loss: 0.3596 - val_loss: 2.3542 - val_distribution_lambda_26_loss: 0.4810 - val_distribution_lambda_27_loss: 1.4480 - val_distribution_lambda_28_loss: 0.4252\n", "Epoch 1067/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1193 - distribution_lambda_26_loss: 0.4301 - distribution_lambda_27_loss: 1.3354 - distribution_lambda_28_loss: 0.3538 - val_loss: 2.3414 - val_distribution_lambda_26_loss: 0.4682 - val_distribution_lambda_27_loss: 1.4486 - val_distribution_lambda_28_loss: 0.4247\n", "Epoch 1068/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1131 - distribution_lambda_26_loss: 0.4135 - distribution_lambda_27_loss: 1.3361 - distribution_lambda_28_loss: 0.3635 - val_loss: 2.3472 - val_distribution_lambda_26_loss: 0.4717 - val_distribution_lambda_27_loss: 1.4499 - val_distribution_lambda_28_loss: 0.4256\n", "Epoch 1069/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0879 - distribution_lambda_26_loss: 0.3832 - distribution_lambda_27_loss: 1.3521 - distribution_lambda_28_loss: 0.3527 - val_loss: 2.3570 - val_distribution_lambda_26_loss: 0.4783 - val_distribution_lambda_27_loss: 1.4509 - val_distribution_lambda_28_loss: 0.4278\n", "Epoch 1070/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0650 - distribution_lambda_26_loss: 0.3934 - distribution_lambda_27_loss: 1.3223 - distribution_lambda_28_loss: 0.3494 - val_loss: 2.3481 - val_distribution_lambda_26_loss: 0.4747 - val_distribution_lambda_27_loss: 1.4472 - val_distribution_lambda_28_loss: 0.4262\n", "Epoch 1071/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1025 - distribution_lambda_26_loss: 0.3953 - distribution_lambda_27_loss: 1.3459 - distribution_lambda_28_loss: 0.3613 - val_loss: 2.3422 - val_distribution_lambda_26_loss: 0.4728 - val_distribution_lambda_27_loss: 1.4450 - val_distribution_lambda_28_loss: 0.4244\n", "Epoch 1072/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0690 - distribution_lambda_26_loss: 0.3855 - distribution_lambda_27_loss: 1.3310 - distribution_lambda_28_loss: 0.3525 - val_loss: 2.3373 - val_distribution_lambda_26_loss: 0.4706 - val_distribution_lambda_27_loss: 1.4429 - val_distribution_lambda_28_loss: 0.4237\n", "Epoch 1073/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1374 - distribution_lambda_26_loss: 0.4181 - distribution_lambda_27_loss: 1.3492 - distribution_lambda_28_loss: 0.3701 - val_loss: 2.3452 - val_distribution_lambda_26_loss: 0.4777 - val_distribution_lambda_27_loss: 1.4438 - val_distribution_lambda_28_loss: 0.4237\n", "Epoch 1074/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.1299 - distribution_lambda_26_loss: 0.4148 - distribution_lambda_27_loss: 1.3530 - distribution_lambda_28_loss: 0.3620 - val_loss: 2.3473 - val_distribution_lambda_26_loss: 0.4793 - val_distribution_lambda_27_loss: 1.4441 - val_distribution_lambda_28_loss: 0.4239\n", "Epoch 1075/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0949 - distribution_lambda_26_loss: 0.4173 - distribution_lambda_27_loss: 1.3316 - distribution_lambda_28_loss: 0.3460 - val_loss: 2.3366 - val_distribution_lambda_26_loss: 0.4716 - val_distribution_lambda_27_loss: 1.4423 - val_distribution_lambda_28_loss: 0.4227\n", "Epoch 1076/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1140 - distribution_lambda_26_loss: 0.4122 - distribution_lambda_27_loss: 1.3391 - distribution_lambda_28_loss: 0.3626 - val_loss: 2.3408 - val_distribution_lambda_26_loss: 0.4757 - val_distribution_lambda_27_loss: 1.4435 - val_distribution_lambda_28_loss: 0.4216\n", "Epoch 1077/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0899 - distribution_lambda_26_loss: 0.3907 - distribution_lambda_27_loss: 1.3376 - distribution_lambda_28_loss: 0.3616 - val_loss: 2.3347 - val_distribution_lambda_26_loss: 0.4719 - val_distribution_lambda_27_loss: 1.4416 - val_distribution_lambda_28_loss: 0.4212\n", "Epoch 1078/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0501 - distribution_lambda_26_loss: 0.3939 - distribution_lambda_27_loss: 1.3237 - distribution_lambda_28_loss: 0.3326 - val_loss: 2.3331 - val_distribution_lambda_26_loss: 0.4700 - val_distribution_lambda_27_loss: 1.4430 - val_distribution_lambda_28_loss: 0.4201\n", "Epoch 1079/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0757 - distribution_lambda_26_loss: 0.3905 - distribution_lambda_27_loss: 1.3336 - distribution_lambda_28_loss: 0.3516 - val_loss: 2.3289 - val_distribution_lambda_26_loss: 0.4670 - val_distribution_lambda_27_loss: 1.4428 - val_distribution_lambda_28_loss: 0.4191\n", "Epoch 1080/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0914 - distribution_lambda_26_loss: 0.4103 - distribution_lambda_27_loss: 1.3280 - distribution_lambda_28_loss: 0.3530 - val_loss: 2.3274 - val_distribution_lambda_26_loss: 0.4667 - val_distribution_lambda_27_loss: 1.4420 - val_distribution_lambda_28_loss: 0.4187\n", "Epoch 1081/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.0613 - distribution_lambda_26_loss: 0.3851 - distribution_lambda_27_loss: 1.3230 - distribution_lambda_28_loss: 0.3532 - val_loss: 2.3358 - val_distribution_lambda_26_loss: 0.4749 - val_distribution_lambda_27_loss: 1.4422 - val_distribution_lambda_28_loss: 0.4187\n", "Epoch 1082/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0656 - distribution_lambda_26_loss: 0.3845 - distribution_lambda_27_loss: 1.3288 - distribution_lambda_28_loss: 0.3523 - val_loss: 2.3296 - val_distribution_lambda_26_loss: 0.4683 - val_distribution_lambda_27_loss: 1.4429 - val_distribution_lambda_28_loss: 0.4184\n", "Epoch 1083/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.1085 - distribution_lambda_26_loss: 0.3996 - distribution_lambda_27_loss: 1.3439 - distribution_lambda_28_loss: 0.3649 - val_loss: 2.3275 - val_distribution_lambda_26_loss: 0.4659 - val_distribution_lambda_27_loss: 1.4427 - val_distribution_lambda_28_loss: 0.4189\n", "Epoch 1084/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 2.0858 - distribution_lambda_26_loss: 0.4106 - distribution_lambda_27_loss: 1.3262 - distribution_lambda_28_loss: 0.3490 - val_loss: 2.3226 - val_distribution_lambda_26_loss: 0.4613 - val_distribution_lambda_27_loss: 1.4410 - val_distribution_lambda_28_loss: 0.4203\n", "Epoch 1085/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0997 - distribution_lambda_26_loss: 0.4204 - distribution_lambda_27_loss: 1.3256 - distribution_lambda_28_loss: 0.3537 - val_loss: 2.3199 - val_distribution_lambda_26_loss: 0.4628 - val_distribution_lambda_27_loss: 1.4383 - val_distribution_lambda_28_loss: 0.4188\n", "Epoch 1086/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0785 - distribution_lambda_26_loss: 0.3974 - distribution_lambda_27_loss: 1.3268 - distribution_lambda_28_loss: 0.3543 - val_loss: 2.3219 - val_distribution_lambda_26_loss: 0.4637 - val_distribution_lambda_27_loss: 1.4393 - val_distribution_lambda_28_loss: 0.4188\n", "Epoch 1087/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0619 - distribution_lambda_26_loss: 0.3861 - distribution_lambda_27_loss: 1.3287 - distribution_lambda_28_loss: 0.3472 - val_loss: 2.3205 - val_distribution_lambda_26_loss: 0.4614 - val_distribution_lambda_27_loss: 1.4395 - val_distribution_lambda_28_loss: 0.4197\n", "Epoch 1088/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.0878 - distribution_lambda_26_loss: 0.3973 - distribution_lambda_27_loss: 1.3289 - distribution_lambda_28_loss: 0.3617 - val_loss: 2.3172 - val_distribution_lambda_26_loss: 0.4594 - val_distribution_lambda_27_loss: 1.4385 - val_distribution_lambda_28_loss: 0.4193\n", "Epoch 1089/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.0503 - distribution_lambda_26_loss: 0.3972 - distribution_lambda_27_loss: 1.3093 - distribution_lambda_28_loss: 0.3438 - val_loss: 2.3237 - val_distribution_lambda_26_loss: 0.4651 - val_distribution_lambda_27_loss: 1.4391 - val_distribution_lambda_28_loss: 0.4195\n", "Epoch 1090/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.0897 - distribution_lambda_26_loss: 0.3887 - distribution_lambda_27_loss: 1.3404 - distribution_lambda_28_loss: 0.3606 - val_loss: 2.3263 - val_distribution_lambda_26_loss: 0.4679 - val_distribution_lambda_27_loss: 1.4410 - val_distribution_lambda_28_loss: 0.4174\n", "Epoch 1091/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.0738 - distribution_lambda_26_loss: 0.3881 - distribution_lambda_27_loss: 1.3259 - distribution_lambda_28_loss: 0.3598 - val_loss: 2.3139 - val_distribution_lambda_26_loss: 0.4593 - val_distribution_lambda_27_loss: 1.4387 - val_distribution_lambda_28_loss: 0.4159\n", "Epoch 1092/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0452 - distribution_lambda_26_loss: 0.3765 - distribution_lambda_27_loss: 1.3305 - distribution_lambda_28_loss: 0.3382 - val_loss: 2.3158 - val_distribution_lambda_26_loss: 0.4622 - val_distribution_lambda_27_loss: 1.4381 - val_distribution_lambda_28_loss: 0.4155\n", "Epoch 1093/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0547 - distribution_lambda_26_loss: 0.3721 - distribution_lambda_27_loss: 1.3272 - distribution_lambda_28_loss: 0.3554 - val_loss: 2.3135 - val_distribution_lambda_26_loss: 0.4599 - val_distribution_lambda_27_loss: 1.4385 - val_distribution_lambda_28_loss: 0.4151\n", "Epoch 1094/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0721 - distribution_lambda_26_loss: 0.3936 - distribution_lambda_27_loss: 1.3262 - distribution_lambda_28_loss: 0.3523 - val_loss: 2.3120 - val_distribution_lambda_26_loss: 0.4612 - val_distribution_lambda_27_loss: 1.4358 - val_distribution_lambda_28_loss: 0.4151\n", "Epoch 1095/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.0661 - distribution_lambda_26_loss: 0.3870 - distribution_lambda_27_loss: 1.3211 - distribution_lambda_28_loss: 0.3581 - val_loss: 2.2983 - val_distribution_lambda_26_loss: 0.4513 - val_distribution_lambda_27_loss: 1.4335 - val_distribution_lambda_28_loss: 0.4135\n", "Epoch 1096/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.0698 - distribution_lambda_26_loss: 0.4038 - distribution_lambda_27_loss: 1.3188 - distribution_lambda_28_loss: 0.3472 - val_loss: 2.2991 - val_distribution_lambda_26_loss: 0.4517 - val_distribution_lambda_27_loss: 1.4348 - val_distribution_lambda_28_loss: 0.4127\n", "Epoch 1097/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0809 - distribution_lambda_26_loss: 0.3900 - distribution_lambda_27_loss: 1.3326 - distribution_lambda_28_loss: 0.3584 - val_loss: 2.3041 - val_distribution_lambda_26_loss: 0.4558 - val_distribution_lambda_27_loss: 1.4359 - val_distribution_lambda_28_loss: 0.4123\n", "Epoch 1098/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.0742 - distribution_lambda_26_loss: 0.3766 - distribution_lambda_27_loss: 1.3353 - distribution_lambda_28_loss: 0.3623 - val_loss: 2.2954 - val_distribution_lambda_26_loss: 0.4514 - val_distribution_lambda_27_loss: 1.4330 - val_distribution_lambda_28_loss: 0.4111\n", "Epoch 1099/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0206 - distribution_lambda_26_loss: 0.3824 - distribution_lambda_27_loss: 1.3024 - distribution_lambda_28_loss: 0.3358 - val_loss: 2.2909 - val_distribution_lambda_26_loss: 0.4498 - val_distribution_lambda_27_loss: 1.4320 - val_distribution_lambda_28_loss: 0.4091\n", "Epoch 1100/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0373 - distribution_lambda_26_loss: 0.3804 - distribution_lambda_27_loss: 1.3197 - distribution_lambda_28_loss: 0.3372 - val_loss: 2.2958 - val_distribution_lambda_26_loss: 0.4530 - val_distribution_lambda_27_loss: 1.4329 - val_distribution_lambda_28_loss: 0.4099\n", "Epoch 1101/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0206 - distribution_lambda_26_loss: 0.3689 - distribution_lambda_27_loss: 1.3092 - distribution_lambda_28_loss: 0.3425 - val_loss: 2.2935 - val_distribution_lambda_26_loss: 0.4550 - val_distribution_lambda_27_loss: 1.4299 - val_distribution_lambda_28_loss: 0.4086\n", "Epoch 1102/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0348 - distribution_lambda_26_loss: 0.3748 - distribution_lambda_27_loss: 1.3170 - distribution_lambda_28_loss: 0.3430 - val_loss: 2.2928 - val_distribution_lambda_26_loss: 0.4548 - val_distribution_lambda_27_loss: 1.4313 - val_distribution_lambda_28_loss: 0.4067\n", "Epoch 1103/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0420 - distribution_lambda_26_loss: 0.3818 - distribution_lambda_27_loss: 1.3208 - distribution_lambda_28_loss: 0.3393 - val_loss: 2.2908 - val_distribution_lambda_26_loss: 0.4497 - val_distribution_lambda_27_loss: 1.4347 - val_distribution_lambda_28_loss: 0.4064\n", "Epoch 1104/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0389 - distribution_lambda_26_loss: 0.3744 - distribution_lambda_27_loss: 1.3220 - distribution_lambda_28_loss: 0.3426 - val_loss: 2.2825 - val_distribution_lambda_26_loss: 0.4456 - val_distribution_lambda_27_loss: 1.4313 - val_distribution_lambda_28_loss: 0.4056\n", "Epoch 1105/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.0491 - distribution_lambda_26_loss: 0.3700 - distribution_lambda_27_loss: 1.3272 - distribution_lambda_28_loss: 0.3518 - val_loss: 2.2818 - val_distribution_lambda_26_loss: 0.4475 - val_distribution_lambda_27_loss: 1.4285 - val_distribution_lambda_28_loss: 0.4057\n", "Epoch 1106/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0359 - distribution_lambda_26_loss: 0.3647 - distribution_lambda_27_loss: 1.3206 - distribution_lambda_28_loss: 0.3507 - val_loss: 2.2834 - val_distribution_lambda_26_loss: 0.4547 - val_distribution_lambda_27_loss: 1.4241 - val_distribution_lambda_28_loss: 0.4047\n", "Epoch 1107/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0449 - distribution_lambda_26_loss: 0.3777 - distribution_lambda_27_loss: 1.3220 - distribution_lambda_28_loss: 0.3451 - val_loss: 2.2783 - val_distribution_lambda_26_loss: 0.4543 - val_distribution_lambda_27_loss: 1.4198 - val_distribution_lambda_28_loss: 0.4041\n", "Epoch 1108/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.0271 - distribution_lambda_26_loss: 0.3645 - distribution_lambda_27_loss: 1.3189 - distribution_lambda_28_loss: 0.3438 - val_loss: 2.2737 - val_distribution_lambda_26_loss: 0.4449 - val_distribution_lambda_27_loss: 1.4240 - val_distribution_lambda_28_loss: 0.4048\n", "Epoch 1109/2500\n", "8/8 [==============================] - 0s 8ms/step - loss: 2.0270 - distribution_lambda_26_loss: 0.3745 - distribution_lambda_27_loss: 1.3035 - distribution_lambda_28_loss: 0.3490 - val_loss: 2.2732 - val_distribution_lambda_26_loss: 0.4412 - val_distribution_lambda_27_loss: 1.4274 - val_distribution_lambda_28_loss: 0.4046\n", "Epoch 1110/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.0375 - distribution_lambda_26_loss: 0.3546 - distribution_lambda_27_loss: 1.3309 - distribution_lambda_28_loss: 0.3520 - val_loss: 2.2676 - val_distribution_lambda_26_loss: 0.4406 - val_distribution_lambda_27_loss: 1.4229 - val_distribution_lambda_28_loss: 0.4041\n", "Epoch 1111/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.0088 - distribution_lambda_26_loss: 0.3714 - distribution_lambda_27_loss: 1.2929 - distribution_lambda_28_loss: 0.3445 - val_loss: 2.2691 - val_distribution_lambda_26_loss: 0.4458 - val_distribution_lambda_27_loss: 1.4199 - val_distribution_lambda_28_loss: 0.4034\n", "Epoch 1112/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0096 - distribution_lambda_26_loss: 0.3685 - distribution_lambda_27_loss: 1.3069 - distribution_lambda_28_loss: 0.3342 - val_loss: 2.2613 - val_distribution_lambda_26_loss: 0.4407 - val_distribution_lambda_27_loss: 1.4176 - val_distribution_lambda_28_loss: 0.4030\n", "Epoch 1113/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0289 - distribution_lambda_26_loss: 0.3608 - distribution_lambda_27_loss: 1.3138 - distribution_lambda_28_loss: 0.3543 - val_loss: 2.2535 - val_distribution_lambda_26_loss: 0.4366 - val_distribution_lambda_27_loss: 1.4150 - val_distribution_lambda_28_loss: 0.4019\n", "Epoch 1114/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.0380 - distribution_lambda_26_loss: 0.3833 - distribution_lambda_27_loss: 1.3105 - distribution_lambda_28_loss: 0.3443 - val_loss: 2.2485 - val_distribution_lambda_26_loss: 0.4338 - val_distribution_lambda_27_loss: 1.4139 - val_distribution_lambda_28_loss: 0.4008\n", "Epoch 1115/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.0182 - distribution_lambda_26_loss: 0.3669 - distribution_lambda_27_loss: 1.3052 - distribution_lambda_28_loss: 0.3461 - val_loss: 2.2592 - val_distribution_lambda_26_loss: 0.4422 - val_distribution_lambda_27_loss: 1.4161 - val_distribution_lambda_28_loss: 0.4009\n", "Epoch 1116/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.0634 - distribution_lambda_26_loss: 0.3818 - distribution_lambda_27_loss: 1.3314 - distribution_lambda_28_loss: 0.3502 - val_loss: 2.2650 - val_distribution_lambda_26_loss: 0.4450 - val_distribution_lambda_27_loss: 1.4184 - val_distribution_lambda_28_loss: 0.4016\n", "Epoch 1117/2500\n", "8/8 [==============================] - 0s 8ms/step - loss: 2.0373 - distribution_lambda_26_loss: 0.3607 - distribution_lambda_27_loss: 1.3185 - distribution_lambda_28_loss: 0.3581 - val_loss: 2.2542 - val_distribution_lambda_26_loss: 0.4411 - val_distribution_lambda_27_loss: 1.4154 - val_distribution_lambda_28_loss: 0.3977\n", "Epoch 1118/2500\n", "8/8 [==============================] - 0s 9ms/step - loss: 2.0434 - distribution_lambda_26_loss: 0.3773 - distribution_lambda_27_loss: 1.3149 - distribution_lambda_28_loss: 0.3513 - val_loss: 2.2467 - val_distribution_lambda_26_loss: 0.4369 - val_distribution_lambda_27_loss: 1.4121 - val_distribution_lambda_28_loss: 0.3978\n", "Epoch 1119/2500\n", "8/8 [==============================] - 0s 11ms/step - loss: 2.0718 - distribution_lambda_26_loss: 0.3833 - distribution_lambda_27_loss: 1.3267 - distribution_lambda_28_loss: 0.3618 - val_loss: 2.2441 - val_distribution_lambda_26_loss: 0.4349 - val_distribution_lambda_27_loss: 1.4120 - val_distribution_lambda_28_loss: 0.3971\n", "Epoch 1120/2500\n", "8/8 [==============================] - 0s 8ms/step - loss: 2.0550 - distribution_lambda_26_loss: 0.3675 - distribution_lambda_27_loss: 1.3276 - distribution_lambda_28_loss: 0.3600 - val_loss: 2.2535 - val_distribution_lambda_26_loss: 0.4424 - val_distribution_lambda_27_loss: 1.4138 - val_distribution_lambda_28_loss: 0.3973\n", "Epoch 1121/2500\n", "8/8 [==============================] - 0s 8ms/step - loss: 2.0543 - distribution_lambda_26_loss: 0.3869 - distribution_lambda_27_loss: 1.3230 - distribution_lambda_28_loss: 0.3444 - val_loss: 2.2439 - val_distribution_lambda_26_loss: 0.4370 - val_distribution_lambda_27_loss: 1.4106 - val_distribution_lambda_28_loss: 0.3964\n", "Epoch 1122/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0133 - distribution_lambda_26_loss: 0.3621 - distribution_lambda_27_loss: 1.3130 - distribution_lambda_28_loss: 0.3382 - val_loss: 2.2535 - val_distribution_lambda_26_loss: 0.4435 - val_distribution_lambda_27_loss: 1.4137 - val_distribution_lambda_28_loss: 0.3963\n", "Epoch 1123/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.0452 - distribution_lambda_26_loss: 0.3666 - distribution_lambda_27_loss: 1.3294 - distribution_lambda_28_loss: 0.3492 - val_loss: 2.2406 - val_distribution_lambda_26_loss: 0.4366 - val_distribution_lambda_27_loss: 1.4071 - val_distribution_lambda_28_loss: 0.3970\n", "Epoch 1124/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.0002 - distribution_lambda_26_loss: 0.3748 - distribution_lambda_27_loss: 1.2993 - distribution_lambda_28_loss: 0.3261 - val_loss: 2.2399 - val_distribution_lambda_26_loss: 0.4369 - val_distribution_lambda_27_loss: 1.4063 - val_distribution_lambda_28_loss: 0.3967\n", "Epoch 1125/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.0036 - distribution_lambda_26_loss: 0.3642 - distribution_lambda_27_loss: 1.2953 - distribution_lambda_28_loss: 0.3442 - val_loss: 2.2363 - val_distribution_lambda_26_loss: 0.4341 - val_distribution_lambda_27_loss: 1.4063 - val_distribution_lambda_28_loss: 0.3959\n", "Epoch 1126/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.0200 - distribution_lambda_26_loss: 0.3626 - distribution_lambda_27_loss: 1.3139 - distribution_lambda_28_loss: 0.3435 - val_loss: 2.2399 - val_distribution_lambda_26_loss: 0.4339 - val_distribution_lambda_27_loss: 1.4100 - val_distribution_lambda_28_loss: 0.3960\n", "Epoch 1127/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0052 - distribution_lambda_26_loss: 0.3557 - distribution_lambda_27_loss: 1.3030 - distribution_lambda_28_loss: 0.3466 - val_loss: 2.2304 - val_distribution_lambda_26_loss: 0.4297 - val_distribution_lambda_27_loss: 1.4067 - val_distribution_lambda_28_loss: 0.3940\n", "Epoch 1128/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9779 - distribution_lambda_26_loss: 0.3486 - distribution_lambda_27_loss: 1.2913 - distribution_lambda_28_loss: 0.3380 - val_loss: 2.2309 - val_distribution_lambda_26_loss: 0.4341 - val_distribution_lambda_27_loss: 1.4041 - val_distribution_lambda_28_loss: 0.3927\n", "Epoch 1129/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 2.0069 - distribution_lambda_26_loss: 0.3434 - distribution_lambda_27_loss: 1.3217 - distribution_lambda_28_loss: 0.3418 - val_loss: 2.2149 - val_distribution_lambda_26_loss: 0.4252 - val_distribution_lambda_27_loss: 1.3992 - val_distribution_lambda_28_loss: 0.3905\n", "Epoch 1130/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9575 - distribution_lambda_26_loss: 0.3411 - distribution_lambda_27_loss: 1.2909 - distribution_lambda_28_loss: 0.3256 - val_loss: 2.2163 - val_distribution_lambda_26_loss: 0.4297 - val_distribution_lambda_27_loss: 1.3981 - val_distribution_lambda_28_loss: 0.3885\n", "Epoch 1131/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.0435 - distribution_lambda_26_loss: 0.3680 - distribution_lambda_27_loss: 1.3216 - distribution_lambda_28_loss: 0.3540 - val_loss: 2.2160 - val_distribution_lambda_26_loss: 0.4323 - val_distribution_lambda_27_loss: 1.3968 - val_distribution_lambda_28_loss: 0.3870\n", "Epoch 1132/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9818 - distribution_lambda_26_loss: 0.3677 - distribution_lambda_27_loss: 1.2827 - distribution_lambda_28_loss: 0.3315 - val_loss: 2.2208 - val_distribution_lambda_26_loss: 0.4381 - val_distribution_lambda_27_loss: 1.3955 - val_distribution_lambda_28_loss: 0.3872\n", "Epoch 1133/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9791 - distribution_lambda_26_loss: 0.3455 - distribution_lambda_27_loss: 1.2952 - distribution_lambda_28_loss: 0.3383 - val_loss: 2.2113 - val_distribution_lambda_26_loss: 0.4323 - val_distribution_lambda_27_loss: 1.3936 - val_distribution_lambda_28_loss: 0.3854\n", "Epoch 1134/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9609 - distribution_lambda_26_loss: 0.3586 - distribution_lambda_27_loss: 1.2891 - distribution_lambda_28_loss: 0.3132 - val_loss: 2.2135 - val_distribution_lambda_26_loss: 0.4328 - val_distribution_lambda_27_loss: 1.3962 - val_distribution_lambda_28_loss: 0.3844\n", "Epoch 1135/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0084 - distribution_lambda_26_loss: 0.3753 - distribution_lambda_27_loss: 1.3047 - distribution_lambda_28_loss: 0.3284 - val_loss: 2.2195 - val_distribution_lambda_26_loss: 0.4377 - val_distribution_lambda_27_loss: 1.3978 - val_distribution_lambda_28_loss: 0.3840\n", "Epoch 1136/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9646 - distribution_lambda_26_loss: 0.3468 - distribution_lambda_27_loss: 1.2802 - distribution_lambda_28_loss: 0.3376 - val_loss: 2.2159 - val_distribution_lambda_26_loss: 0.4367 - val_distribution_lambda_27_loss: 1.3962 - val_distribution_lambda_28_loss: 0.3829\n", "Epoch 1137/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.9645 - distribution_lambda_26_loss: 0.3369 - distribution_lambda_27_loss: 1.2921 - distribution_lambda_28_loss: 0.3355 - val_loss: 2.2105 - val_distribution_lambda_26_loss: 0.4308 - val_distribution_lambda_27_loss: 1.3978 - val_distribution_lambda_28_loss: 0.3819\n", "Epoch 1138/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.9971 - distribution_lambda_26_loss: 0.3676 - distribution_lambda_27_loss: 1.2979 - distribution_lambda_28_loss: 0.3316 - val_loss: 2.2106 - val_distribution_lambda_26_loss: 0.4265 - val_distribution_lambda_27_loss: 1.4009 - val_distribution_lambda_28_loss: 0.3832\n", "Epoch 1139/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0234 - distribution_lambda_26_loss: 0.3694 - distribution_lambda_27_loss: 1.3135 - distribution_lambda_28_loss: 0.3406 - val_loss: 2.1997 - val_distribution_lambda_26_loss: 0.4215 - val_distribution_lambda_27_loss: 1.3959 - val_distribution_lambda_28_loss: 0.3824\n", "Epoch 1140/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0068 - distribution_lambda_26_loss: 0.3553 - distribution_lambda_27_loss: 1.3013 - distribution_lambda_28_loss: 0.3502 - val_loss: 2.2071 - val_distribution_lambda_26_loss: 0.4317 - val_distribution_lambda_27_loss: 1.3933 - val_distribution_lambda_28_loss: 0.3821\n", "Epoch 1141/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 2.0014 - distribution_lambda_26_loss: 0.3677 - distribution_lambda_27_loss: 1.2925 - distribution_lambda_28_loss: 0.3412 - val_loss: 2.2096 - val_distribution_lambda_26_loss: 0.4328 - val_distribution_lambda_27_loss: 1.3944 - val_distribution_lambda_28_loss: 0.3825\n", "Epoch 1142/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9617 - distribution_lambda_26_loss: 0.3498 - distribution_lambda_27_loss: 1.2875 - distribution_lambda_28_loss: 0.3244 - val_loss: 2.1914 - val_distribution_lambda_26_loss: 0.4175 - val_distribution_lambda_27_loss: 1.3918 - val_distribution_lambda_28_loss: 0.3821\n", "Epoch 1143/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9928 - distribution_lambda_26_loss: 0.3690 - distribution_lambda_27_loss: 1.2955 - distribution_lambda_28_loss: 0.3284 - val_loss: 2.1940 - val_distribution_lambda_26_loss: 0.4199 - val_distribution_lambda_27_loss: 1.3926 - val_distribution_lambda_28_loss: 0.3815\n", "Epoch 1144/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9687 - distribution_lambda_26_loss: 0.3443 - distribution_lambda_27_loss: 1.2902 - distribution_lambda_28_loss: 0.3342 - val_loss: 2.1954 - val_distribution_lambda_26_loss: 0.4242 - val_distribution_lambda_27_loss: 1.3914 - val_distribution_lambda_28_loss: 0.3799\n", "Epoch 1145/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 2.0058 - distribution_lambda_26_loss: 0.3700 - distribution_lambda_27_loss: 1.2938 - distribution_lambda_28_loss: 0.3420 - val_loss: 2.2059 - val_distribution_lambda_26_loss: 0.4350 - val_distribution_lambda_27_loss: 1.3901 - val_distribution_lambda_28_loss: 0.3808\n", "Epoch 1146/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.9693 - distribution_lambda_26_loss: 0.3514 - distribution_lambda_27_loss: 1.2807 - distribution_lambda_28_loss: 0.3371 - val_loss: 2.1941 - val_distribution_lambda_26_loss: 0.4304 - val_distribution_lambda_27_loss: 1.3840 - val_distribution_lambda_28_loss: 0.3797\n", "Epoch 1147/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9745 - distribution_lambda_26_loss: 0.3547 - distribution_lambda_27_loss: 1.2921 - distribution_lambda_28_loss: 0.3277 - val_loss: 2.1924 - val_distribution_lambda_26_loss: 0.4263 - val_distribution_lambda_27_loss: 1.3859 - val_distribution_lambda_28_loss: 0.3801\n", "Epoch 1148/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9676 - distribution_lambda_26_loss: 0.3622 - distribution_lambda_27_loss: 1.2806 - distribution_lambda_28_loss: 0.3248 - val_loss: 2.1871 - val_distribution_lambda_26_loss: 0.4210 - val_distribution_lambda_27_loss: 1.3871 - val_distribution_lambda_28_loss: 0.3790\n", "Epoch 1149/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9725 - distribution_lambda_26_loss: 0.3579 - distribution_lambda_27_loss: 1.2811 - distribution_lambda_28_loss: 0.3335 - val_loss: 2.1995 - val_distribution_lambda_26_loss: 0.4257 - val_distribution_lambda_27_loss: 1.3926 - val_distribution_lambda_28_loss: 0.3813\n", "Epoch 1150/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9421 - distribution_lambda_26_loss: 0.3297 - distribution_lambda_27_loss: 1.2880 - distribution_lambda_28_loss: 0.3244 - val_loss: 2.2089 - val_distribution_lambda_26_loss: 0.4335 - val_distribution_lambda_27_loss: 1.3920 - val_distribution_lambda_28_loss: 0.3835\n", "Epoch 1151/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9782 - distribution_lambda_26_loss: 0.3447 - distribution_lambda_27_loss: 1.3003 - distribution_lambda_28_loss: 0.3332 - val_loss: 2.1908 - val_distribution_lambda_26_loss: 0.4198 - val_distribution_lambda_27_loss: 1.3890 - val_distribution_lambda_28_loss: 0.3820\n", "Epoch 1152/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9529 - distribution_lambda_26_loss: 0.3411 - distribution_lambda_27_loss: 1.2871 - distribution_lambda_28_loss: 0.3247 - val_loss: 2.1901 - val_distribution_lambda_26_loss: 0.4230 - val_distribution_lambda_27_loss: 1.3876 - val_distribution_lambda_28_loss: 0.3795\n", "Epoch 1153/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 7ms/step - loss: 1.9601 - distribution_lambda_26_loss: 0.3456 - distribution_lambda_27_loss: 1.2888 - distribution_lambda_28_loss: 0.3257 - val_loss: 2.1824 - val_distribution_lambda_26_loss: 0.4183 - val_distribution_lambda_27_loss: 1.3853 - val_distribution_lambda_28_loss: 0.3789\n", "Epoch 1154/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9572 - distribution_lambda_26_loss: 0.3354 - distribution_lambda_27_loss: 1.2887 - distribution_lambda_28_loss: 0.3331 - val_loss: 2.1751 - val_distribution_lambda_26_loss: 0.4149 - val_distribution_lambda_27_loss: 1.3824 - val_distribution_lambda_28_loss: 0.3778\n", "Epoch 1155/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9430 - distribution_lambda_26_loss: 0.3316 - distribution_lambda_27_loss: 1.2910 - distribution_lambda_28_loss: 0.3204 - val_loss: 2.1840 - val_distribution_lambda_26_loss: 0.4287 - val_distribution_lambda_27_loss: 1.3791 - val_distribution_lambda_28_loss: 0.3763\n", "Epoch 1156/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9916 - distribution_lambda_26_loss: 0.3642 - distribution_lambda_27_loss: 1.3010 - distribution_lambda_28_loss: 0.3264 - val_loss: 2.1620 - val_distribution_lambda_26_loss: 0.4152 - val_distribution_lambda_27_loss: 1.3739 - val_distribution_lambda_28_loss: 0.3729\n", "Epoch 1157/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9569 - distribution_lambda_26_loss: 0.3478 - distribution_lambda_27_loss: 1.2875 - distribution_lambda_28_loss: 0.3215 - val_loss: 2.1699 - val_distribution_lambda_26_loss: 0.4211 - val_distribution_lambda_27_loss: 1.3762 - val_distribution_lambda_28_loss: 0.3726\n", "Epoch 1158/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9649 - distribution_lambda_26_loss: 0.3556 - distribution_lambda_27_loss: 1.2821 - distribution_lambda_28_loss: 0.3272 - val_loss: 2.1688 - val_distribution_lambda_26_loss: 0.4207 - val_distribution_lambda_27_loss: 1.3781 - val_distribution_lambda_28_loss: 0.3701\n", "Epoch 1159/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.9683 - distribution_lambda_26_loss: 0.3584 - distribution_lambda_27_loss: 1.2851 - distribution_lambda_28_loss: 0.3248 - val_loss: 2.1623 - val_distribution_lambda_26_loss: 0.4165 - val_distribution_lambda_27_loss: 1.3760 - val_distribution_lambda_28_loss: 0.3698\n", "Epoch 1160/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9249 - distribution_lambda_26_loss: 0.3475 - distribution_lambda_27_loss: 1.2628 - distribution_lambda_28_loss: 0.3146 - val_loss: 2.1622 - val_distribution_lambda_26_loss: 0.4166 - val_distribution_lambda_27_loss: 1.3764 - val_distribution_lambda_28_loss: 0.3692\n", "Epoch 1161/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9449 - distribution_lambda_26_loss: 0.3432 - distribution_lambda_27_loss: 1.2787 - distribution_lambda_28_loss: 0.3230 - val_loss: 2.1627 - val_distribution_lambda_26_loss: 0.4189 - val_distribution_lambda_27_loss: 1.3749 - val_distribution_lambda_28_loss: 0.3689\n", "Epoch 1162/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9505 - distribution_lambda_26_loss: 0.3355 - distribution_lambda_27_loss: 1.2919 - distribution_lambda_28_loss: 0.3231 - val_loss: 2.1581 - val_distribution_lambda_26_loss: 0.4219 - val_distribution_lambda_27_loss: 1.3684 - val_distribution_lambda_28_loss: 0.3679\n", "Epoch 1163/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8972 - distribution_lambda_26_loss: 0.3324 - distribution_lambda_27_loss: 1.2578 - distribution_lambda_28_loss: 0.3070 - val_loss: 2.1475 - val_distribution_lambda_26_loss: 0.4151 - val_distribution_lambda_27_loss: 1.3660 - val_distribution_lambda_28_loss: 0.3664\n", "Epoch 1164/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9420 - distribution_lambda_26_loss: 0.3440 - distribution_lambda_27_loss: 1.2750 - distribution_lambda_28_loss: 0.3229 - val_loss: 2.1594 - val_distribution_lambda_26_loss: 0.4227 - val_distribution_lambda_27_loss: 1.3708 - val_distribution_lambda_28_loss: 0.3659\n", "Epoch 1165/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9246 - distribution_lambda_26_loss: 0.3259 - distribution_lambda_27_loss: 1.2736 - distribution_lambda_28_loss: 0.3251 - val_loss: 2.1673 - val_distribution_lambda_26_loss: 0.4266 - val_distribution_lambda_27_loss: 1.3749 - val_distribution_lambda_28_loss: 0.3658\n", "Epoch 1166/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.9895 - distribution_lambda_26_loss: 0.3571 - distribution_lambda_27_loss: 1.2973 - distribution_lambda_28_loss: 0.3351 - val_loss: 2.1784 - val_distribution_lambda_26_loss: 0.4362 - val_distribution_lambda_27_loss: 1.3758 - val_distribution_lambda_28_loss: 0.3665\n", "Epoch 1167/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.9405 - distribution_lambda_26_loss: 0.3450 - distribution_lambda_27_loss: 1.2716 - distribution_lambda_28_loss: 0.3239 - val_loss: 2.1617 - val_distribution_lambda_26_loss: 0.4230 - val_distribution_lambda_27_loss: 1.3713 - val_distribution_lambda_28_loss: 0.3674\n", "Epoch 1168/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9627 - distribution_lambda_26_loss: 0.3666 - distribution_lambda_27_loss: 1.2785 - distribution_lambda_28_loss: 0.3177 - val_loss: 2.1460 - val_distribution_lambda_26_loss: 0.4131 - val_distribution_lambda_27_loss: 1.3684 - val_distribution_lambda_28_loss: 0.3646\n", "Epoch 1169/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9517 - distribution_lambda_26_loss: 0.3501 - distribution_lambda_27_loss: 1.2805 - distribution_lambda_28_loss: 0.3211 - val_loss: 2.1632 - val_distribution_lambda_26_loss: 0.4218 - val_distribution_lambda_27_loss: 1.3746 - val_distribution_lambda_28_loss: 0.3668\n", "Epoch 1170/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9228 - distribution_lambda_26_loss: 0.3272 - distribution_lambda_27_loss: 1.2750 - distribution_lambda_28_loss: 0.3207 - val_loss: 2.1723 - val_distribution_lambda_26_loss: 0.4271 - val_distribution_lambda_27_loss: 1.3757 - val_distribution_lambda_28_loss: 0.3695\n", "Epoch 1171/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9098 - distribution_lambda_26_loss: 0.3295 - distribution_lambda_27_loss: 1.2634 - distribution_lambda_28_loss: 0.3169 - val_loss: 2.1703 - val_distribution_lambda_26_loss: 0.4293 - val_distribution_lambda_27_loss: 1.3740 - val_distribution_lambda_28_loss: 0.3671\n", "Epoch 1172/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9334 - distribution_lambda_26_loss: 0.3394 - distribution_lambda_27_loss: 1.2688 - distribution_lambda_28_loss: 0.3252 - val_loss: 2.1626 - val_distribution_lambda_26_loss: 0.4275 - val_distribution_lambda_27_loss: 1.3705 - val_distribution_lambda_28_loss: 0.3646\n", "Epoch 1173/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9249 - distribution_lambda_26_loss: 0.3307 - distribution_lambda_27_loss: 1.2621 - distribution_lambda_28_loss: 0.3321 - val_loss: 2.1554 - val_distribution_lambda_26_loss: 0.4246 - val_distribution_lambda_27_loss: 1.3681 - val_distribution_lambda_28_loss: 0.3627\n", "Epoch 1174/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9431 - distribution_lambda_26_loss: 0.3240 - distribution_lambda_27_loss: 1.2846 - distribution_lambda_28_loss: 0.3345 - val_loss: 2.1513 - val_distribution_lambda_26_loss: 0.4209 - val_distribution_lambda_27_loss: 1.3671 - val_distribution_lambda_28_loss: 0.3633\n", "Epoch 1175/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9460 - distribution_lambda_26_loss: 0.3376 - distribution_lambda_27_loss: 1.2796 - distribution_lambda_28_loss: 0.3288 - val_loss: 2.1371 - val_distribution_lambda_26_loss: 0.4147 - val_distribution_lambda_27_loss: 1.3605 - val_distribution_lambda_28_loss: 0.3620\n", "Epoch 1176/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9553 - distribution_lambda_26_loss: 0.3349 - distribution_lambda_27_loss: 1.2906 - distribution_lambda_28_loss: 0.3297 - val_loss: 2.1321 - val_distribution_lambda_26_loss: 0.4108 - val_distribution_lambda_27_loss: 1.3596 - val_distribution_lambda_28_loss: 0.3616\n", "Epoch 1177/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 1.9207 - distribution_lambda_26_loss: 0.3311 - distribution_lambda_27_loss: 1.2666 - distribution_lambda_28_loss: 0.3231 - val_loss: 2.1382 - val_distribution_lambda_26_loss: 0.4177 - val_distribution_lambda_27_loss: 1.3602 - val_distribution_lambda_28_loss: 0.3603\n", "Epoch 1178/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9383 - distribution_lambda_26_loss: 0.3512 - distribution_lambda_27_loss: 1.2649 - distribution_lambda_28_loss: 0.3222 - val_loss: 2.1299 - val_distribution_lambda_26_loss: 0.4093 - val_distribution_lambda_27_loss: 1.3607 - val_distribution_lambda_28_loss: 0.3599\n", "Epoch 1179/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9429 - distribution_lambda_26_loss: 0.3262 - distribution_lambda_27_loss: 1.2827 - distribution_lambda_28_loss: 0.3340 - val_loss: 2.1330 - val_distribution_lambda_26_loss: 0.4138 - val_distribution_lambda_27_loss: 1.3603 - val_distribution_lambda_28_loss: 0.3588\n", "Epoch 1180/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9202 - distribution_lambda_26_loss: 0.3423 - distribution_lambda_27_loss: 1.2725 - distribution_lambda_28_loss: 0.3054 - val_loss: 2.1289 - val_distribution_lambda_26_loss: 0.4157 - val_distribution_lambda_27_loss: 1.3568 - val_distribution_lambda_28_loss: 0.3563\n", "Epoch 1181/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9072 - distribution_lambda_26_loss: 0.3279 - distribution_lambda_27_loss: 1.2652 - distribution_lambda_28_loss: 0.3141 - val_loss: 2.1426 - val_distribution_lambda_26_loss: 0.4304 - val_distribution_lambda_27_loss: 1.3579 - val_distribution_lambda_28_loss: 0.3543\n", "Epoch 1182/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9195 - distribution_lambda_26_loss: 0.3291 - distribution_lambda_27_loss: 1.2732 - distribution_lambda_28_loss: 0.3173 - val_loss: 2.1353 - val_distribution_lambda_26_loss: 0.4258 - val_distribution_lambda_27_loss: 1.3565 - val_distribution_lambda_28_loss: 0.3530\n", "Epoch 1183/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9666 - distribution_lambda_26_loss: 0.3377 - distribution_lambda_27_loss: 1.2928 - distribution_lambda_28_loss: 0.3361 - val_loss: 2.1267 - val_distribution_lambda_26_loss: 0.4234 - val_distribution_lambda_27_loss: 1.3523 - val_distribution_lambda_28_loss: 0.3510\n", "Epoch 1184/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9016 - distribution_lambda_26_loss: 0.3436 - distribution_lambda_27_loss: 1.2535 - distribution_lambda_28_loss: 0.3045 - val_loss: 2.1275 - val_distribution_lambda_26_loss: 0.4236 - val_distribution_lambda_27_loss: 1.3527 - val_distribution_lambda_28_loss: 0.3512\n", "Epoch 1185/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9280 - distribution_lambda_26_loss: 0.3380 - distribution_lambda_27_loss: 1.2747 - distribution_lambda_28_loss: 0.3154 - val_loss: 2.1170 - val_distribution_lambda_26_loss: 0.4136 - val_distribution_lambda_27_loss: 1.3521 - val_distribution_lambda_28_loss: 0.3513\n", "Epoch 1186/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9184 - distribution_lambda_26_loss: 0.3264 - distribution_lambda_27_loss: 1.2803 - distribution_lambda_28_loss: 0.3117 - val_loss: 2.1173 - val_distribution_lambda_26_loss: 0.4107 - val_distribution_lambda_27_loss: 1.3524 - val_distribution_lambda_28_loss: 0.3542\n", "Epoch 1187/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8950 - distribution_lambda_26_loss: 0.3322 - distribution_lambda_27_loss: 1.2505 - distribution_lambda_28_loss: 0.3124 - val_loss: 2.1204 - val_distribution_lambda_26_loss: 0.4184 - val_distribution_lambda_27_loss: 1.3495 - val_distribution_lambda_28_loss: 0.3526\n", "Epoch 1188/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9061 - distribution_lambda_26_loss: 0.3184 - distribution_lambda_27_loss: 1.2753 - distribution_lambda_28_loss: 0.3125 - val_loss: 2.1221 - val_distribution_lambda_26_loss: 0.4149 - val_distribution_lambda_27_loss: 1.3546 - val_distribution_lambda_28_loss: 0.3527\n", "Epoch 1189/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9241 - distribution_lambda_26_loss: 0.3224 - distribution_lambda_27_loss: 1.2744 - distribution_lambda_28_loss: 0.3273 - val_loss: 2.1292 - val_distribution_lambda_26_loss: 0.4165 - val_distribution_lambda_27_loss: 1.3592 - val_distribution_lambda_28_loss: 0.3535\n", "Epoch 1190/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9438 - distribution_lambda_26_loss: 0.3305 - distribution_lambda_27_loss: 1.2769 - distribution_lambda_28_loss: 0.3363 - val_loss: 2.1157 - val_distribution_lambda_26_loss: 0.4101 - val_distribution_lambda_27_loss: 1.3556 - val_distribution_lambda_28_loss: 0.3499\n", "Epoch 1191/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9032 - distribution_lambda_26_loss: 0.3279 - distribution_lambda_27_loss: 1.2723 - distribution_lambda_28_loss: 0.3029 - val_loss: 2.1116 - val_distribution_lambda_26_loss: 0.4119 - val_distribution_lambda_27_loss: 1.3517 - val_distribution_lambda_28_loss: 0.3481\n", "Epoch 1192/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9272 - distribution_lambda_26_loss: 0.3478 - distribution_lambda_27_loss: 1.2666 - distribution_lambda_28_loss: 0.3127 - val_loss: 2.1161 - val_distribution_lambda_26_loss: 0.4189 - val_distribution_lambda_27_loss: 1.3486 - val_distribution_lambda_28_loss: 0.3487\n", "Epoch 1193/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9224 - distribution_lambda_26_loss: 0.3498 - distribution_lambda_27_loss: 1.2622 - distribution_lambda_28_loss: 0.3104 - val_loss: 2.1090 - val_distribution_lambda_26_loss: 0.4164 - val_distribution_lambda_27_loss: 1.3464 - val_distribution_lambda_28_loss: 0.3463\n", "Epoch 1194/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8902 - distribution_lambda_26_loss: 0.3176 - distribution_lambda_27_loss: 1.2557 - distribution_lambda_28_loss: 0.3169 - val_loss: 2.0983 - val_distribution_lambda_26_loss: 0.4100 - val_distribution_lambda_27_loss: 1.3454 - val_distribution_lambda_28_loss: 0.3429\n", "Epoch 1195/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9395 - distribution_lambda_26_loss: 0.3506 - distribution_lambda_27_loss: 1.2698 - distribution_lambda_28_loss: 0.3191 - val_loss: 2.1180 - val_distribution_lambda_26_loss: 0.4230 - val_distribution_lambda_27_loss: 1.3499 - val_distribution_lambda_28_loss: 0.3451\n", "Epoch 1196/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9019 - distribution_lambda_26_loss: 0.3382 - distribution_lambda_27_loss: 1.2591 - distribution_lambda_28_loss: 0.3045 - val_loss: 2.1053 - val_distribution_lambda_26_loss: 0.4089 - val_distribution_lambda_27_loss: 1.3492 - val_distribution_lambda_28_loss: 0.3472\n", "Epoch 1197/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8891 - distribution_lambda_26_loss: 0.3180 - distribution_lambda_27_loss: 1.2478 - distribution_lambda_28_loss: 0.3234 - val_loss: 2.1190 - val_distribution_lambda_26_loss: 0.4235 - val_distribution_lambda_27_loss: 1.3490 - val_distribution_lambda_28_loss: 0.3465\n", "Epoch 1198/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8825 - distribution_lambda_26_loss: 0.3357 - distribution_lambda_27_loss: 1.2556 - distribution_lambda_28_loss: 0.2912 - val_loss: 2.1007 - val_distribution_lambda_26_loss: 0.4147 - val_distribution_lambda_27_loss: 1.3442 - val_distribution_lambda_28_loss: 0.3418\n", "Epoch 1199/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8999 - distribution_lambda_26_loss: 0.3318 - distribution_lambda_27_loss: 1.2524 - distribution_lambda_28_loss: 0.3157 - val_loss: 2.0869 - val_distribution_lambda_26_loss: 0.4071 - val_distribution_lambda_27_loss: 1.3401 - val_distribution_lambda_28_loss: 0.3397\n", "Epoch 1200/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9427 - distribution_lambda_26_loss: 0.3279 - distribution_lambda_27_loss: 1.2804 - distribution_lambda_28_loss: 0.3344 - val_loss: 2.1034 - val_distribution_lambda_26_loss: 0.4188 - val_distribution_lambda_27_loss: 1.3400 - val_distribution_lambda_28_loss: 0.3446\n", "Epoch 1201/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 1.9120 - distribution_lambda_26_loss: 0.3248 - distribution_lambda_27_loss: 1.2672 - distribution_lambda_28_loss: 0.3200 - val_loss: 2.0959 - val_distribution_lambda_26_loss: 0.4146 - val_distribution_lambda_27_loss: 1.3373 - val_distribution_lambda_28_loss: 0.3440\n", "Epoch 1202/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.8702 - distribution_lambda_26_loss: 0.3272 - distribution_lambda_27_loss: 1.2456 - distribution_lambda_28_loss: 0.2975 - val_loss: 2.1028 - val_distribution_lambda_26_loss: 0.4219 - val_distribution_lambda_27_loss: 1.3375 - val_distribution_lambda_28_loss: 0.3435\n", "Epoch 1203/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8851 - distribution_lambda_26_loss: 0.3319 - distribution_lambda_27_loss: 1.2500 - distribution_lambda_28_loss: 0.3032 - val_loss: 2.1038 - val_distribution_lambda_26_loss: 0.4253 - val_distribution_lambda_27_loss: 1.3365 - val_distribution_lambda_28_loss: 0.3420\n", "Epoch 1204/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8799 - distribution_lambda_26_loss: 0.3296 - distribution_lambda_27_loss: 1.2531 - distribution_lambda_28_loss: 0.2973 - val_loss: 2.0984 - val_distribution_lambda_26_loss: 0.4267 - val_distribution_lambda_27_loss: 1.3334 - val_distribution_lambda_28_loss: 0.3383\n", "Epoch 1205/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9108 - distribution_lambda_26_loss: 0.3324 - distribution_lambda_27_loss: 1.2535 - distribution_lambda_28_loss: 0.3248 - val_loss: 2.0760 - val_distribution_lambda_26_loss: 0.4032 - val_distribution_lambda_27_loss: 1.3347 - val_distribution_lambda_28_loss: 0.3381\n", "Epoch 1206/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9278 - distribution_lambda_26_loss: 0.3369 - distribution_lambda_27_loss: 1.2716 - distribution_lambda_28_loss: 0.3192 - val_loss: 2.0749 - val_distribution_lambda_26_loss: 0.4089 - val_distribution_lambda_27_loss: 1.3306 - val_distribution_lambda_28_loss: 0.3355\n", "Epoch 1207/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9226 - distribution_lambda_26_loss: 0.3324 - distribution_lambda_27_loss: 1.2628 - distribution_lambda_28_loss: 0.3274 - val_loss: 2.0765 - val_distribution_lambda_26_loss: 0.4082 - val_distribution_lambda_27_loss: 1.3321 - val_distribution_lambda_28_loss: 0.3362\n", "Epoch 1208/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.8793 - distribution_lambda_26_loss: 0.3326 - distribution_lambda_27_loss: 1.2382 - distribution_lambda_28_loss: 0.3085 - val_loss: 2.0953 - val_distribution_lambda_26_loss: 0.4273 - val_distribution_lambda_27_loss: 1.3315 - val_distribution_lambda_28_loss: 0.3364\n", "Epoch 1209/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9060 - distribution_lambda_26_loss: 0.3292 - distribution_lambda_27_loss: 1.2682 - distribution_lambda_28_loss: 0.3086 - val_loss: 2.0955 - val_distribution_lambda_26_loss: 0.4240 - val_distribution_lambda_27_loss: 1.3356 - val_distribution_lambda_28_loss: 0.3359\n", "Epoch 1210/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9024 - distribution_lambda_26_loss: 0.3367 - distribution_lambda_27_loss: 1.2516 - distribution_lambda_28_loss: 0.3141 - val_loss: 2.0975 - val_distribution_lambda_26_loss: 0.4273 - val_distribution_lambda_27_loss: 1.3309 - val_distribution_lambda_28_loss: 0.3393\n", "Epoch 1211/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8730 - distribution_lambda_26_loss: 0.3283 - distribution_lambda_27_loss: 1.2427 - distribution_lambda_28_loss: 0.3019 - val_loss: 2.0813 - val_distribution_lambda_26_loss: 0.4166 - val_distribution_lambda_27_loss: 1.3294 - val_distribution_lambda_28_loss: 0.3353\n", "Epoch 1212/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8636 - distribution_lambda_26_loss: 0.3244 - distribution_lambda_27_loss: 1.2340 - distribution_lambda_28_loss: 0.3052 - val_loss: 2.0831 - val_distribution_lambda_26_loss: 0.4159 - val_distribution_lambda_27_loss: 1.3310 - val_distribution_lambda_28_loss: 0.3361\n", "Epoch 1213/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8674 - distribution_lambda_26_loss: 0.3162 - distribution_lambda_27_loss: 1.2549 - distribution_lambda_28_loss: 0.2963 - val_loss: 2.0799 - val_distribution_lambda_26_loss: 0.4151 - val_distribution_lambda_27_loss: 1.3296 - val_distribution_lambda_28_loss: 0.3353\n", "Epoch 1214/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8446 - distribution_lambda_26_loss: 0.3285 - distribution_lambda_27_loss: 1.2158 - distribution_lambda_28_loss: 0.3003 - val_loss: 2.0881 - val_distribution_lambda_26_loss: 0.4220 - val_distribution_lambda_27_loss: 1.3303 - val_distribution_lambda_28_loss: 0.3358\n", "Epoch 1215/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8966 - distribution_lambda_26_loss: 0.3374 - distribution_lambda_27_loss: 1.2477 - distribution_lambda_28_loss: 0.3115 - val_loss: 2.0782 - val_distribution_lambda_26_loss: 0.4172 - val_distribution_lambda_27_loss: 1.3269 - val_distribution_lambda_28_loss: 0.3341\n", "Epoch 1216/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8091 - distribution_lambda_26_loss: 0.2950 - distribution_lambda_27_loss: 1.2254 - distribution_lambda_28_loss: 0.2887 - val_loss: 2.0718 - val_distribution_lambda_26_loss: 0.4137 - val_distribution_lambda_27_loss: 1.3264 - val_distribution_lambda_28_loss: 0.3317\n", "Epoch 1217/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8917 - distribution_lambda_26_loss: 0.3225 - distribution_lambda_27_loss: 1.2609 - distribution_lambda_28_loss: 0.3083 - val_loss: 2.0772 - val_distribution_lambda_26_loss: 0.4203 - val_distribution_lambda_27_loss: 1.3260 - val_distribution_lambda_28_loss: 0.3310\n", "Epoch 1218/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8634 - distribution_lambda_26_loss: 0.3154 - distribution_lambda_27_loss: 1.2375 - distribution_lambda_28_loss: 0.3105 - val_loss: 2.0781 - val_distribution_lambda_26_loss: 0.4235 - val_distribution_lambda_27_loss: 1.3260 - val_distribution_lambda_28_loss: 0.3286\n", "Epoch 1219/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9059 - distribution_lambda_26_loss: 0.3250 - distribution_lambda_27_loss: 1.2734 - distribution_lambda_28_loss: 0.3075 - val_loss: 2.0858 - val_distribution_lambda_26_loss: 0.4324 - val_distribution_lambda_27_loss: 1.3228 - val_distribution_lambda_28_loss: 0.3306\n", "Epoch 1220/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8586 - distribution_lambda_26_loss: 0.3223 - distribution_lambda_27_loss: 1.2293 - distribution_lambda_28_loss: 0.3070 - val_loss: 2.0634 - val_distribution_lambda_26_loss: 0.4199 - val_distribution_lambda_27_loss: 1.3159 - val_distribution_lambda_28_loss: 0.3277\n", "Epoch 1221/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8576 - distribution_lambda_26_loss: 0.3141 - distribution_lambda_27_loss: 1.2422 - distribution_lambda_28_loss: 0.3013 - val_loss: 2.0492 - val_distribution_lambda_26_loss: 0.4104 - val_distribution_lambda_27_loss: 1.3136 - val_distribution_lambda_28_loss: 0.3252\n", "Epoch 1222/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8787 - distribution_lambda_26_loss: 0.3219 - distribution_lambda_27_loss: 1.2528 - distribution_lambda_28_loss: 0.3041 - val_loss: 2.0624 - val_distribution_lambda_26_loss: 0.4160 - val_distribution_lambda_27_loss: 1.3172 - val_distribution_lambda_28_loss: 0.3292\n", "Epoch 1223/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8581 - distribution_lambda_26_loss: 0.3109 - distribution_lambda_27_loss: 1.2420 - distribution_lambda_28_loss: 0.3053 - val_loss: 2.0597 - val_distribution_lambda_26_loss: 0.4114 - val_distribution_lambda_27_loss: 1.3173 - val_distribution_lambda_28_loss: 0.3310\n", "Epoch 1224/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8560 - distribution_lambda_26_loss: 0.3337 - distribution_lambda_27_loss: 1.2256 - distribution_lambda_28_loss: 0.2967 - val_loss: 2.0637 - val_distribution_lambda_26_loss: 0.4153 - val_distribution_lambda_27_loss: 1.3180 - val_distribution_lambda_28_loss: 0.3303\n", "Epoch 1225/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 1.8865 - distribution_lambda_26_loss: 0.3130 - distribution_lambda_27_loss: 1.2599 - distribution_lambda_28_loss: 0.3136 - val_loss: 2.0592 - val_distribution_lambda_26_loss: 0.4114 - val_distribution_lambda_27_loss: 1.3185 - val_distribution_lambda_28_loss: 0.3293\n", "Epoch 1226/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.9036 - distribution_lambda_26_loss: 0.3256 - distribution_lambda_27_loss: 1.2631 - distribution_lambda_28_loss: 0.3148 - val_loss: 2.0667 - val_distribution_lambda_26_loss: 0.4190 - val_distribution_lambda_27_loss: 1.3193 - val_distribution_lambda_28_loss: 0.3285\n", "Epoch 1227/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8570 - distribution_lambda_26_loss: 0.3100 - distribution_lambda_27_loss: 1.2486 - distribution_lambda_28_loss: 0.2983 - val_loss: 2.0591 - val_distribution_lambda_26_loss: 0.4093 - val_distribution_lambda_27_loss: 1.3188 - val_distribution_lambda_28_loss: 0.3310\n", "Epoch 1228/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8614 - distribution_lambda_26_loss: 0.3116 - distribution_lambda_27_loss: 1.2354 - distribution_lambda_28_loss: 0.3143 - val_loss: 2.0540 - val_distribution_lambda_26_loss: 0.4109 - val_distribution_lambda_27_loss: 1.3148 - val_distribution_lambda_28_loss: 0.3283\n", "Epoch 1229/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8485 - distribution_lambda_26_loss: 0.3141 - distribution_lambda_27_loss: 1.2351 - distribution_lambda_28_loss: 0.2993 - val_loss: 2.0719 - val_distribution_lambda_26_loss: 0.4301 - val_distribution_lambda_27_loss: 1.3138 - val_distribution_lambda_28_loss: 0.3280\n", "Epoch 1230/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8144 - distribution_lambda_26_loss: 0.3136 - distribution_lambda_27_loss: 1.2161 - distribution_lambda_28_loss: 0.2847 - val_loss: 2.0693 - val_distribution_lambda_26_loss: 0.4261 - val_distribution_lambda_27_loss: 1.3152 - val_distribution_lambda_28_loss: 0.3280\n", "Epoch 1231/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8628 - distribution_lambda_26_loss: 0.3315 - distribution_lambda_27_loss: 1.2413 - distribution_lambda_28_loss: 0.2901 - val_loss: 2.0460 - val_distribution_lambda_26_loss: 0.4109 - val_distribution_lambda_27_loss: 1.3111 - val_distribution_lambda_28_loss: 0.3240\n", "Epoch 1232/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8012 - distribution_lambda_26_loss: 0.3153 - distribution_lambda_27_loss: 1.2076 - distribution_lambda_28_loss: 0.2782 - val_loss: 2.0363 - val_distribution_lambda_26_loss: 0.4061 - val_distribution_lambda_27_loss: 1.3092 - val_distribution_lambda_28_loss: 0.3211\n", "Epoch 1233/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8819 - distribution_lambda_26_loss: 0.3358 - distribution_lambda_27_loss: 1.2362 - distribution_lambda_28_loss: 0.3100 - val_loss: 2.0442 - val_distribution_lambda_26_loss: 0.4175 - val_distribution_lambda_27_loss: 1.3063 - val_distribution_lambda_28_loss: 0.3204\n", "Epoch 1234/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7934 - distribution_lambda_26_loss: 0.3040 - distribution_lambda_27_loss: 1.2101 - distribution_lambda_28_loss: 0.2793 - val_loss: 2.0470 - val_distribution_lambda_26_loss: 0.4151 - val_distribution_lambda_27_loss: 1.3098 - val_distribution_lambda_28_loss: 0.3221\n", "Epoch 1235/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8616 - distribution_lambda_26_loss: 0.3099 - distribution_lambda_27_loss: 1.2534 - distribution_lambda_28_loss: 0.2983 - val_loss: 2.0460 - val_distribution_lambda_26_loss: 0.4146 - val_distribution_lambda_27_loss: 1.3070 - val_distribution_lambda_28_loss: 0.3244\n", "Epoch 1236/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8659 - distribution_lambda_26_loss: 0.3239 - distribution_lambda_27_loss: 1.2505 - distribution_lambda_28_loss: 0.2915 - val_loss: 2.0382 - val_distribution_lambda_26_loss: 0.4135 - val_distribution_lambda_27_loss: 1.3030 - val_distribution_lambda_28_loss: 0.3217\n", "Epoch 1237/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 1.8294 - distribution_lambda_26_loss: 0.3261 - distribution_lambda_27_loss: 1.2172 - distribution_lambda_28_loss: 0.2861 - val_loss: 2.0361 - val_distribution_lambda_26_loss: 0.4147 - val_distribution_lambda_27_loss: 1.2997 - val_distribution_lambda_28_loss: 0.3217\n", "Epoch 1238/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 1.8343 - distribution_lambda_26_loss: 0.2969 - distribution_lambda_27_loss: 1.2419 - distribution_lambda_28_loss: 0.2954 - val_loss: 2.0308 - val_distribution_lambda_26_loss: 0.4143 - val_distribution_lambda_27_loss: 1.2985 - val_distribution_lambda_28_loss: 0.3180\n", "Epoch 1239/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8668 - distribution_lambda_26_loss: 0.3152 - distribution_lambda_27_loss: 1.2323 - distribution_lambda_28_loss: 0.3192 - val_loss: 2.0278 - val_distribution_lambda_26_loss: 0.4053 - val_distribution_lambda_27_loss: 1.3009 - val_distribution_lambda_28_loss: 0.3215\n", "Epoch 1240/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8591 - distribution_lambda_26_loss: 0.3132 - distribution_lambda_27_loss: 1.2408 - distribution_lambda_28_loss: 0.3051 - val_loss: 2.0265 - val_distribution_lambda_26_loss: 0.4119 - val_distribution_lambda_27_loss: 1.2972 - val_distribution_lambda_28_loss: 0.3174\n", "Epoch 1241/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.8563 - distribution_lambda_26_loss: 0.3093 - distribution_lambda_27_loss: 1.2508 - distribution_lambda_28_loss: 0.2962 - val_loss: 2.0337 - val_distribution_lambda_26_loss: 0.4161 - val_distribution_lambda_27_loss: 1.2984 - val_distribution_lambda_28_loss: 0.3192\n", "Epoch 1242/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7869 - distribution_lambda_26_loss: 0.2895 - distribution_lambda_27_loss: 1.2191 - distribution_lambda_28_loss: 0.2782 - val_loss: 2.0212 - val_distribution_lambda_26_loss: 0.4086 - val_distribution_lambda_27_loss: 1.2939 - val_distribution_lambda_28_loss: 0.3186\n", "Epoch 1243/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.8404 - distribution_lambda_26_loss: 0.3055 - distribution_lambda_27_loss: 1.2420 - distribution_lambda_28_loss: 0.2929 - val_loss: 2.0333 - val_distribution_lambda_26_loss: 0.4194 - val_distribution_lambda_27_loss: 1.2954 - val_distribution_lambda_28_loss: 0.3185\n", "Epoch 1244/2500\n", "8/8 [==============================] - 0s 9ms/step - loss: 1.8695 - distribution_lambda_26_loss: 0.3338 - distribution_lambda_27_loss: 1.2336 - distribution_lambda_28_loss: 0.3021 - val_loss: 2.0343 - val_distribution_lambda_26_loss: 0.4238 - val_distribution_lambda_27_loss: 1.2927 - val_distribution_lambda_28_loss: 0.3178\n", "Epoch 1245/2500\n", "8/8 [==============================] - 0s 11ms/step - loss: 1.8287 - distribution_lambda_26_loss: 0.3077 - distribution_lambda_27_loss: 1.2352 - distribution_lambda_28_loss: 0.2858 - val_loss: 2.0288 - val_distribution_lambda_26_loss: 0.4148 - val_distribution_lambda_27_loss: 1.2938 - val_distribution_lambda_28_loss: 0.3202\n", "Epoch 1246/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.8382 - distribution_lambda_26_loss: 0.3046 - distribution_lambda_27_loss: 1.2309 - distribution_lambda_28_loss: 0.3027 - val_loss: 2.0265 - val_distribution_lambda_26_loss: 0.4136 - val_distribution_lambda_27_loss: 1.2934 - val_distribution_lambda_28_loss: 0.3195\n", "Epoch 1247/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.8401 - distribution_lambda_26_loss: 0.2991 - distribution_lambda_27_loss: 1.2365 - distribution_lambda_28_loss: 0.3045 - val_loss: 2.0278 - val_distribution_lambda_26_loss: 0.4158 - val_distribution_lambda_27_loss: 1.2899 - val_distribution_lambda_28_loss: 0.3221\n", "Epoch 1248/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.8422 - distribution_lambda_26_loss: 0.3180 - distribution_lambda_27_loss: 1.2334 - distribution_lambda_28_loss: 0.2908 - val_loss: 2.0175 - val_distribution_lambda_26_loss: 0.4050 - val_distribution_lambda_27_loss: 1.2878 - val_distribution_lambda_28_loss: 0.3247\n", "Epoch 1249/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 7ms/step - loss: 1.8479 - distribution_lambda_26_loss: 0.3188 - distribution_lambda_27_loss: 1.2339 - distribution_lambda_28_loss: 0.2952 - val_loss: 2.0206 - val_distribution_lambda_26_loss: 0.4183 - val_distribution_lambda_27_loss: 1.2851 - val_distribution_lambda_28_loss: 0.3172\n", "Epoch 1250/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8554 - distribution_lambda_26_loss: 0.3169 - distribution_lambda_27_loss: 1.2403 - distribution_lambda_28_loss: 0.2982 - val_loss: 2.0224 - val_distribution_lambda_26_loss: 0.4176 - val_distribution_lambda_27_loss: 1.2883 - val_distribution_lambda_28_loss: 0.3166\n", "Epoch 1251/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8327 - distribution_lambda_26_loss: 0.3041 - distribution_lambda_27_loss: 1.2301 - distribution_lambda_28_loss: 0.2985 - val_loss: 2.0228 - val_distribution_lambda_26_loss: 0.4171 - val_distribution_lambda_27_loss: 1.2896 - val_distribution_lambda_28_loss: 0.3161\n", "Epoch 1252/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8173 - distribution_lambda_26_loss: 0.3169 - distribution_lambda_27_loss: 1.2154 - distribution_lambda_28_loss: 0.2850 - val_loss: 2.0230 - val_distribution_lambda_26_loss: 0.4094 - val_distribution_lambda_27_loss: 1.2953 - val_distribution_lambda_28_loss: 0.3184\n", "Epoch 1253/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.8042 - distribution_lambda_26_loss: 0.3170 - distribution_lambda_27_loss: 1.2085 - distribution_lambda_28_loss: 0.2787 - val_loss: 2.0125 - val_distribution_lambda_26_loss: 0.4044 - val_distribution_lambda_27_loss: 1.2930 - val_distribution_lambda_28_loss: 0.3151\n", "Epoch 1254/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8433 - distribution_lambda_26_loss: 0.3020 - distribution_lambda_27_loss: 1.2327 - distribution_lambda_28_loss: 0.3086 - val_loss: 2.0177 - val_distribution_lambda_26_loss: 0.4090 - val_distribution_lambda_27_loss: 1.2918 - val_distribution_lambda_28_loss: 0.3169\n", "Epoch 1255/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8283 - distribution_lambda_26_loss: 0.3036 - distribution_lambda_27_loss: 1.2257 - distribution_lambda_28_loss: 0.2990 - val_loss: 2.0306 - val_distribution_lambda_26_loss: 0.4238 - val_distribution_lambda_27_loss: 1.2899 - val_distribution_lambda_28_loss: 0.3169\n", "Epoch 1256/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.8024 - distribution_lambda_26_loss: 0.3187 - distribution_lambda_27_loss: 1.2108 - distribution_lambda_28_loss: 0.2729 - val_loss: 2.0060 - val_distribution_lambda_26_loss: 0.4104 - val_distribution_lambda_27_loss: 1.2809 - val_distribution_lambda_28_loss: 0.3147\n", "Epoch 1257/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.8029 - distribution_lambda_26_loss: 0.3002 - distribution_lambda_27_loss: 1.2270 - distribution_lambda_28_loss: 0.2757 - val_loss: 2.0067 - val_distribution_lambda_26_loss: 0.4117 - val_distribution_lambda_27_loss: 1.2802 - val_distribution_lambda_28_loss: 0.3149\n", "Epoch 1258/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.7896 - distribution_lambda_26_loss: 0.3109 - distribution_lambda_27_loss: 1.2083 - distribution_lambda_28_loss: 0.2704 - val_loss: 2.0048 - val_distribution_lambda_26_loss: 0.4164 - val_distribution_lambda_27_loss: 1.2769 - val_distribution_lambda_28_loss: 0.3115\n", "Epoch 1259/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.7822 - distribution_lambda_26_loss: 0.3091 - distribution_lambda_27_loss: 1.1963 - distribution_lambda_28_loss: 0.2768 - val_loss: 1.9907 - val_distribution_lambda_26_loss: 0.4063 - val_distribution_lambda_27_loss: 1.2721 - val_distribution_lambda_28_loss: 0.3123\n", "Epoch 1260/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.7922 - distribution_lambda_26_loss: 0.2822 - distribution_lambda_27_loss: 1.2181 - distribution_lambda_28_loss: 0.2919 - val_loss: 1.9935 - val_distribution_lambda_26_loss: 0.4158 - val_distribution_lambda_27_loss: 1.2668 - val_distribution_lambda_28_loss: 0.3109\n", "Epoch 1261/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.7922 - distribution_lambda_26_loss: 0.3018 - distribution_lambda_27_loss: 1.1998 - distribution_lambda_28_loss: 0.2905 - val_loss: 1.9898 - val_distribution_lambda_26_loss: 0.4101 - val_distribution_lambda_27_loss: 1.2683 - val_distribution_lambda_28_loss: 0.3113\n", "Epoch 1262/2500\n", "8/8 [==============================] - 0s 9ms/step - loss: 1.8048 - distribution_lambda_26_loss: 0.2980 - distribution_lambda_27_loss: 1.2233 - distribution_lambda_28_loss: 0.2834 - val_loss: 1.9865 - val_distribution_lambda_26_loss: 0.4038 - val_distribution_lambda_27_loss: 1.2696 - val_distribution_lambda_28_loss: 0.3130\n", "Epoch 1263/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7661 - distribution_lambda_26_loss: 0.2978 - distribution_lambda_27_loss: 1.1859 - distribution_lambda_28_loss: 0.2824 - val_loss: 2.0106 - val_distribution_lambda_26_loss: 0.4162 - val_distribution_lambda_27_loss: 1.2754 - val_distribution_lambda_28_loss: 0.3190\n", "Epoch 1264/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.7723 - distribution_lambda_26_loss: 0.3080 - distribution_lambda_27_loss: 1.1801 - distribution_lambda_28_loss: 0.2843 - val_loss: 2.0154 - val_distribution_lambda_26_loss: 0.4177 - val_distribution_lambda_27_loss: 1.2773 - val_distribution_lambda_28_loss: 0.3204\n", "Epoch 1265/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.7459 - distribution_lambda_26_loss: 0.3012 - distribution_lambda_27_loss: 1.1750 - distribution_lambda_28_loss: 0.2697 - val_loss: 2.0047 - val_distribution_lambda_26_loss: 0.4126 - val_distribution_lambda_27_loss: 1.2748 - val_distribution_lambda_28_loss: 0.3173\n", "Epoch 1266/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.7724 - distribution_lambda_26_loss: 0.2995 - distribution_lambda_27_loss: 1.2059 - distribution_lambda_28_loss: 0.2670 - val_loss: 1.9830 - val_distribution_lambda_26_loss: 0.4029 - val_distribution_lambda_27_loss: 1.2655 - val_distribution_lambda_28_loss: 0.3147\n", "Epoch 1267/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.7833 - distribution_lambda_26_loss: 0.3101 - distribution_lambda_27_loss: 1.2076 - distribution_lambda_28_loss: 0.2655 - val_loss: 1.9888 - val_distribution_lambda_26_loss: 0.4061 - val_distribution_lambda_27_loss: 1.2636 - val_distribution_lambda_28_loss: 0.3190\n", "Epoch 1268/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8066 - distribution_lambda_26_loss: 0.3115 - distribution_lambda_27_loss: 1.2053 - distribution_lambda_28_loss: 0.2898 - val_loss: 1.9932 - val_distribution_lambda_26_loss: 0.4196 - val_distribution_lambda_27_loss: 1.2589 - val_distribution_lambda_28_loss: 0.3147\n", "Epoch 1269/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8186 - distribution_lambda_26_loss: 0.3004 - distribution_lambda_27_loss: 1.2167 - distribution_lambda_28_loss: 0.3015 - val_loss: 1.9728 - val_distribution_lambda_26_loss: 0.4100 - val_distribution_lambda_27_loss: 1.2525 - val_distribution_lambda_28_loss: 0.3104\n", "Epoch 1270/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7870 - distribution_lambda_26_loss: 0.3013 - distribution_lambda_27_loss: 1.2053 - distribution_lambda_28_loss: 0.2805 - val_loss: 1.9662 - val_distribution_lambda_26_loss: 0.4073 - val_distribution_lambda_27_loss: 1.2496 - val_distribution_lambda_28_loss: 0.3093\n", "Epoch 1271/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8132 - distribution_lambda_26_loss: 0.3076 - distribution_lambda_27_loss: 1.2158 - distribution_lambda_28_loss: 0.2899 - val_loss: 1.9635 - val_distribution_lambda_26_loss: 0.4032 - val_distribution_lambda_27_loss: 1.2514 - val_distribution_lambda_28_loss: 0.3090\n", "Epoch 1272/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.8041 - distribution_lambda_26_loss: 0.3264 - distribution_lambda_27_loss: 1.2054 - distribution_lambda_28_loss: 0.2723 - val_loss: 1.9768 - val_distribution_lambda_26_loss: 0.4118 - val_distribution_lambda_27_loss: 1.2549 - val_distribution_lambda_28_loss: 0.3101\n", "Epoch 1273/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 1.7848 - distribution_lambda_26_loss: 0.2953 - distribution_lambda_27_loss: 1.2098 - distribution_lambda_28_loss: 0.2797 - val_loss: 1.9649 - val_distribution_lambda_26_loss: 0.4081 - val_distribution_lambda_27_loss: 1.2500 - val_distribution_lambda_28_loss: 0.3068\n", "Epoch 1274/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7550 - distribution_lambda_26_loss: 0.2991 - distribution_lambda_27_loss: 1.1823 - distribution_lambda_28_loss: 0.2736 - val_loss: 1.9691 - val_distribution_lambda_26_loss: 0.4068 - val_distribution_lambda_27_loss: 1.2554 - val_distribution_lambda_28_loss: 0.3069\n", "Epoch 1275/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8000 - distribution_lambda_26_loss: 0.3145 - distribution_lambda_27_loss: 1.2122 - distribution_lambda_28_loss: 0.2732 - val_loss: 1.9586 - val_distribution_lambda_26_loss: 0.4050 - val_distribution_lambda_27_loss: 1.2515 - val_distribution_lambda_28_loss: 0.3021\n", "Epoch 1276/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7855 - distribution_lambda_26_loss: 0.3158 - distribution_lambda_27_loss: 1.1868 - distribution_lambda_28_loss: 0.2830 - val_loss: 1.9585 - val_distribution_lambda_26_loss: 0.4089 - val_distribution_lambda_27_loss: 1.2452 - val_distribution_lambda_28_loss: 0.3045\n", "Epoch 1277/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8134 - distribution_lambda_26_loss: 0.3003 - distribution_lambda_27_loss: 1.2220 - distribution_lambda_28_loss: 0.2911 - val_loss: 1.9684 - val_distribution_lambda_26_loss: 0.4172 - val_distribution_lambda_27_loss: 1.2458 - val_distribution_lambda_28_loss: 0.3054\n", "Epoch 1278/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8006 - distribution_lambda_26_loss: 0.3079 - distribution_lambda_27_loss: 1.2119 - distribution_lambda_28_loss: 0.2809 - val_loss: 1.9496 - val_distribution_lambda_26_loss: 0.4074 - val_distribution_lambda_27_loss: 1.2404 - val_distribution_lambda_28_loss: 0.3017\n", "Epoch 1279/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7661 - distribution_lambda_26_loss: 0.3096 - distribution_lambda_27_loss: 1.1801 - distribution_lambda_28_loss: 0.2764 - val_loss: 1.9498 - val_distribution_lambda_26_loss: 0.4081 - val_distribution_lambda_27_loss: 1.2386 - val_distribution_lambda_28_loss: 0.3030\n", "Epoch 1280/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7476 - distribution_lambda_26_loss: 0.2865 - distribution_lambda_27_loss: 1.1955 - distribution_lambda_28_loss: 0.2657 - val_loss: 1.9387 - val_distribution_lambda_26_loss: 0.4043 - val_distribution_lambda_27_loss: 1.2329 - val_distribution_lambda_28_loss: 0.3014\n", "Epoch 1281/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8028 - distribution_lambda_26_loss: 0.3094 - distribution_lambda_27_loss: 1.2185 - distribution_lambda_28_loss: 0.2750 - val_loss: 1.9412 - val_distribution_lambda_26_loss: 0.4083 - val_distribution_lambda_27_loss: 1.2322 - val_distribution_lambda_28_loss: 0.3006\n", "Epoch 1282/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.7249 - distribution_lambda_26_loss: 0.2992 - distribution_lambda_27_loss: 1.1741 - distribution_lambda_28_loss: 0.2517 - val_loss: 1.9456 - val_distribution_lambda_26_loss: 0.4102 - val_distribution_lambda_27_loss: 1.2347 - val_distribution_lambda_28_loss: 0.3007\n", "Epoch 1283/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7979 - distribution_lambda_26_loss: 0.2915 - distribution_lambda_27_loss: 1.2242 - distribution_lambda_28_loss: 0.2821 - val_loss: 1.9376 - val_distribution_lambda_26_loss: 0.4067 - val_distribution_lambda_27_loss: 1.2314 - val_distribution_lambda_28_loss: 0.2995\n", "Epoch 1284/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.8278 - distribution_lambda_26_loss: 0.3109 - distribution_lambda_27_loss: 1.2190 - distribution_lambda_28_loss: 0.2979 - val_loss: 1.9475 - val_distribution_lambda_26_loss: 0.4081 - val_distribution_lambda_27_loss: 1.2368 - val_distribution_lambda_28_loss: 0.3025\n", "Epoch 1285/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7912 - distribution_lambda_26_loss: 0.3196 - distribution_lambda_27_loss: 1.1929 - distribution_lambda_28_loss: 0.2786 - val_loss: 1.9677 - val_distribution_lambda_26_loss: 0.4177 - val_distribution_lambda_27_loss: 1.2453 - val_distribution_lambda_28_loss: 0.3047\n", "Epoch 1286/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7797 - distribution_lambda_26_loss: 0.2940 - distribution_lambda_27_loss: 1.2034 - distribution_lambda_28_loss: 0.2823 - val_loss: 1.9459 - val_distribution_lambda_26_loss: 0.4036 - val_distribution_lambda_27_loss: 1.2395 - val_distribution_lambda_28_loss: 0.3027\n", "Epoch 1287/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.7303 - distribution_lambda_26_loss: 0.2826 - distribution_lambda_27_loss: 1.1822 - distribution_lambda_28_loss: 0.2655 - val_loss: 1.9465 - val_distribution_lambda_26_loss: 0.4062 - val_distribution_lambda_27_loss: 1.2374 - val_distribution_lambda_28_loss: 0.3029\n", "Epoch 1288/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7809 - distribution_lambda_26_loss: 0.3162 - distribution_lambda_27_loss: 1.1933 - distribution_lambda_28_loss: 0.2713 - val_loss: 1.9387 - val_distribution_lambda_26_loss: 0.3980 - val_distribution_lambda_27_loss: 1.2388 - val_distribution_lambda_28_loss: 0.3019\n", "Epoch 1289/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7200 - distribution_lambda_26_loss: 0.2972 - distribution_lambda_27_loss: 1.1716 - distribution_lambda_28_loss: 0.2513 - val_loss: 1.9409 - val_distribution_lambda_26_loss: 0.4062 - val_distribution_lambda_27_loss: 1.2359 - val_distribution_lambda_28_loss: 0.2988\n", "Epoch 1290/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.7345 - distribution_lambda_26_loss: 0.2926 - distribution_lambda_27_loss: 1.1764 - distribution_lambda_28_loss: 0.2655 - val_loss: 1.9280 - val_distribution_lambda_26_loss: 0.3967 - val_distribution_lambda_27_loss: 1.2299 - val_distribution_lambda_28_loss: 0.3014\n", "Epoch 1291/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7374 - distribution_lambda_26_loss: 0.2908 - distribution_lambda_27_loss: 1.1825 - distribution_lambda_28_loss: 0.2641 - val_loss: 1.9471 - val_distribution_lambda_26_loss: 0.4120 - val_distribution_lambda_27_loss: 1.2326 - val_distribution_lambda_28_loss: 0.3025\n", "Epoch 1292/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7957 - distribution_lambda_26_loss: 0.2966 - distribution_lambda_27_loss: 1.2184 - distribution_lambda_28_loss: 0.2807 - val_loss: 1.9358 - val_distribution_lambda_26_loss: 0.4097 - val_distribution_lambda_27_loss: 1.2270 - val_distribution_lambda_28_loss: 0.2991\n", "Epoch 1293/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.7714 - distribution_lambda_26_loss: 0.3082 - distribution_lambda_27_loss: 1.1918 - distribution_lambda_28_loss: 0.2714 - val_loss: 1.9305 - val_distribution_lambda_26_loss: 0.4026 - val_distribution_lambda_27_loss: 1.2281 - val_distribution_lambda_28_loss: 0.2998\n", "Epoch 1294/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7490 - distribution_lambda_26_loss: 0.3019 - distribution_lambda_27_loss: 1.1693 - distribution_lambda_28_loss: 0.2778 - val_loss: 1.9338 - val_distribution_lambda_26_loss: 0.4094 - val_distribution_lambda_27_loss: 1.2236 - val_distribution_lambda_28_loss: 0.3008\n", "Epoch 1295/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7738 - distribution_lambda_26_loss: 0.3006 - distribution_lambda_27_loss: 1.1928 - distribution_lambda_28_loss: 0.2804 - val_loss: 1.9475 - val_distribution_lambda_26_loss: 0.4221 - val_distribution_lambda_27_loss: 1.2240 - val_distribution_lambda_28_loss: 0.3014\n", "Epoch 1296/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7697 - distribution_lambda_26_loss: 0.3088 - distribution_lambda_27_loss: 1.1976 - distribution_lambda_28_loss: 0.2633 - val_loss: 1.9327 - val_distribution_lambda_26_loss: 0.4084 - val_distribution_lambda_27_loss: 1.2227 - val_distribution_lambda_28_loss: 0.3016\n", "Epoch 1297/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 1.7682 - distribution_lambda_26_loss: 0.3077 - distribution_lambda_27_loss: 1.1963 - distribution_lambda_28_loss: 0.2643 - val_loss: 1.9197 - val_distribution_lambda_26_loss: 0.3982 - val_distribution_lambda_27_loss: 1.2210 - val_distribution_lambda_28_loss: 0.3005\n", "Epoch 1298/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7816 - distribution_lambda_26_loss: 0.2947 - distribution_lambda_27_loss: 1.1983 - distribution_lambda_28_loss: 0.2886 - val_loss: 1.9235 - val_distribution_lambda_26_loss: 0.4071 - val_distribution_lambda_27_loss: 1.2185 - val_distribution_lambda_28_loss: 0.2979\n", "Epoch 1299/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7676 - distribution_lambda_26_loss: 0.3036 - distribution_lambda_27_loss: 1.1869 - distribution_lambda_28_loss: 0.2770 - val_loss: 1.9224 - val_distribution_lambda_26_loss: 0.4064 - val_distribution_lambda_27_loss: 1.2176 - val_distribution_lambda_28_loss: 0.2985\n", "Epoch 1300/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7695 - distribution_lambda_26_loss: 0.3185 - distribution_lambda_27_loss: 1.1918 - distribution_lambda_28_loss: 0.2591 - val_loss: 1.9181 - val_distribution_lambda_26_loss: 0.4000 - val_distribution_lambda_27_loss: 1.2198 - val_distribution_lambda_28_loss: 0.2983\n", "Epoch 1301/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7982 - distribution_lambda_26_loss: 0.3145 - distribution_lambda_27_loss: 1.2027 - distribution_lambda_28_loss: 0.2810 - val_loss: 1.9301 - val_distribution_lambda_26_loss: 0.4100 - val_distribution_lambda_27_loss: 1.2190 - val_distribution_lambda_28_loss: 0.3011\n", "Epoch 1302/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.7550 - distribution_lambda_26_loss: 0.3086 - distribution_lambda_27_loss: 1.1836 - distribution_lambda_28_loss: 0.2628 - val_loss: 1.9384 - val_distribution_lambda_26_loss: 0.4203 - val_distribution_lambda_27_loss: 1.2173 - val_distribution_lambda_28_loss: 0.3007\n", "Epoch 1303/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7936 - distribution_lambda_26_loss: 0.2936 - distribution_lambda_27_loss: 1.2155 - distribution_lambda_28_loss: 0.2845 - val_loss: 1.9295 - val_distribution_lambda_26_loss: 0.4144 - val_distribution_lambda_27_loss: 1.2164 - val_distribution_lambda_28_loss: 0.2986\n", "Epoch 1304/2500\n", "8/8 [==============================] - 0s 8ms/step - loss: 1.7365 - distribution_lambda_26_loss: 0.3023 - distribution_lambda_27_loss: 1.1697 - distribution_lambda_28_loss: 0.2646 - val_loss: 1.9402 - val_distribution_lambda_26_loss: 0.4162 - val_distribution_lambda_27_loss: 1.2237 - val_distribution_lambda_28_loss: 0.3003\n", "Epoch 1305/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7409 - distribution_lambda_26_loss: 0.3091 - distribution_lambda_27_loss: 1.1646 - distribution_lambda_28_loss: 0.2672 - val_loss: 1.9332 - val_distribution_lambda_26_loss: 0.4120 - val_distribution_lambda_27_loss: 1.2195 - val_distribution_lambda_28_loss: 0.3017\n", "Epoch 1306/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7855 - distribution_lambda_26_loss: 0.3244 - distribution_lambda_27_loss: 1.1878 - distribution_lambda_28_loss: 0.2733 - val_loss: 1.9214 - val_distribution_lambda_26_loss: 0.4138 - val_distribution_lambda_27_loss: 1.2104 - val_distribution_lambda_28_loss: 0.2972\n", "Epoch 1307/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7828 - distribution_lambda_26_loss: 0.3195 - distribution_lambda_27_loss: 1.1874 - distribution_lambda_28_loss: 0.2759 - val_loss: 1.9086 - val_distribution_lambda_26_loss: 0.4080 - val_distribution_lambda_27_loss: 1.2050 - val_distribution_lambda_28_loss: 0.2956\n", "Epoch 1308/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6954 - distribution_lambda_26_loss: 0.2811 - distribution_lambda_27_loss: 1.1625 - distribution_lambda_28_loss: 0.2517 - val_loss: 1.8996 - val_distribution_lambda_26_loss: 0.4044 - val_distribution_lambda_27_loss: 1.2022 - val_distribution_lambda_28_loss: 0.2930\n", "Epoch 1309/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8071 - distribution_lambda_26_loss: 0.3050 - distribution_lambda_27_loss: 1.2201 - distribution_lambda_28_loss: 0.2820 - val_loss: 1.8971 - val_distribution_lambda_26_loss: 0.3960 - val_distribution_lambda_27_loss: 1.2046 - val_distribution_lambda_28_loss: 0.2965\n", "Epoch 1310/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7471 - distribution_lambda_26_loss: 0.2950 - distribution_lambda_27_loss: 1.1892 - distribution_lambda_28_loss: 0.2629 - val_loss: 1.9143 - val_distribution_lambda_26_loss: 0.4092 - val_distribution_lambda_27_loss: 1.2084 - val_distribution_lambda_28_loss: 0.2967\n", "Epoch 1311/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7186 - distribution_lambda_26_loss: 0.2850 - distribution_lambda_27_loss: 1.1672 - distribution_lambda_28_loss: 0.2664 - val_loss: 1.9102 - val_distribution_lambda_26_loss: 0.4071 - val_distribution_lambda_27_loss: 1.2054 - val_distribution_lambda_28_loss: 0.2976\n", "Epoch 1312/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6931 - distribution_lambda_26_loss: 0.3015 - distribution_lambda_27_loss: 1.1472 - distribution_lambda_28_loss: 0.2443 - val_loss: 1.9169 - val_distribution_lambda_26_loss: 0.4136 - val_distribution_lambda_27_loss: 1.2070 - val_distribution_lambda_28_loss: 0.2963\n", "Epoch 1313/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.7593 - distribution_lambda_26_loss: 0.2820 - distribution_lambda_27_loss: 1.1993 - distribution_lambda_28_loss: 0.2780 - val_loss: 1.9103 - val_distribution_lambda_26_loss: 0.4098 - val_distribution_lambda_27_loss: 1.2031 - val_distribution_lambda_28_loss: 0.2974\n", "Epoch 1314/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7579 - distribution_lambda_26_loss: 0.2948 - distribution_lambda_27_loss: 1.1883 - distribution_lambda_28_loss: 0.2748 - val_loss: 1.9275 - val_distribution_lambda_26_loss: 0.4219 - val_distribution_lambda_27_loss: 1.2054 - val_distribution_lambda_28_loss: 0.3002\n", "Epoch 1315/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.7490 - distribution_lambda_26_loss: 0.2864 - distribution_lambda_27_loss: 1.1902 - distribution_lambda_28_loss: 0.2723 - val_loss: 1.9132 - val_distribution_lambda_26_loss: 0.4059 - val_distribution_lambda_27_loss: 1.2064 - val_distribution_lambda_28_loss: 0.3009\n", "Epoch 1316/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7593 - distribution_lambda_26_loss: 0.3005 - distribution_lambda_27_loss: 1.1856 - distribution_lambda_28_loss: 0.2732 - val_loss: 1.9098 - val_distribution_lambda_26_loss: 0.4024 - val_distribution_lambda_27_loss: 1.2071 - val_distribution_lambda_28_loss: 0.3003\n", "Epoch 1317/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7509 - distribution_lambda_26_loss: 0.2927 - distribution_lambda_27_loss: 1.1848 - distribution_lambda_28_loss: 0.2734 - val_loss: 1.9070 - val_distribution_lambda_26_loss: 0.4038 - val_distribution_lambda_27_loss: 1.2057 - val_distribution_lambda_28_loss: 0.2976\n", "Epoch 1318/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.8030 - distribution_lambda_26_loss: 0.3071 - distribution_lambda_27_loss: 1.2080 - distribution_lambda_28_loss: 0.2879 - val_loss: 1.9074 - val_distribution_lambda_26_loss: 0.4085 - val_distribution_lambda_27_loss: 1.2053 - val_distribution_lambda_28_loss: 0.2935\n", "Epoch 1319/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.7527 - distribution_lambda_26_loss: 0.3008 - distribution_lambda_27_loss: 1.1718 - distribution_lambda_28_loss: 0.2801 - val_loss: 1.9071 - val_distribution_lambda_26_loss: 0.4113 - val_distribution_lambda_27_loss: 1.2007 - val_distribution_lambda_28_loss: 0.2951\n", "Epoch 1320/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7857 - distribution_lambda_26_loss: 0.2868 - distribution_lambda_27_loss: 1.2070 - distribution_lambda_28_loss: 0.2919 - val_loss: 1.8909 - val_distribution_lambda_26_loss: 0.4039 - val_distribution_lambda_27_loss: 1.1972 - val_distribution_lambda_28_loss: 0.2898\n", "Epoch 1321/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 1.7327 - distribution_lambda_26_loss: 0.2836 - distribution_lambda_27_loss: 1.1784 - distribution_lambda_28_loss: 0.2707 - val_loss: 1.8967 - val_distribution_lambda_26_loss: 0.4083 - val_distribution_lambda_27_loss: 1.1955 - val_distribution_lambda_28_loss: 0.2928\n", "Epoch 1322/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.7240 - distribution_lambda_26_loss: 0.2811 - distribution_lambda_27_loss: 1.1752 - distribution_lambda_28_loss: 0.2677 - val_loss: 1.8917 - val_distribution_lambda_26_loss: 0.4086 - val_distribution_lambda_27_loss: 1.1911 - val_distribution_lambda_28_loss: 0.2919\n", "Epoch 1323/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7732 - distribution_lambda_26_loss: 0.3031 - distribution_lambda_27_loss: 1.1878 - distribution_lambda_28_loss: 0.2823 - val_loss: 1.8934 - val_distribution_lambda_26_loss: 0.4044 - val_distribution_lambda_27_loss: 1.1965 - val_distribution_lambda_28_loss: 0.2925\n", "Epoch 1324/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6882 - distribution_lambda_26_loss: 0.3013 - distribution_lambda_27_loss: 1.1378 - distribution_lambda_28_loss: 0.2491 - val_loss: 1.8814 - val_distribution_lambda_26_loss: 0.3988 - val_distribution_lambda_27_loss: 1.1929 - val_distribution_lambda_28_loss: 0.2897\n", "Epoch 1325/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 1.7263 - distribution_lambda_26_loss: 0.2829 - distribution_lambda_27_loss: 1.1687 - distribution_lambda_28_loss: 0.2747 - val_loss: 1.8888 - val_distribution_lambda_26_loss: 0.4098 - val_distribution_lambda_27_loss: 1.1874 - val_distribution_lambda_28_loss: 0.2915\n", "Epoch 1326/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6928 - distribution_lambda_26_loss: 0.2911 - distribution_lambda_27_loss: 1.1420 - distribution_lambda_28_loss: 0.2597 - val_loss: 1.8910 - val_distribution_lambda_26_loss: 0.4135 - val_distribution_lambda_27_loss: 1.1847 - val_distribution_lambda_28_loss: 0.2928\n", "Epoch 1327/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7603 - distribution_lambda_26_loss: 0.3096 - distribution_lambda_27_loss: 1.1764 - distribution_lambda_28_loss: 0.2743 - val_loss: 1.9007 - val_distribution_lambda_26_loss: 0.4188 - val_distribution_lambda_27_loss: 1.1892 - val_distribution_lambda_28_loss: 0.2927\n", "Epoch 1328/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7044 - distribution_lambda_26_loss: 0.2860 - distribution_lambda_27_loss: 1.1725 - distribution_lambda_28_loss: 0.2460 - val_loss: 1.8917 - val_distribution_lambda_26_loss: 0.4043 - val_distribution_lambda_27_loss: 1.1961 - val_distribution_lambda_28_loss: 0.2913\n", "Epoch 1329/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7391 - distribution_lambda_26_loss: 0.2969 - distribution_lambda_27_loss: 1.1737 - distribution_lambda_28_loss: 0.2685 - val_loss: 1.8833 - val_distribution_lambda_26_loss: 0.4078 - val_distribution_lambda_27_loss: 1.1861 - val_distribution_lambda_28_loss: 0.2894\n", "Epoch 1330/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7193 - distribution_lambda_26_loss: 0.3038 - distribution_lambda_27_loss: 1.1560 - distribution_lambda_28_loss: 0.2595 - val_loss: 1.8905 - val_distribution_lambda_26_loss: 0.4168 - val_distribution_lambda_27_loss: 1.1863 - val_distribution_lambda_28_loss: 0.2874\n", "Epoch 1331/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7420 - distribution_lambda_26_loss: 0.3019 - distribution_lambda_27_loss: 1.1752 - distribution_lambda_28_loss: 0.2650 - val_loss: 1.8908 - val_distribution_lambda_26_loss: 0.4212 - val_distribution_lambda_27_loss: 1.1831 - val_distribution_lambda_28_loss: 0.2865\n", "Epoch 1332/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6880 - distribution_lambda_26_loss: 0.3063 - distribution_lambda_27_loss: 1.1334 - distribution_lambda_28_loss: 0.2482 - val_loss: 1.8788 - val_distribution_lambda_26_loss: 0.4114 - val_distribution_lambda_27_loss: 1.1807 - val_distribution_lambda_28_loss: 0.2867\n", "Epoch 1333/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7030 - distribution_lambda_26_loss: 0.2976 - distribution_lambda_27_loss: 1.1585 - distribution_lambda_28_loss: 0.2470 - val_loss: 1.8797 - val_distribution_lambda_26_loss: 0.4060 - val_distribution_lambda_27_loss: 1.1841 - val_distribution_lambda_28_loss: 0.2895\n", "Epoch 1334/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7297 - distribution_lambda_26_loss: 0.2992 - distribution_lambda_27_loss: 1.1643 - distribution_lambda_28_loss: 0.2662 - val_loss: 1.8753 - val_distribution_lambda_26_loss: 0.4032 - val_distribution_lambda_27_loss: 1.1816 - val_distribution_lambda_28_loss: 0.2905\n", "Epoch 1335/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6779 - distribution_lambda_26_loss: 0.2750 - distribution_lambda_27_loss: 1.1376 - distribution_lambda_28_loss: 0.2653 - val_loss: 1.8876 - val_distribution_lambda_26_loss: 0.4093 - val_distribution_lambda_27_loss: 1.1846 - val_distribution_lambda_28_loss: 0.2937\n", "Epoch 1336/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6930 - distribution_lambda_26_loss: 0.2826 - distribution_lambda_27_loss: 1.1602 - distribution_lambda_28_loss: 0.2502 - val_loss: 1.8874 - val_distribution_lambda_26_loss: 0.4085 - val_distribution_lambda_27_loss: 1.1848 - val_distribution_lambda_28_loss: 0.2941\n", "Epoch 1337/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7224 - distribution_lambda_26_loss: 0.2971 - distribution_lambda_27_loss: 1.1674 - distribution_lambda_28_loss: 0.2578 - val_loss: 1.8861 - val_distribution_lambda_26_loss: 0.4087 - val_distribution_lambda_27_loss: 1.1837 - val_distribution_lambda_28_loss: 0.2937\n", "Epoch 1338/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6795 - distribution_lambda_26_loss: 0.2654 - distribution_lambda_27_loss: 1.1488 - distribution_lambda_28_loss: 0.2653 - val_loss: 1.8740 - val_distribution_lambda_26_loss: 0.4121 - val_distribution_lambda_27_loss: 1.1764 - val_distribution_lambda_28_loss: 0.2855\n", "Epoch 1339/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6858 - distribution_lambda_26_loss: 0.3082 - distribution_lambda_27_loss: 1.1269 - distribution_lambda_28_loss: 0.2508 - val_loss: 1.8665 - val_distribution_lambda_26_loss: 0.4050 - val_distribution_lambda_27_loss: 1.1732 - val_distribution_lambda_28_loss: 0.2882\n", "Epoch 1340/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7181 - distribution_lambda_26_loss: 0.2896 - distribution_lambda_27_loss: 1.1602 - distribution_lambda_28_loss: 0.2683 - val_loss: 1.8894 - val_distribution_lambda_26_loss: 0.4267 - val_distribution_lambda_27_loss: 1.1757 - val_distribution_lambda_28_loss: 0.2870\n", "Epoch 1341/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6996 - distribution_lambda_26_loss: 0.2896 - distribution_lambda_27_loss: 1.1480 - distribution_lambda_28_loss: 0.2620 - val_loss: 1.8752 - val_distribution_lambda_26_loss: 0.4147 - val_distribution_lambda_27_loss: 1.1733 - val_distribution_lambda_28_loss: 0.2872\n", "Epoch 1342/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6703 - distribution_lambda_26_loss: 0.2861 - distribution_lambda_27_loss: 1.1316 - distribution_lambda_28_loss: 0.2526 - val_loss: 1.8661 - val_distribution_lambda_26_loss: 0.4095 - val_distribution_lambda_27_loss: 1.1678 - val_distribution_lambda_28_loss: 0.2889\n", "Epoch 1343/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7304 - distribution_lambda_26_loss: 0.2944 - distribution_lambda_27_loss: 1.1656 - distribution_lambda_28_loss: 0.2703 - val_loss: 1.8791 - val_distribution_lambda_26_loss: 0.4168 - val_distribution_lambda_27_loss: 1.1684 - val_distribution_lambda_28_loss: 0.2939\n", "Epoch 1344/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7061 - distribution_lambda_26_loss: 0.2921 - distribution_lambda_27_loss: 1.1476 - distribution_lambda_28_loss: 0.2663 - val_loss: 1.8732 - val_distribution_lambda_26_loss: 0.4110 - val_distribution_lambda_27_loss: 1.1676 - val_distribution_lambda_28_loss: 0.2945\n", "Epoch 1345/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 1.6687 - distribution_lambda_26_loss: 0.2727 - distribution_lambda_27_loss: 1.1333 - distribution_lambda_28_loss: 0.2627 - val_loss: 1.8728 - val_distribution_lambda_26_loss: 0.4153 - val_distribution_lambda_27_loss: 1.1646 - val_distribution_lambda_28_loss: 0.2929\n", "Epoch 1346/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.7164 - distribution_lambda_26_loss: 0.2872 - distribution_lambda_27_loss: 1.1667 - distribution_lambda_28_loss: 0.2625 - val_loss: 1.8779 - val_distribution_lambda_26_loss: 0.4227 - val_distribution_lambda_27_loss: 1.1651 - val_distribution_lambda_28_loss: 0.2901\n", "Epoch 1347/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7507 - distribution_lambda_26_loss: 0.3042 - distribution_lambda_27_loss: 1.1842 - distribution_lambda_28_loss: 0.2623 - val_loss: 1.8806 - val_distribution_lambda_26_loss: 0.4237 - val_distribution_lambda_27_loss: 1.1671 - val_distribution_lambda_28_loss: 0.2898\n", "Epoch 1348/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7000 - distribution_lambda_26_loss: 0.2997 - distribution_lambda_27_loss: 1.1501 - distribution_lambda_28_loss: 0.2503 - val_loss: 1.8603 - val_distribution_lambda_26_loss: 0.4143 - val_distribution_lambda_27_loss: 1.1613 - val_distribution_lambda_28_loss: 0.2847\n", "Epoch 1349/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6618 - distribution_lambda_26_loss: 0.2861 - distribution_lambda_27_loss: 1.1304 - distribution_lambda_28_loss: 0.2452 - val_loss: 1.8672 - val_distribution_lambda_26_loss: 0.4211 - val_distribution_lambda_27_loss: 1.1626 - val_distribution_lambda_28_loss: 0.2835\n", "Epoch 1350/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7144 - distribution_lambda_26_loss: 0.2953 - distribution_lambda_27_loss: 1.1559 - distribution_lambda_28_loss: 0.2632 - val_loss: 1.8681 - val_distribution_lambda_26_loss: 0.4133 - val_distribution_lambda_27_loss: 1.1683 - val_distribution_lambda_28_loss: 0.2865\n", "Epoch 1351/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7383 - distribution_lambda_26_loss: 0.3006 - distribution_lambda_27_loss: 1.1740 - distribution_lambda_28_loss: 0.2636 - val_loss: 1.8688 - val_distribution_lambda_26_loss: 0.4094 - val_distribution_lambda_27_loss: 1.1710 - val_distribution_lambda_28_loss: 0.2884\n", "Epoch 1352/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6911 - distribution_lambda_26_loss: 0.2944 - distribution_lambda_27_loss: 1.1415 - distribution_lambda_28_loss: 0.2552 - val_loss: 1.8730 - val_distribution_lambda_26_loss: 0.4169 - val_distribution_lambda_27_loss: 1.1695 - val_distribution_lambda_28_loss: 0.2866\n", "Epoch 1353/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7345 - distribution_lambda_26_loss: 0.2846 - distribution_lambda_27_loss: 1.1792 - distribution_lambda_28_loss: 0.2707 - val_loss: 1.8527 - val_distribution_lambda_26_loss: 0.4031 - val_distribution_lambda_27_loss: 1.1656 - val_distribution_lambda_28_loss: 0.2841\n", "Epoch 1354/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6594 - distribution_lambda_26_loss: 0.2798 - distribution_lambda_27_loss: 1.1257 - distribution_lambda_28_loss: 0.2539 - val_loss: 1.8727 - val_distribution_lambda_26_loss: 0.4199 - val_distribution_lambda_27_loss: 1.1678 - val_distribution_lambda_28_loss: 0.2850\n", "Epoch 1355/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7312 - distribution_lambda_26_loss: 0.2970 - distribution_lambda_27_loss: 1.1622 - distribution_lambda_28_loss: 0.2720 - val_loss: 1.8642 - val_distribution_lambda_26_loss: 0.4157 - val_distribution_lambda_27_loss: 1.1638 - val_distribution_lambda_28_loss: 0.2846\n", "Epoch 1356/2500\n", "8/8 [==============================] - 0s 5ms/step - loss: 1.7081 - distribution_lambda_26_loss: 0.2991 - distribution_lambda_27_loss: 1.1533 - distribution_lambda_28_loss: 0.2558 - val_loss: 1.8717 - val_distribution_lambda_26_loss: 0.4180 - val_distribution_lambda_27_loss: 1.1658 - val_distribution_lambda_28_loss: 0.2879\n", "Epoch 1357/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7436 - distribution_lambda_26_loss: 0.3117 - distribution_lambda_27_loss: 1.1718 - distribution_lambda_28_loss: 0.2601 - val_loss: 1.8588 - val_distribution_lambda_26_loss: 0.4081 - val_distribution_lambda_27_loss: 1.1632 - val_distribution_lambda_28_loss: 0.2875\n", "Epoch 1358/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6690 - distribution_lambda_26_loss: 0.2687 - distribution_lambda_27_loss: 1.1492 - distribution_lambda_28_loss: 0.2511 - val_loss: 1.8446 - val_distribution_lambda_26_loss: 0.3996 - val_distribution_lambda_27_loss: 1.1585 - val_distribution_lambda_28_loss: 0.2866\n", "Epoch 1359/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6805 - distribution_lambda_26_loss: 0.2677 - distribution_lambda_27_loss: 1.1498 - distribution_lambda_28_loss: 0.2630 - val_loss: 1.8579 - val_distribution_lambda_26_loss: 0.4077 - val_distribution_lambda_27_loss: 1.1624 - val_distribution_lambda_28_loss: 0.2878\n", "Epoch 1360/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6571 - distribution_lambda_26_loss: 0.3046 - distribution_lambda_27_loss: 1.1164 - distribution_lambda_28_loss: 0.2361 - val_loss: 1.8805 - val_distribution_lambda_26_loss: 0.4219 - val_distribution_lambda_27_loss: 1.1666 - val_distribution_lambda_28_loss: 0.2920\n", "Epoch 1361/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6469 - distribution_lambda_26_loss: 0.2805 - distribution_lambda_27_loss: 1.1229 - distribution_lambda_28_loss: 0.2434 - val_loss: 1.8590 - val_distribution_lambda_26_loss: 0.4078 - val_distribution_lambda_27_loss: 1.1598 - val_distribution_lambda_28_loss: 0.2914\n", "Epoch 1362/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6649 - distribution_lambda_26_loss: 0.2835 - distribution_lambda_27_loss: 1.1226 - distribution_lambda_28_loss: 0.2588 - val_loss: 1.8527 - val_distribution_lambda_26_loss: 0.4078 - val_distribution_lambda_27_loss: 1.1563 - val_distribution_lambda_28_loss: 0.2885\n", "Epoch 1363/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6892 - distribution_lambda_26_loss: 0.2931 - distribution_lambda_27_loss: 1.1545 - distribution_lambda_28_loss: 0.2417 - val_loss: 1.8517 - val_distribution_lambda_26_loss: 0.4085 - val_distribution_lambda_27_loss: 1.1601 - val_distribution_lambda_28_loss: 0.2831\n", "Epoch 1364/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7399 - distribution_lambda_26_loss: 0.3014 - distribution_lambda_27_loss: 1.1614 - distribution_lambda_28_loss: 0.2771 - val_loss: 1.8532 - val_distribution_lambda_26_loss: 0.4134 - val_distribution_lambda_27_loss: 1.1564 - val_distribution_lambda_28_loss: 0.2834\n", "Epoch 1365/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6811 - distribution_lambda_26_loss: 0.2814 - distribution_lambda_27_loss: 1.1454 - distribution_lambda_28_loss: 0.2542 - val_loss: 1.8714 - val_distribution_lambda_26_loss: 0.4246 - val_distribution_lambda_27_loss: 1.1613 - val_distribution_lambda_28_loss: 0.2854\n", "Epoch 1366/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6638 - distribution_lambda_26_loss: 0.3024 - distribution_lambda_27_loss: 1.1137 - distribution_lambda_28_loss: 0.2477 - val_loss: 1.8833 - val_distribution_lambda_26_loss: 0.4282 - val_distribution_lambda_27_loss: 1.1654 - val_distribution_lambda_28_loss: 0.2897\n", "Epoch 1367/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7079 - distribution_lambda_26_loss: 0.3148 - distribution_lambda_27_loss: 1.1379 - distribution_lambda_28_loss: 0.2552 - val_loss: 1.8281 - val_distribution_lambda_26_loss: 0.3966 - val_distribution_lambda_27_loss: 1.1486 - val_distribution_lambda_28_loss: 0.2829\n", "Epoch 1368/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6750 - distribution_lambda_26_loss: 0.2886 - distribution_lambda_27_loss: 1.1450 - distribution_lambda_28_loss: 0.2413 - val_loss: 1.8332 - val_distribution_lambda_26_loss: 0.4005 - val_distribution_lambda_27_loss: 1.1484 - val_distribution_lambda_28_loss: 0.2843\n", "Epoch 1369/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 7ms/step - loss: 1.6781 - distribution_lambda_26_loss: 0.2864 - distribution_lambda_27_loss: 1.1336 - distribution_lambda_28_loss: 0.2581 - val_loss: 1.8420 - val_distribution_lambda_26_loss: 0.4155 - val_distribution_lambda_27_loss: 1.1458 - val_distribution_lambda_28_loss: 0.2807\n", "Epoch 1370/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6910 - distribution_lambda_26_loss: 0.3231 - distribution_lambda_27_loss: 1.1307 - distribution_lambda_28_loss: 0.2372 - val_loss: 1.8397 - val_distribution_lambda_26_loss: 0.4128 - val_distribution_lambda_27_loss: 1.1450 - val_distribution_lambda_28_loss: 0.2818\n", "Epoch 1371/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6783 - distribution_lambda_26_loss: 0.3001 - distribution_lambda_27_loss: 1.1289 - distribution_lambda_28_loss: 0.2492 - val_loss: 1.8289 - val_distribution_lambda_26_loss: 0.4128 - val_distribution_lambda_27_loss: 1.1379 - val_distribution_lambda_28_loss: 0.2782\n", "Epoch 1372/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6332 - distribution_lambda_26_loss: 0.2932 - distribution_lambda_27_loss: 1.1098 - distribution_lambda_28_loss: 0.2301 - val_loss: 1.8319 - val_distribution_lambda_26_loss: 0.4127 - val_distribution_lambda_27_loss: 1.1396 - val_distribution_lambda_28_loss: 0.2797\n", "Epoch 1373/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6915 - distribution_lambda_26_loss: 0.2854 - distribution_lambda_27_loss: 1.1426 - distribution_lambda_28_loss: 0.2635 - val_loss: 1.8528 - val_distribution_lambda_26_loss: 0.4258 - val_distribution_lambda_27_loss: 1.1473 - val_distribution_lambda_28_loss: 0.2797\n", "Epoch 1374/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6639 - distribution_lambda_26_loss: 0.2775 - distribution_lambda_27_loss: 1.1263 - distribution_lambda_28_loss: 0.2600 - val_loss: 1.8595 - val_distribution_lambda_26_loss: 0.4294 - val_distribution_lambda_27_loss: 1.1508 - val_distribution_lambda_28_loss: 0.2793\n", "Epoch 1375/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7115 - distribution_lambda_26_loss: 0.3145 - distribution_lambda_27_loss: 1.1444 - distribution_lambda_28_loss: 0.2527 - val_loss: 1.8397 - val_distribution_lambda_26_loss: 0.4064 - val_distribution_lambda_27_loss: 1.1502 - val_distribution_lambda_28_loss: 0.2831\n", "Epoch 1376/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6330 - distribution_lambda_26_loss: 0.2888 - distribution_lambda_27_loss: 1.1128 - distribution_lambda_28_loss: 0.2314 - val_loss: 1.8485 - val_distribution_lambda_26_loss: 0.4153 - val_distribution_lambda_27_loss: 1.1488 - val_distribution_lambda_28_loss: 0.2844\n", "Epoch 1377/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6995 - distribution_lambda_26_loss: 0.2978 - distribution_lambda_27_loss: 1.1393 - distribution_lambda_28_loss: 0.2623 - val_loss: 1.8505 - val_distribution_lambda_26_loss: 0.4195 - val_distribution_lambda_27_loss: 1.1472 - val_distribution_lambda_28_loss: 0.2837\n", "Epoch 1378/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6273 - distribution_lambda_26_loss: 0.2843 - distribution_lambda_27_loss: 1.1052 - distribution_lambda_28_loss: 0.2379 - val_loss: 1.8336 - val_distribution_lambda_26_loss: 0.4095 - val_distribution_lambda_27_loss: 1.1433 - val_distribution_lambda_28_loss: 0.2808\n", "Epoch 1379/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7017 - distribution_lambda_26_loss: 0.3158 - distribution_lambda_27_loss: 1.1227 - distribution_lambda_28_loss: 0.2631 - val_loss: 1.8504 - val_distribution_lambda_26_loss: 0.4218 - val_distribution_lambda_27_loss: 1.1463 - val_distribution_lambda_28_loss: 0.2824\n", "Epoch 1380/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6385 - distribution_lambda_26_loss: 0.2745 - distribution_lambda_27_loss: 1.1256 - distribution_lambda_28_loss: 0.2383 - val_loss: 1.8604 - val_distribution_lambda_26_loss: 0.4220 - val_distribution_lambda_27_loss: 1.1529 - val_distribution_lambda_28_loss: 0.2854\n", "Epoch 1381/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6608 - distribution_lambda_26_loss: 0.2932 - distribution_lambda_27_loss: 1.1230 - distribution_lambda_28_loss: 0.2446 - val_loss: 1.8469 - val_distribution_lambda_26_loss: 0.4071 - val_distribution_lambda_27_loss: 1.1527 - val_distribution_lambda_28_loss: 0.2870\n", "Epoch 1382/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6833 - distribution_lambda_26_loss: 0.2892 - distribution_lambda_27_loss: 1.1361 - distribution_lambda_28_loss: 0.2581 - val_loss: 1.8174 - val_distribution_lambda_26_loss: 0.3941 - val_distribution_lambda_27_loss: 1.1447 - val_distribution_lambda_28_loss: 0.2786\n", "Epoch 1383/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6375 - distribution_lambda_26_loss: 0.2935 - distribution_lambda_27_loss: 1.1046 - distribution_lambda_28_loss: 0.2394 - val_loss: 1.8205 - val_distribution_lambda_26_loss: 0.4038 - val_distribution_lambda_27_loss: 1.1387 - val_distribution_lambda_28_loss: 0.2780\n", "Epoch 1384/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.6447 - distribution_lambda_26_loss: 0.3053 - distribution_lambda_27_loss: 1.0954 - distribution_lambda_28_loss: 0.2439 - val_loss: 1.8237 - val_distribution_lambda_26_loss: 0.4040 - val_distribution_lambda_27_loss: 1.1399 - val_distribution_lambda_28_loss: 0.2797\n", "Epoch 1385/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6827 - distribution_lambda_26_loss: 0.2703 - distribution_lambda_27_loss: 1.1596 - distribution_lambda_28_loss: 0.2528 - val_loss: 1.8384 - val_distribution_lambda_26_loss: 0.4173 - val_distribution_lambda_27_loss: 1.1415 - val_distribution_lambda_28_loss: 0.2797\n", "Epoch 1386/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6205 - distribution_lambda_26_loss: 0.2591 - distribution_lambda_27_loss: 1.1215 - distribution_lambda_28_loss: 0.2399 - val_loss: 1.8379 - val_distribution_lambda_26_loss: 0.4155 - val_distribution_lambda_27_loss: 1.1426 - val_distribution_lambda_28_loss: 0.2797\n", "Epoch 1387/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6431 - distribution_lambda_26_loss: 0.2994 - distribution_lambda_27_loss: 1.1057 - distribution_lambda_28_loss: 0.2380 - val_loss: 1.8228 - val_distribution_lambda_26_loss: 0.4150 - val_distribution_lambda_27_loss: 1.1302 - val_distribution_lambda_28_loss: 0.2776\n", "Epoch 1388/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6701 - distribution_lambda_26_loss: 0.3013 - distribution_lambda_27_loss: 1.1314 - distribution_lambda_28_loss: 0.2373 - val_loss: 1.8056 - val_distribution_lambda_26_loss: 0.4170 - val_distribution_lambda_27_loss: 1.1167 - val_distribution_lambda_28_loss: 0.2719\n", "Epoch 1389/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.7022 - distribution_lambda_26_loss: 0.2865 - distribution_lambda_27_loss: 1.1570 - distribution_lambda_28_loss: 0.2587 - val_loss: 1.8050 - val_distribution_lambda_26_loss: 0.4128 - val_distribution_lambda_27_loss: 1.1159 - val_distribution_lambda_28_loss: 0.2763\n", "Epoch 1390/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6258 - distribution_lambda_26_loss: 0.2759 - distribution_lambda_27_loss: 1.1192 - distribution_lambda_28_loss: 0.2307 - val_loss: 1.8014 - val_distribution_lambda_26_loss: 0.4045 - val_distribution_lambda_27_loss: 1.1199 - val_distribution_lambda_28_loss: 0.2770\n", "Epoch 1391/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6405 - distribution_lambda_26_loss: 0.2701 - distribution_lambda_27_loss: 1.1285 - distribution_lambda_28_loss: 0.2420 - val_loss: 1.8139 - val_distribution_lambda_26_loss: 0.4142 - val_distribution_lambda_27_loss: 1.1224 - val_distribution_lambda_28_loss: 0.2773\n", "Epoch 1392/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6785 - distribution_lambda_26_loss: 0.2832 - distribution_lambda_27_loss: 1.1354 - distribution_lambda_28_loss: 0.2598 - val_loss: 1.8181 - val_distribution_lambda_26_loss: 0.4100 - val_distribution_lambda_27_loss: 1.1257 - val_distribution_lambda_28_loss: 0.2823\n", "Epoch 1393/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 1.7182 - distribution_lambda_26_loss: 0.2949 - distribution_lambda_27_loss: 1.1681 - distribution_lambda_28_loss: 0.2552 - val_loss: 1.8283 - val_distribution_lambda_26_loss: 0.4156 - val_distribution_lambda_27_loss: 1.1309 - val_distribution_lambda_28_loss: 0.2819\n", "Epoch 1394/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6057 - distribution_lambda_26_loss: 0.2722 - distribution_lambda_27_loss: 1.1000 - distribution_lambda_28_loss: 0.2335 - val_loss: 1.8231 - val_distribution_lambda_26_loss: 0.4145 - val_distribution_lambda_27_loss: 1.1278 - val_distribution_lambda_28_loss: 0.2808\n", "Epoch 1395/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.6116 - distribution_lambda_26_loss: 0.2559 - distribution_lambda_27_loss: 1.1215 - distribution_lambda_28_loss: 0.2341 - val_loss: 1.8379 - val_distribution_lambda_26_loss: 0.4281 - val_distribution_lambda_27_loss: 1.1273 - val_distribution_lambda_28_loss: 0.2824\n", "Epoch 1396/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6578 - distribution_lambda_26_loss: 0.2818 - distribution_lambda_27_loss: 1.1247 - distribution_lambda_28_loss: 0.2513 - val_loss: 1.8239 - val_distribution_lambda_26_loss: 0.4164 - val_distribution_lambda_27_loss: 1.1272 - val_distribution_lambda_28_loss: 0.2803\n", "Epoch 1397/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6434 - distribution_lambda_26_loss: 0.2845 - distribution_lambda_27_loss: 1.1263 - distribution_lambda_28_loss: 0.2326 - val_loss: 1.8358 - val_distribution_lambda_26_loss: 0.4239 - val_distribution_lambda_27_loss: 1.1302 - val_distribution_lambda_28_loss: 0.2817\n", "Epoch 1398/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6128 - distribution_lambda_26_loss: 0.2814 - distribution_lambda_27_loss: 1.1105 - distribution_lambda_28_loss: 0.2208 - val_loss: 1.8373 - val_distribution_lambda_26_loss: 0.4224 - val_distribution_lambda_27_loss: 1.1340 - val_distribution_lambda_28_loss: 0.2809\n", "Epoch 1399/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6466 - distribution_lambda_26_loss: 0.2861 - distribution_lambda_27_loss: 1.1161 - distribution_lambda_28_loss: 0.2445 - val_loss: 1.8259 - val_distribution_lambda_26_loss: 0.4107 - val_distribution_lambda_27_loss: 1.1350 - val_distribution_lambda_28_loss: 0.2802\n", "Epoch 1400/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6798 - distribution_lambda_26_loss: 0.2879 - distribution_lambda_27_loss: 1.1407 - distribution_lambda_28_loss: 0.2512 - val_loss: 1.8284 - val_distribution_lambda_26_loss: 0.4173 - val_distribution_lambda_27_loss: 1.1303 - val_distribution_lambda_28_loss: 0.2808\n", "Epoch 1401/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6558 - distribution_lambda_26_loss: 0.2933 - distribution_lambda_27_loss: 1.1224 - distribution_lambda_28_loss: 0.2401 - val_loss: 1.8193 - val_distribution_lambda_26_loss: 0.4098 - val_distribution_lambda_27_loss: 1.1272 - val_distribution_lambda_28_loss: 0.2823\n", "Epoch 1402/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6643 - distribution_lambda_26_loss: 0.2784 - distribution_lambda_27_loss: 1.1327 - distribution_lambda_28_loss: 0.2533 - val_loss: 1.8188 - val_distribution_lambda_26_loss: 0.4128 - val_distribution_lambda_27_loss: 1.1271 - val_distribution_lambda_28_loss: 0.2790\n", "Epoch 1403/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6982 - distribution_lambda_26_loss: 0.2969 - distribution_lambda_27_loss: 1.1417 - distribution_lambda_28_loss: 0.2596 - val_loss: 1.8294 - val_distribution_lambda_26_loss: 0.4177 - val_distribution_lambda_27_loss: 1.1279 - val_distribution_lambda_28_loss: 0.2838\n", "Epoch 1404/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6520 - distribution_lambda_26_loss: 0.2843 - distribution_lambda_27_loss: 1.1253 - distribution_lambda_28_loss: 0.2423 - val_loss: 1.8301 - val_distribution_lambda_26_loss: 0.4235 - val_distribution_lambda_27_loss: 1.1251 - val_distribution_lambda_28_loss: 0.2815\n", "Epoch 1405/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6810 - distribution_lambda_26_loss: 0.3005 - distribution_lambda_27_loss: 1.1295 - distribution_lambda_28_loss: 0.2510 - val_loss: 1.8142 - val_distribution_lambda_26_loss: 0.4112 - val_distribution_lambda_27_loss: 1.1213 - val_distribution_lambda_28_loss: 0.2817\n", "Epoch 1406/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.6321 - distribution_lambda_26_loss: 0.2767 - distribution_lambda_27_loss: 1.1065 - distribution_lambda_28_loss: 0.2489 - val_loss: 1.8091 - val_distribution_lambda_26_loss: 0.4108 - val_distribution_lambda_27_loss: 1.1177 - val_distribution_lambda_28_loss: 0.2807\n", "Epoch 1407/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6636 - distribution_lambda_26_loss: 0.2850 - distribution_lambda_27_loss: 1.1221 - distribution_lambda_28_loss: 0.2565 - val_loss: 1.8142 - val_distribution_lambda_26_loss: 0.4112 - val_distribution_lambda_27_loss: 1.1224 - val_distribution_lambda_28_loss: 0.2805\n", "Epoch 1408/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6377 - distribution_lambda_26_loss: 0.2683 - distribution_lambda_27_loss: 1.1275 - distribution_lambda_28_loss: 0.2419 - val_loss: 1.8402 - val_distribution_lambda_26_loss: 0.4245 - val_distribution_lambda_27_loss: 1.1346 - val_distribution_lambda_28_loss: 0.2811\n", "Epoch 1409/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6658 - distribution_lambda_26_loss: 0.2691 - distribution_lambda_27_loss: 1.1491 - distribution_lambda_28_loss: 0.2476 - val_loss: 1.8537 - val_distribution_lambda_26_loss: 0.4351 - val_distribution_lambda_27_loss: 1.1382 - val_distribution_lambda_28_loss: 0.2804\n", "Epoch 1410/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6474 - distribution_lambda_26_loss: 0.2918 - distribution_lambda_27_loss: 1.1075 - distribution_lambda_28_loss: 0.2481 - val_loss: 1.8183 - val_distribution_lambda_26_loss: 0.4050 - val_distribution_lambda_27_loss: 1.1338 - val_distribution_lambda_28_loss: 0.2795\n", "Epoch 1411/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6426 - distribution_lambda_26_loss: 0.2748 - distribution_lambda_27_loss: 1.1227 - distribution_lambda_28_loss: 0.2452 - val_loss: 1.8153 - val_distribution_lambda_26_loss: 0.4023 - val_distribution_lambda_27_loss: 1.1315 - val_distribution_lambda_28_loss: 0.2814\n", "Epoch 1412/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6965 - distribution_lambda_26_loss: 0.2804 - distribution_lambda_27_loss: 1.1505 - distribution_lambda_28_loss: 0.2657 - val_loss: 1.8345 - val_distribution_lambda_26_loss: 0.4169 - val_distribution_lambda_27_loss: 1.1306 - val_distribution_lambda_28_loss: 0.2870\n", "Epoch 1413/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6683 - distribution_lambda_26_loss: 0.2938 - distribution_lambda_27_loss: 1.1290 - distribution_lambda_28_loss: 0.2455 - val_loss: 1.8302 - val_distribution_lambda_26_loss: 0.4211 - val_distribution_lambda_27_loss: 1.1267 - val_distribution_lambda_28_loss: 0.2824\n", "Epoch 1414/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6318 - distribution_lambda_26_loss: 0.2861 - distribution_lambda_27_loss: 1.1085 - distribution_lambda_28_loss: 0.2372 - val_loss: 1.8295 - val_distribution_lambda_26_loss: 0.4248 - val_distribution_lambda_27_loss: 1.1256 - val_distribution_lambda_28_loss: 0.2791\n", "Epoch 1415/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6503 - distribution_lambda_26_loss: 0.2964 - distribution_lambda_27_loss: 1.1161 - distribution_lambda_28_loss: 0.2378 - val_loss: 1.8168 - val_distribution_lambda_26_loss: 0.4143 - val_distribution_lambda_27_loss: 1.1216 - val_distribution_lambda_28_loss: 0.2808\n", "Epoch 1416/2500\n", "8/8 [==============================] - 0s 7ms/step - loss: 1.6750 - distribution_lambda_26_loss: 0.2846 - distribution_lambda_27_loss: 1.1224 - distribution_lambda_28_loss: 0.2680 - val_loss: 1.8054 - val_distribution_lambda_26_loss: 0.4101 - val_distribution_lambda_27_loss: 1.1189 - val_distribution_lambda_28_loss: 0.2763\n", "Epoch 1417/2500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "8/8 [==============================] - 0s 6ms/step - loss: 1.6381 - distribution_lambda_26_loss: 0.2740 - distribution_lambda_27_loss: 1.1117 - distribution_lambda_28_loss: 0.2524 - val_loss: 1.8139 - val_distribution_lambda_26_loss: 0.4185 - val_distribution_lambda_27_loss: 1.1185 - val_distribution_lambda_28_loss: 0.2769\n", "Epoch 1418/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.5959 - distribution_lambda_26_loss: 0.2659 - distribution_lambda_27_loss: 1.1019 - distribution_lambda_28_loss: 0.2281 - val_loss: 1.8195 - val_distribution_lambda_26_loss: 0.4156 - val_distribution_lambda_27_loss: 1.1225 - val_distribution_lambda_28_loss: 0.2813\n", "Epoch 1419/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.6285 - distribution_lambda_26_loss: 0.2839 - distribution_lambda_27_loss: 1.1172 - distribution_lambda_28_loss: 0.2274 - val_loss: 1.8219 - val_distribution_lambda_26_loss: 0.4192 - val_distribution_lambda_27_loss: 1.1207 - val_distribution_lambda_28_loss: 0.2820\n", "Epoch 1420/2500\n", "8/8 [==============================] - 0s 6ms/step - loss: 1.5751 - distribution_lambda_26_loss: 0.2813 - distribution_lambda_27_loss: 1.0689 - distribution_lambda_28_loss: 0.2249 - val_loss: 1.8140 - val_distribution_lambda_26_loss: 0.4139 - val_distribution_lambda_27_loss: 1.1180 - val_distribution_lambda_28_loss: 0.2821\n" ] } ], "source": [ "load_model_gk = True# load scaler and model weights for goalkeeper player predictor\n", "refit_model_gk = True\n", "\n", "if(load_model_gk):\n", " scaler_gk = pickle.load(open('saves/scaler_gk.pkl', 'rb'))\n", " \n", " X_gk_train = scaler_gk.transform(X_gk_train_)\n", " X_gk_test = scaler_gk.transform(X_gk_test_)\n", " \n", " \n", "n_epochs = 2500\n", "\n", "n_samples = X_gk_train.shape[0]\n", "\n", "batch_size = 128\n", "\n", "X_gk_len = X_gk_train.shape[1]\n", "y_gk_len = y_gk_train.shape[1]\n", "\n", "\n", "#tailweight_param = 1.1\n", "\n", "tailweight_min = 0.5\n", "tailweight_range = 1.1\n", "\n", "\n", "callback = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience = 30)\n", "neg_log_likelihood = lambda x, rv_x: -rv_x.log_prob(x)\n", "\n", "\n", "inputs = tfk.layers.Input(shape=(X_gk_len,), name=\"input\")\n", "x = tfk.layers.Dense(16, activation=\"relu\") (inputs)\n", "x = tfk.layers.Dropout(0.2)(x)\n", "x = tfk.layers.Dense(16, activation=\"relu\") (x)\n", "\n", "\n", "prob_dist_params = 4\n", "\n", "def prob_dist(t): \n", " return tfp.distributions.SinhArcsinh(loc=t[..., 0], scale=1e-3 + tf.math.softplus(t[..., 1]), skewness = t[..., 2], \n", " tailweight = tailweight_min + tailweight_range * tf.math.sigmoid(t[..., 3]),\n", " allow_nan_stats = False)\n", "\n", "x1 = tfk.layers.Dense(8, activation=\"sigmoid\")(x)\n", "x1 = tfk.layers.Dense(prob_dist_params, activation=\"linear\")(x1)\n", "out_1 = tfp.layers.DistributionLambda(prob_dist)(x1)\n", "\n", "x2 = tfk.layers.Dense(16, activation=\"sigmoid\")(x)\n", "\n", "x22 = tfk.layers.Dense(prob_dist_params, activation=\"linear\")(x2)\n", "out_2 = tfp.layers.DistributionLambda(prob_dist)(x22)\n", "\n", "x23 = tfk.layers.Dense(1, activation=\"sigmoid\")(x2)\n", "out_3 = tfp.layers.DistributionLambda(lambda t: tfp.distributions.Bernoulli(probs = t[..., 0]))(x23)\n", "\n", "\n", "modelb_gk = tf.keras.Model(inputs, [out_1, out_2, out_3])\n", "\n", "modelb_gk.compile(optimizer=tf.keras.optimizers.Nadam(learning_rate = 0.001), \n", " loss=neg_log_likelihood)\n", "\n", "if(load_model_gk):\n", " modelb_gk.load_weights('saves/modelb_gk')\n", "\n", "if( (not load_model_gk) or refit_model_gk): \n", " modelb_gk.fit(X_gk_train.astype('float32'), [y_gk_train[:, 0].astype('float32'), y_gk_train[:, 1].astype('float32'), y_gk_train[:, 2].astype('int')], \n", " validation_data = (X_gk_test.astype('float32'), [y_gk_test[:, 0].astype('float32'), y_gk_test[:, 1].astype('float32'), y_gk_test[:, 2].astype('int')]),\n", " batch_size = batch_size, shuffle = True, epochs=n_epochs, verbose=True, callbacks = [callback])" ] }, { "cell_type": "code", "execution_count": 47, "id": "39a9bdc6", "metadata": {}, "outputs": [], "source": [ "def sample_predict_gk(X, iterations = 100):\n", " y = np.zeros((3, X.shape[0]))\n", " \n", " dist = modelb_gk(X)\n", " \n", " for i in range(iterations):\n", " y[0, :] += dist[0].sample()\n", " y[1, :] += dist[1].sample()\n", " y[2, :] += dist[2].sample()\n", " \n", " return y.transpose() / iterations\n" ] }, { "cell_type": "code", "execution_count": 56, "id": "c41cf448", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0.26941154847581295\n", "0.6648856762830053\n" ] }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "0.28428997092873365\n", "0.5972433047845432\n" ] }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "y_gk_train_predict = sample_predict_gk(X_gk_train)\n", "\n", "plt.plot([0, 20], [0, 20])\n", "\n", "plt.scatter(y_gk_train[:, 0], y_gk_train_predict[:, 0], color = 'orange', edgecolors = 'black', s = 20)\n", "plt.scatter(y_gk_train[:, 1], y_gk_train_predict[:, 1], color = 'green', edgecolors = 'black', s = 20)\n", "\n", "print(r2_score(y_gk_train[:, 0], y_gk_train_predict[:, 0]))\n", "print(r2_score(y_gk_train[:, 1], y_gk_train_predict[:, 1]))\n", "\n", "plt.show()\n", "\n", "y_gk_test_predict = sample_predict_gk(X_gk_test)\n", "\n", "plt.plot([0, 20], [0, 20])\n", "\n", "plt.scatter(y_gk_test[:, 0], y_gk_test_predict[:, 0], color = 'orange', edgecolors = 'black', s = 20)\n", "plt.scatter(y_gk_test[:, 1], y_gk_test_predict[:, 1], color = 'green', edgecolors = 'black', s = 20)\n", "\n", "print(r2_score(y_gk_test[:, 0], y_gk_test_predict[:, 0]))\n", "print(r2_score(y_gk_test[:, 1], y_gk_test_predict[:, 1]))\n", "\n", "\n" ] }, { "cell_type": "markdown", "id": "91869883", "metadata": {}, "source": [ "Use the following codes to save the scalers and the model weights" ] }, { "cell_type": "code", "execution_count": 57, "id": "cecf5392", "metadata": {}, "outputs": [], "source": [ "save_model_of = True\n", "save_model_gk = True\n", "\n", "if(save_model_of):\n", " pickle.dump(scaler, open('saves/scaler.pkl', 'wb'))\n", " modelb.save_weights('saves/modelb')\n", " \n", "if(save_model_gk):\n", " pickle.dump(scaler_gk, open('saves/scaler_gk.pkl', 'wb'))\n", " modelb_gk.save_weights('saves/modelb_gk')\n", " " ] }, { "cell_type": "markdown", "id": "32635a0e", "metadata": {}, "source": [ "Generalized prediction function for a player (playing for team against opp_team, at home or not)\n", "\n", "Estimate prediction mean and sigma (using a custom definitions).\n", "\n", "Generate a plot.\n" ] }, { "cell_type": "code", "execution_count": 21, "id": "ddf433f9", "metadata": {}, "outputs": [], "source": [ "def vote_predict_NNb(player, team, opp_team, home = 1, plot = 0, log = 0, oldseason = False):\n", " if(players['r'][player] == 'P'):\n", " ptest = player_match_data_ext_gk(player, team, opp_team, oldseason = oldseason)\n", "\n", " x_ptest = np.array(ptest)[:, 3:]\n", " r = np.array(ptest)[0, 0]\n", "\n", " # add home and role\n", " xadd = np.zeros((1, 1))\n", " xadd[0, 0] = home\n", "\n", " x_ptest = np.concatenate((x_ptest, xadd), axis = 1)\n", "\n", " x_scaled = scaler_gk.transform(x_ptest)\n", "\n", " dist = modelb_gk(x_scaled)\n", " \n", " clean_shoot_prob = dist[2].probs.numpy()[0]\n", " else:\n", " ptest = player_match_data_ext(player, team, opp_team, oldseason = oldseason)\n", "\n", " x_ptest = np.array(ptest)[:, 4:]\n", " r = np.array(ptest)[0, 0]\n", "\n", " # add home and role\n", " xadd = np.zeros((1, 4))\n", " xadd[0, 0] = home\n", " xadd[0, 1] = r == 'D'\n", " xadd[0, 2] = r == 'C'\n", " xadd[0, 3] = r == 'A'\n", "\n", " x_ptest = np.concatenate((x_ptest, xadd), axis = 1)\n", "\n", " x_scaled = scaler.transform(x_ptest)\n", "\n", " dist = modelb(x_scaled)\n", " \n", " \n", " x = np.arange(0, 40, 0.002)\n", "\n", " px1 = dist[0].prob(x);\n", " px2 = dist[1].prob(x);\n", "\n", " \n", " #sample1 = dist[0].sample(10000)\n", " #sample2 = dist[1].sample(10000)\n", " \n", " m1 = np.average(x, weights = px1)\n", " m2 = np.average(x, weights = px2)\n", " \n", " #m1 = np.mean(sample1)\n", " #m2 = np.mean(sample2)\n", " \n", " #s1 = np.std(sample1)\n", " #s2 = np.std(sample2)\n", " \n", " # not standard deviation, but expected range extimated by quantile \n", " \n", " if(players['r'][player] == 'P'):\n", " s1 = ( dist[0].quantile(0.9545) - m1 ) / 2\n", " s2 = -( dist[1].quantile(1 - 0.9) - m2 ) / 2\n", " else:\n", " s1 = ( dist[0].quantile(0.9545) - m1 ) / 2\n", " s2 = ( dist[1].quantile(0.9) - m2 ) / 2\n", " \n", "\n", " \n", " #y_pred_m = np.array([dist[0].loc, dist[1].loc]).flatten()\n", " y_pred_m = np.array([m1, m2]).flatten()\n", " #y_pred_s = np.array([dist[0].scale, dist[1].scale]).flatten()\n", " y_pred_s = np.array([s1, s2]).flatten()\n", " \n", " clean_sheet_text = ''\n", " if(players['r'][player] == 'P'):\n", " clean_sheet_text = ' (' + \"{:.1f}\".format(clean_shoot_prob*100) + '% cs)'\n", " \n", " if(plot):\n", " ax = plt.gca()\n", " \n", " plt.plot(x, px1, \n", " label = 'MV ' + \"{:.2f}\".format(y_pred_m[0]) + ' ± ' + \"{:.2f}\".format(2 * y_pred_s[0]),\n", " color = 'b')\n", " plt.plot(x, px2, \n", " label = 'FV ' + \"{:.2f}\".format(y_pred_m[1]) + ' + ' + \"{:.2f}\".format(2 * y_pred_s[1]) + clean_sheet_text,\n", " color = 'g')\n", " \n", " plt.fill_between(x, px1, color = 'lightblue')\n", " plt.fill_between(x, px2, color = 'lightgreen')\n", " \n", " plt.legend()\n", " \n", " plt.vlines(x = y_pred_m[0], color = 'b', ymin = 0, ymax = 3, linestyle = 'dashed')\n", " plt.vlines(x = y_pred_m[1], color = 'g', ymin = 0, ymax = 3, linestyle = 'dashed')\n", " \n", " plt.title(player + ' (' + team + ' vs ' + opp_team + ')')\n", " \n", " plt.xlim([0, 15])\n", " \n", " if(players['r'][player] == 'P'): \n", " plt.ylim([0, 2.5])\n", " else:\n", " plt.ylim([0, 1.5])\n", " \n", " plt.show()\n", " \n", " if(log):\n", " print(player + ': ' + \n", " 'MV ' + \"{:.2f}\".format(y_pred_m[0]) + ' ± ' + \"{:.2f}\".format(2 * y_pred_s[0]) +\n", " '; FV ' + \"{:.2f}\".format(y_pred_m[1]) + ' + ' + \"{:.2f}\".format(2 * y_pred_s[1]) + clean_sheet_text);\n", " return [y_pred_m, y_pred_s, dist]\n" ] }, { "cell_type": "markdown", "id": "98817aa0", "metadata": {}, "source": [ "Load Serie A calendar. " ] }, { "cell_type": "code", "execution_count": 22, "id": "d31bad38", "metadata": {}, "outputs": [], "source": [ "cal = np.array(pd.read_excel('fantacalcio/seriea_calendar.xlsx', header = None))\n", "\n", "cal_df = pd.DataFrame(columns = ['matchday', 'team1', 'team2'])\n", "\n", "matchday = 0\n", "\n", "for i in range(cal.shape[0]):\n", " if(cal[i, 0][0].isnumeric()):\n", " matchday = matchday + 1\n", " continue\n", " \n", " teams = cal[i, 0].split('-')\n", " \n", " frame = pd.DataFrame([[matchday, teams[0], teams[1]]], columns = cal_df.columns)\n", "\n", " cal_df = pd.concat([cal_df, frame], ignore_index = True)\n", " " ] }, { "cell_type": "code", "execution_count": 23, "id": "62b9f588", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
matchdayteam1team2
01FiorentinaCremonese
11VeronaNapoli
21JuventusSassuolo
31LazioBologna
41LecceInter
............
37538LecceBologna
37638SassuoloFiorentina
37738MilanVerona
37838TorinoInter
37938UdineseJuventus
\n", "

380 rows × 3 columns

\n", "
" ], "text/plain": [ " matchday team1 team2\n", "0 1 Fiorentina Cremonese\n", "1 1 Verona Napoli\n", "2 1 Juventus Sassuolo\n", "3 1 Lazio Bologna\n", "4 1 Lecce Inter\n", ".. ... ... ...\n", "375 38 Lecce Bologna\n", "376 38 Sassuolo Fiorentina\n", "377 38 Milan Verona\n", "378 38 Torino Inter\n", "379 38 Udinese Juventus\n", "\n", "[380 rows x 3 columns]" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "cal_df" ] }, { "cell_type": "markdown", "id": "62872819", "metadata": {}, "source": [ "Function for generating a prediction for a player, taking match data from a given matchday, according to Serie A calendar." ] }, { "cell_type": "code", "execution_count": 24, "id": "c58ba41d", "metadata": {}, "outputs": [], "source": [ "def PlayerMatch(player, match = 0):\n", " team = players.loc[player]['team']\n", " \n", " if(match == 0):\n", " oppteam = 'Avg'\n", " home = 1\n", " else:\n", " for i in range (cal_df.shape[0]):\n", " if(cal_df['matchday'][i] == match):\n", " if(cal_df['team1'][i] == team):\n", " home = 1\n", " oppteam = cal_df['team2'][i]\n", " elif(cal_df['team2'][i] == team):\n", " home = 0\n", " oppteam = cal_df['team1'][i]\n", " \n", " return [player, team, oppteam, home]\n", "\n", "def predict_player(player, match = 0, plot = 0, log = 0, oldseason = False):\n", " [player, team, oppteam, home] = PlayerMatch(player, match)\n", " return vote_predict_NNb(player, team, oppteam, home = home, plot = plot, log = log, oldseason = oldseason)" ] }, { "cell_type": "markdown", "id": "e8b63a98", "metadata": {}, "source": [ "Load current matchday playing probabilities for Serie A players." ] }, { "cell_type": "code", "execution_count": 25, "id": "f79792b6", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
starterpercentage
player
Tatarusanu1.0090
Thiaw0.6565
Kjaer1.0085
Kalulu1.0090
Saelemaekers0.6060
.........
Dumfries0.4560
Mkhitaryan0.4555
Asllani0.0030
Gagliardini0.0050
Lukaku0.4060
\n", "

438 rows × 2 columns

\n", "
" ], "text/plain": [ " starter percentage\n", "player \n", "Tatarusanu 1.00 90\n", "Thiaw 0.65 65\n", "Kjaer 1.00 85\n", "Kalulu 1.00 90\n", "Saelemaekers 0.60 60\n", "... ... ...\n", "Dumfries 0.45 60\n", "Mkhitaryan 0.45 55\n", "Asllani 0.00 30\n", "Gagliardini 0.00 50\n", "Lukaku 0.40 60\n", "\n", "[438 rows x 2 columns]" ] }, "execution_count": 25, "metadata": {}, "output_type": "execute_result" } ], "source": [ "probables = pd.read_excel('mid_outputs/match_probable_players.xlsx', index_col = 0) \n", "\n", "probables" ] }, { "cell_type": "markdown", "id": "e4751014", "metadata": {}, "source": [ "Generate prediction data for each Serie A player for the current matchday.\n", "\n", "Output to excel file, using a template made for data elaboration." ] }, { "cell_type": "code", "execution_count": 58, "id": "5e63c2b7", "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Meret: MV 6.24 ± 0.83; FV 5.81 + 0.85 (56.5% cs)\n", "Provedel: MV 6.24 ± 0.83; FV 4.69 + 1.04 (0.9% cs)\n", "Vicario: MV 6.24 ± 0.83; FV 5.24 + 0.81 (22.3% cs)\n", "Szczesny: MV 6.24 ± 0.83; FV 5.41 + 1.14 (20.8% cs)\n", "Falcone: MV 6.24 ± 0.83; FV 5.10 + 0.81 (1.3% cs)\n", "Silvestri: MV 6.24 ± 0.83; FV 6.32 + 0.70 (90.3% cs)\n", "Rui Patricio: MV 6.24 ± 0.83; FV 5.21 + 1.01 (36.2% cs)\n", "Onana: MV 6.24 ± 0.83; FV 5.92 + 0.68 (75.7% cs)\n", "Sepe: MV 6.24 ± 0.83; FV 5.12 + 0.83 (15.6% cs)\n", "Milinkovic-Savic V.: MV 6.24 ± 0.83; FV 5.00 + 0.95 (11.2% cs)\n", "Musso: MV 6.24 ± 0.83; FV 3.81 + 1.49 (0.6% cs)\n", "Maignan: MV 6.24 ± 0.83; FV 6.00 + 0.73 (73.6% cs)\n", "Carnesecchi: MV 6.24 ± 0.83; FV 4.57 + 1.04 (0.2% cs)\n", "Di Gregorio: MV 6.25 ± 0.82; FV 4.11 + 1.48 (1.1% cs)\n", "Audero: MV 6.24 ± 0.83; FV 4.55 + 1.06 (0.6% cs)\n", "Montipo': MV 6.24 ± 0.83; FV 4.98 + 0.94 (6.1% cs)\n", "Skorupski: MV 6.24 ± 0.83; FV 4.59 + 0.97 (0.3% cs)\n", "Consigli: MV 6.24 ± 0.83; FV 4.17 + 1.27 (0.2% cs)\n", "Dragowski: MV 6.24 ± 0.83; FV 5.35 + 0.75 (19.2% cs)\n", "Terracciano: MV 6.24 ± 0.83; FV 4.16 + 1.30 (0.1% cs)\n", "Tatarusanu: MV 6.24 ± 0.83; FV 4.59 + 1.26 (1.1% cs)\n", "Handanovic: MV 6.24 ± 0.83; FV 5.88 + 0.68 (73.4% cs)\n", "Sportiello: MV 6.23 ± 0.83; FV 3.84 + 1.56 (0.6% cs)\n", "Perin: MV 6.25 ± 0.83; FV 5.67 + 1.10 (36.8% cs)\n", "Zoet: MV 6.24 ± 0.83; FV 4.94 + 0.82 (6.0% cs)\n", "Ochoa: MV 6.24 ± 0.83; FV 4.69 + 0.90 (2.1% cs)\n", "Pegolo: MV 6.19 ± 0.84; FV 3.81 + 1.55 (0.2% cs)\n", "Gollini: MV 6.24 ± 0.83; FV 5.18 + 0.91 (12.0% cs)\n", "Mirante no data\n", "Sarr M. no data\n", "Lamanna no data\n", "Ujkani no data\n", "Berisha: MV 6.24 ± 0.83; FV 5.34 + 0.97 (24.2% cs)\n", "Marchetti no data\n", "Perilli no data\n", "Padelli: MV 6.24 ± 0.83; FV 4.85 + 0.92 (0.8% cs)\n", "Perisan no data\n", "Bardi: MV 6.24 ± 0.83; FV 4.52 + 1.11 (1.2% cs)\n", "Cordaz no data\n", "Pinsoglio: MV 6.24 ± 0.83; FV 4.93 + 0.88 (5.9% cs)\n", "Fiorillo: MV 6.24 ± 0.83; FV 4.54 + 1.12 (0.1% cs)\n", "Cragno: MV 6.24 ± 0.83; FV 4.31 + 1.32 (0.0% cs)\n", "Sirigu: MV 6.24 ± 0.83; FV 4.39 + 1.28 (0.0% cs)\n", "Cerofolini no data\n", "Rossi F.: MV 6.24 ± 0.83; FV 4.15 + 1.31 (0.1% cs)\n", "Ravaglia F. no data\n", "Brancolini no data\n", "Bleve no data\n", "Berardi A.: MV 6.24 ± 0.83; FV 4.39 + 1.22 (0.1% cs)\n", "Russo A. no data\n", "Gemello: MV 6.24 ± 0.83; FV 6.00 + 0.89 (75.0% cs)\n", "Ravaglia: MV 6.24 ± 0.83; FV 4.33 + 1.32 (0.0% cs)\n", "Boer no data\n", "Adamonis no data\n", "Marfella: MV 6.24 ± 0.83; FV 5.68 + 0.90 (40.5% cs)\n", "Zovko: MV 6.24 ± 0.83; FV 4.84 + 0.84 (1.3% cs)\n", "Piana no data\n", "Bagnolini no data\n", "Luis Maximiano: MV 6.10 ± 0.86; FV 4.82 + 1.71 (56.1% cs)\n", "Svilar no data\n", "Sorrentino A. no data\n", "Ciezkowski no data\n", "Saro no data\n", "Vasquez D. no data\n", "Turk no data\n", "Dimarco: MV 6.29 ± 0.95; FV 6.93 + 2.01\n", "Smalling: MV 6.22 ± 1.00; FV 6.64 + 1.69\n", "Doig: MV 6.32 ± 1.21; FV 7.07 + 2.57\n", "Carlos Augusto: MV 6.04 ± 1.05; FV 6.52 + 2.02\n", "Kim: MV 6.32 ± 0.94; FV 6.85 + 1.93\n", "Posch: MV 6.17 ± 1.20; FV 6.96 + 2.72\n", "Di Lorenzo: MV 6.24 ± 0.80; FV 6.70 + 1.63\n", "Danilo: MV 6.27 ± 0.94; FV 6.74 + 1.77\n", "Hernandez T.: MV 6.04 ± 1.15; FV 6.44 + 1.95\n", "Udogie: MV 6.15 ± 1.10; FV 6.75 + 2.24\n", "Parisi: MV 6.28 ± 0.90; FV 6.93 + 1.99\n", "Mario Rui: MV 6.23 ± 0.79; FV 6.57 + 1.45\n", "Romagnoli: MV 6.13 ± 0.99; FV 6.30 + 1.31\n", "Bastoni S.: MV 6.15 ± 0.95; FV 6.54 + 1.64\n", "Mazzocchi: MV 6.18 ± 1.05; FV 6.69 + 1.95\n", "Valeri: MV 5.93 ± 0.81; FV 6.08 + 0.99\n", "Tomori: MV 6.13 ± 0.91; FV 6.40 + 1.32\n", "Scalvini: MV 5.82 ± 1.11; FV 5.97 + 1.53\n", "Toloi: MV 5.99 ± 0.97; FV 6.18 + 1.29\n", "Demiral: MV 5.83 ± 0.90; FV 5.92 + 1.15\n", "Maehle: MV 5.83 ± 1.00; FV 5.94 + 1.35\n", "Dumfries: MV 6.22 ± 1.09; FV 6.79 + 2.06\n", "Baschirotto: MV 6.17 ± 1.06; FV 6.57 + 1.81\n", "Bijol: MV 6.00 ± 1.01; FV 6.29 + 1.61\n", "Schuurs: MV 6.16 ± 0.81; FV 6.36 + 1.17\n", "Juan Jesus: MV 6.19 ± 0.70; FV 6.51 + 1.31\n", "Depaoli: MV 6.07 ± 1.04; FV 6.54 + 1.96\n", "Mancini: MV 6.10 ± 0.72; FV 6.14 + 0.80\n", "Ibanez: MV 6.09 ± 1.00; FV 6.44 + 1.57\n", "Rodrigo Becao: MV 6.16 ± 0.88; FV 6.41 + 1.29\n", "Ebuehi: MV 6.17 ± 0.80; FV 6.55 + 1.41\n", "Gosens: MV 6.09 ± 0.66; FV 6.41 + 1.16\n", "Darmian: MV 6.18 ± 0.80; FV 6.68 + 1.61\n", "Reca: MV 6.03 ± 1.02; FV 6.31 + 1.56\n", "Bremer: MV 6.08 ± 1.02; FV 6.32 + 1.43\n", "Sernicola: MV 5.78 ± 0.84; FV 5.86 + 1.03\n", "Rrahmani: MV 6.30 ± 0.91; FV 6.83 + 1.87\n", "Vojvoda: MV 6.02 ± 0.99; FV 6.26 + 1.48\n", "Holm: MV 6.06 ± 0.87; FV 6.28 + 1.28\n", "Bastoni: MV 6.17 ± 0.83; FV 6.30 + 1.08\n", "Milenkovic: MV 5.84 ± 1.08; FV 5.92 + 1.41\n", "Kalulu: MV 5.82 ± 1.04; FV 5.84 + 1.14\n", "Martinez Quarta: MV 5.90 ± 1.03; FV 5.98 + 1.21\n", "Casale: MV 5.94 ± 0.94; FV 6.01 + 1.20\n", "Perez N.: MV 6.09 ± 0.87; FV 6.13 + 0.97\n", "Olivera: MV 6.17 ± 0.70; FV 6.58 + 1.42\n", "Izzo: MV 5.93 ± 0.79; FV 5.93 + 0.75\n", "Luperto: MV 6.13 ± 0.93; FV 6.32 + 1.23\n", "Skriniar: MV 6.02 ± 0.74; FV 5.97 + 0.69\n", "Rodriguez R.: MV 5.96 ± 0.87; FV 5.98 + 0.97\n", "Marusic: MV 5.99 ± 0.81; FV 6.02 + 0.88\n", "Lazzari: MV 6.03 ± 0.85; FV 6.07 + 0.95\n", "Kyriakopoulos: MV 5.99 ± 0.94; FV 6.08 + 1.15\n", "Ampadu: MV 5.88 ± 0.88; FV 5.88 + 1.02\n", "Ismajli: MV 6.15 ± 0.74; FV 6.16 + 0.85\n", "Llorente D.: MV 5.98 ± 0.98; FV 6.19 + 1.35\n", "Cambiaso: MV 6.00 ± 0.81; FV 6.02 + 0.87\n", "Hysaj: MV 5.96 ± 0.71; FV 6.00 + 0.73\n", "Biraghi: MV 5.96 ± 0.75; FV 5.97 + 0.72\n", "Medel: MV 5.99 ± 0.78; FV 5.92 + 0.73\n", "Bonucci: MV 6.20 ± 0.97; FV 6.66 + 1.78\n", "Calabria: MV 5.95 ± 1.00; FV 6.17 + 1.48\n", "Acerbi: MV 6.15 ± 0.74; FV 6.24 + 0.94\n", "Spinazzola: MV 5.95 ± 0.66; FV 6.03 + 0.65\n", "Lykogiannis: MV 6.01 ± 0.71; FV 6.08 + 0.79\n", "Pellegrini Lu.: MV 6.02 ± 0.77; FV 6.06 + 0.86\n", "Djidji: MV 5.87 ± 1.01; FV 5.99 + 1.42\n", "Lazaro: MV 5.91 ± 1.06; FV 6.07 + 1.40\n", "Augello: MV 5.68 ± 0.90; FV 5.72 + 1.07\n", "Gallo: MV 5.96 ± 0.75; FV 5.93 + 0.72\n", "Singo: MV 6.03 ± 0.91; FV 6.24 + 1.33\n", "Mari': MV 5.80 ± 1.11; FV 5.90 + 1.49\n", "Caldirola: MV 5.77 ± 0.96; FV 5.72 + 0.97\n", "Dodo': MV 5.77 ± 0.95; FV 5.65 + 0.95\n", "De Vrij: MV 6.05 ± 0.78; FV 6.14 + 0.89\n", "Patric: MV 6.00 ± 0.93; FV 6.01 + 1.00\n", "Faraoni: MV 6.04 ± 0.83; FV 6.32 + 1.33\n", "Ceccherini: MV 5.96 ± 0.96; FV 6.12 + 1.35\n", "Hateboer: MV 5.73 ± 0.86; FV 5.75 + 1.02\n", "Rogerio: MV 5.77 ± 0.93; FV 5.74 + 1.09\n", "Umtiti: MV 5.92 ± 1.03; FV 6.00 + 1.18\n", "Aina: MV 6.00 ± 1.03; FV 6.25 + 1.51\n", "Birindelli: MV 5.80 ± 0.74; FV 5.80 + 0.80\n", "Lucumi': MV 5.94 ± 0.84; FV 5.91 + 0.89\n", "Ehizibue: MV 5.93 ± 0.92; FV 6.20 + 1.55\n", "Bianchetti: MV 5.54 ± 1.02; FV 5.60 + 1.15\n", "Ferrari G.: MV 5.71 ± 1.10; FV 5.78 + 1.40\n", "Fazio: MV 5.80 ± 1.31; FV 6.05 + 1.86\n", "Gravillon: MV 5.92 ± 1.00; FV 6.06 + 1.41\n", "Buongiorno: MV 5.88 ± 0.89; FV 5.87 + 0.97\n", "Gunter: MV 5.66 ± 1.00; FV 5.62 + 1.15\n", "Troost-Ekong: MV 5.86 ± 1.14; FV 5.93 + 1.39\n", "Soumaoro: MV 5.88 ± 0.98; FV 5.86 + 1.01\n", "Ceccaroni: MV 5.93 ± 1.03; FV 6.05 + 1.34\n", "Pongracic: MV 5.96 ± 0.78; FV 5.93 + 0.76\n", "Soppy: MV 5.77 ± 0.76; FV 5.81 + 0.84\n", "Gendrey: MV 5.82 ± 0.70; FV 5.80 + 0.63\n", "Hien: MV 5.91 ± 0.81; FV 5.87 + 0.83\n", "Ferrari A.: MV 5.57 ± 1.18; FV 5.61 + 1.33\n", "Masina: MV 6.10 ± 1.06; FV 6.62 + 2.09\n", "Zappacosta: MV 5.93 ± 0.79; FV 6.08 + 1.03\n", "Gyomber: MV 5.83 ± 0.85; FV 5.78 + 0.82\n", "Alex Sandro: MV 5.82 ± 0.91; FV 5.76 + 0.84\n", "Pezzella Giu.: MV 5.90 ± 0.68; FV 5.91 + 0.60\n", "Bereszynski: MV 6.00 ± 0.65; FV 5.95 + 0.56\n", "Venuti: MV 5.75 ± 0.83; FV 5.73 + 0.85\n", "Palomino: MV 5.86 ± 1.01; FV 5.92 + 1.19\n", "Nuytinck: MV 5.71 ± 1.10; FV 5.68 + 1.25\n", "Marlon: MV 5.78 ± 0.76; FV 5.75 + 0.72\n", "Magnani: MV 5.95 ± 0.84; FV 5.89 + 0.84\n", "Colley: MV 5.67 ± 1.14; FV 5.68 + 1.36\n", "Nikolaou: MV 5.74 ± 0.79; FV 5.64 + 0.77\n", "Terzic: MV 6.00 ± 0.56; FV 5.93 + 0.40\n", "Igor: MV 5.75 ± 0.98; FV 5.60 + 0.94\n", "Toljan: MV 5.65 ± 0.86; FV 5.60 + 0.91\n", "Zortea: MV 5.80 ± 0.84; FV 5.88 + 1.10\n", "Dawidowicz: MV 5.87 ± 0.97; FV 5.90 + 1.23\n", "Celik: MV 5.81 ± 0.74; FV 5.81 + 0.68\n", "Bellanova: MV 6.05 ± 0.78; FV 6.18 + 0.93\n", "Erlic: MV 5.75 ± 1.06; FV 5.71 + 1.18\n", "Ballo-Toure': MV 6.14 ± 0.79; FV 6.51 + 1.35\n", "Dest: MV 5.79 ± 0.83; FV 5.78 + 0.80\n", "Stojanovic: MV 5.90 ± 0.76; FV 5.91 + 0.76\n", "Amian: MV 5.80 ± 0.81; FV 5.74 + 0.85\n", "Bradaric: MV 5.75 ± 0.83; FV 5.73 + 0.98\n", "Daniliuc: MV 5.81 ± 1.08; FV 5.86 + 1.33\n", "Zima: MV 5.87 ± 0.94; FV 5.90 + 1.12\n", "De Winter: MV 5.94 ± 0.76; FV 5.87 + 0.67\n", "Quagliata: MV 5.73 ± 0.71; FV 5.73 + 0.68\n", "Ebosse: MV 5.75 ± 0.72; FV 5.69 + 0.64\n", "Aiwu: MV 5.70 ± 1.06; FV 5.75 + 1.30\n", "Lochoshvili: MV 5.58 ± 0.90; FV 5.54 + 0.96\n", "Bronn: MV 5.80 ± 0.70; FV 5.78 + 0.61\n", "Thiaw: MV 5.99 ± 0.83; FV 5.97 + 0.80\n", "Zeefuik: MV 5.98 ± 0.86; FV 6.06 + 1.03\n", "Romagnoli S.: MV 5.98 ± 1.15; FV 6.30 + 1.81\n", "Ghiglione: MV 5.67 ± 0.97; FV 5.69 + 1.15\n", "Rugani: MV 6.04 ± 0.62; FV 5.98 + 0.52\n", "De Sciglio: MV 5.94 ± 0.66; FV 5.94 + 0.57\n", "Djimsiti: MV 5.80 ± 0.79; FV 5.81 + 0.80\n", "Caldara: MV 5.79 ± 0.96; FV 5.73 + 1.01\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Karsdorp: MV 5.88 ± 0.79; FV 5.90 + 0.74\n", "Marchizza: MV 5.75 ± 0.76; FV 5.71 + 0.79\n", "Kjaer: MV 5.87 ± 0.72; FV 5.83 + 0.63\n", "Okoli: MV 5.59 ± 0.92; FV 5.53 + 0.89\n", "Amione: MV 5.52 ± 0.85; FV 5.45 + 0.88\n", "Ruggeri: MV 5.71 ± 0.65; FV 5.73 + 0.54\n", "Zanoli: MV 5.70 ± 0.81; FV 5.63 + 0.83\n", "Wisniewski: MV 5.95 ± 0.87; FV 6.00 + 1.03\n", "Radovanovic: MV 5.68 ± 0.75; FV 5.60 + 0.71\n", "Dermaku: MV 5.93 ± 0.88; FV 5.98 + 1.05\n", "D'ambrosio: MV 6.16 ± 0.68; FV 6.39 + 1.11\n", "De Silvestri: MV 5.95 ± 0.99; FV 6.14 + 1.46\n", "Chiriches: MV 5.58 ± 1.22; FV 5.54 + 1.24\n", "Murru: MV 5.50 ± 0.82; FV 5.44 + 0.84\n", "Bonifazi: MV 5.83 ± 0.83; FV 5.74 + 0.82\n", "Donati: MV 5.75 ± 0.89; FV 5.71 + 0.94\n", "Walukiewicz: MV 5.91 ± 0.70; FV 5.91 + 0.62\n", "Ranieri L.: MV 5.78 ± 0.85; FV 5.77 + 1.01\n", "Gabbia: MV 5.65 ± 0.90; FV 5.57 + 0.87\n", "Kumbulla: MV 5.87 ± 0.65; FV 5.90 + 0.56\n", "Adopo: MV 5.75 ± 0.66; FV 5.66 + 0.67\n", "Pirola: MV 5.63 ± 0.90; FV 5.54 + 0.92\n", "Lovato: MV 5.73 ± 1.03; FV 5.63 + 1.05\n", "Tuia: MV 5.80 ± 0.90; FV 5.82 + 1.11\n", "Ferrer: MV 5.90 ± 0.89; FV 5.90 + 0.98\n", "Antov: MV 5.69 ± 1.06; FV 5.66 + 1.13\n", "Vasquez: MV 5.62 ± 1.00; FV 5.60 + 1.12\n", "Ruan: MV 5.70 ± 1.07; FV 5.55 + 1.00\n", "Ostigard: MV 6.13 ± 0.64; FV 6.09 + 0.68\n", "Coppola D.: MV 5.80 ± 0.74; FV 5.71 + 0.73\n", "Cacace: MV 5.94 ± 0.72; FV 5.90 + 0.63\n", "Gatti: MV 5.95 ± 0.77; FV 5.93 + 0.72\n", "Gila: MV 5.90 ± 0.88; FV 5.89 + 0.95\n", "Bayeye: MV 5.91 ± 0.99; FV 6.03 + 1.38\n", "Sambia: MV 5.83 ± 0.80; FV 5.83 + 0.79\n", "Moutinho J.: MV 5.79 ± 0.81; FV 5.72 + 0.84\n", "Conti: MV 5.79 ± 0.90; FV 5.84 + 1.12\n", "Marrone: MV 5.55 ± 0.92; FV 5.47 + 0.95\n", "Tonelli: MV 5.88 ± 0.76; FV 5.83 + 0.67\n", "Murillo: MV 5.54 ± 0.73; FV 5.44 + 0.72\n", "Radu: MV 6.05 ± 0.74; FV 5.91 + 0.63\n", "Paletta: MV 5.84 ± 0.94; FV 5.88 + 1.14\n", "Florenzi: MV 6.15 ± 0.83; FV 6.39 + 1.19\n", "Sala: MV 5.93 ± 0.73; FV 5.95 + 0.78\n", "Fares: MV 5.79 ± 0.80; FV 5.78 + 0.93\n", "Romagna: MV 5.82 ± 0.98; FV 5.84 + 1.22\n", "Cassandro: MV 5.92 ± 0.87; FV 5.99 + 1.06\n", "Muldur: MV 5.69 ± 0.86; FV 5.65 + 0.94\n", "Amey: MV 6.04 ± 0.87; FV 6.12 + 1.04\n", "Zanotti: MV 6.10 ± 0.81; FV 6.27 + 1.07\n", "Ebosele: MV 6.03 ± 0.66; FV 5.99 + 0.59\n", "Buta: MV 5.95 ± 0.86; FV 5.97 + 0.90\n", "Abankwah: MV 5.95 ± 0.86; FV 5.97 + 0.90\n", "Guessand A.: MV 5.95 ± 0.86; FV 5.97 + 0.90\n", "Cabal: MV 6.00 ± 0.89; FV 6.09 + 1.07\n", "Sosa: MV 5.76 ± 0.96; FV 5.75 + 1.10\n", "Guarino: MV 6.06 ± 0.81; FV 6.19 + 1.00\n", "Carboni F.: MV 5.90 ± 0.92; FV 5.97 + 1.06\n", "Zaccagni: MV 6.40 ± 1.33; FV 7.40 + 3.24\n", "Kvaratskhelia: MV 6.64 ± 1.45; FV 7.60 + 3.27\n", "Milinkovic-Savic: MV 6.28 ± 1.28; FV 7.06 + 2.80\n", "Barella: MV 6.38 ± 1.15; FV 7.20 + 2.56\n", "Zielinski: MV 6.41 ± 1.10; FV 7.17 + 2.38\n", "Luis Alberto: MV 6.31 ± 1.08; FV 7.02 + 2.29\n", "Strefezza: MV 6.29 ± 0.94; FV 7.09 + 2.28\n", "Felipe Anderson: MV 6.19 ± 1.25; FV 7.02 + 2.81\n", "Koopmeiners: MV 6.12 ± 1.16; FV 6.75 + 2.37\n", "Calhanoglu: MV 6.33 ± 0.99; FV 7.01 + 2.14\n", "Frattesi: MV 6.10 ± 1.20; FV 6.77 + 2.47\n", "Diaz B.: MV 6.14 ± 1.19; FV 6.89 + 2.56\n", "Vlasic: MV 6.13 ± 1.16; FV 6.76 + 2.27\n", "Zambo Anguissa: MV 6.40 ± 1.11; FV 7.13 + 2.35\n", "Elmas: MV 6.36 ± 1.08; FV 7.09 + 2.28\n", "Miranchuk: MV 6.21 ± 1.21; FV 6.93 + 2.46\n", "Samardzic: MV 6.22 ± 1.05; FV 6.86 + 2.14\n", "Pereyra: MV 6.25 ± 1.09; FV 6.88 + 2.22\n", "Politano: MV 6.29 ± 0.89; FV 6.98 + 2.05\n", "Rabiot: MV 6.22 ± 1.12; FV 6.85 + 2.23\n", "Ciurria: MV 6.04 ± 1.16; FV 6.67 + 2.38\n", "Lazovic: MV 6.27 ± 1.15; FV 6.95 + 2.31\n", "Lobotka: MV 6.18 ± 0.69; FV 6.65 + 1.51\n", "Radonjic: MV 6.13 ± 1.00; FV 6.64 + 1.82\n", "Ferguson: MV 6.23 ± 0.94; FV 6.81 + 1.94\n", "Bonaventura: MV 6.09 ± 0.96; FV 6.40 + 1.49\n", "Pessina: MV 6.11 ± 1.09; FV 6.64 + 2.05\n", "Tonali: MV 6.10 ± 1.09; FV 6.54 + 1.91\n", "Kostic: MV 6.20 ± 0.99; FV 6.77 + 1.94\n", "Baldanzi: MV 6.40 ± 1.07; FV 7.27 + 2.53\n", "Lovric: MV 6.13 ± 0.76; FV 6.48 + 1.30\n", "Pellegrini Lo.: MV 6.06 ± 1.17; FV 6.66 + 2.28\n", "El Shaarawy: MV 6.19 ± 0.97; FV 6.84 + 2.00\n", "Orsolini: MV 6.29 ± 1.36; FV 7.26 + 3.30\n", "Ikone': MV 6.04 ± 1.10; FV 6.46 + 1.92\n", "Candreva: MV 6.05 ± 1.14; FV 6.45 + 1.98\n", "Bennacer: MV 6.14 ± 0.83; FV 6.43 + 1.25\n", "Pasalic: MV 5.91 ± 1.01; FV 6.31 + 1.73\n", "Mkhitaryan: MV 6.16 ± 0.90; FV 6.68 + 1.69\n", "Colpani: MV 5.96 ± 0.87; FV 6.43 + 1.75\n", "Pogba: MV 6.04 ± 0.83; FV 6.19 + 1.04\n", "Chiesa: MV 6.19 ± 0.98; FV 6.69 + 1.81\n", "Bandinelli: MV 6.06 ± 0.80; FV 6.39 + 1.28\n", "Matic: MV 6.12 ± 0.78; FV 6.38 + 1.15\n", "Fagioli: MV 6.19 ± 0.96; FV 6.75 + 1.86\n", "Messias: MV 5.95 ± 1.07; FV 6.32 + 1.84\n", "Arslan: MV 6.01 ± 0.70; FV 6.10 + 0.79\n", "Ricci S.: MV 6.17 ± 0.91; FV 6.52 + 1.49\n", "Ranocchia F.: MV 6.01 ± 0.92; FV 6.43 + 1.65\n", "Verdi: MV 6.17 ± 0.84; FV 6.66 + 1.63\n", "Sensi: MV 6.00 ± 1.10; FV 6.41 + 1.95\n", "Barak: MV 5.83 ± 0.84; FV 5.97 + 1.20\n", "Soriano: MV 6.04 ± 0.74; FV 6.20 + 1.02\n", "Dominguez: MV 6.23 ± 1.09; FV 6.81 + 2.17\n", "Vilhena: MV 5.86 ± 1.00; FV 6.11 + 1.54\n", "Brozovic: MV 6.22 ± 0.82; FV 6.67 + 1.59\n", "Cristante: MV 5.95 ± 0.85; FV 6.09 + 1.06\n", "Thorstvedt: MV 5.87 ± 0.89; FV 6.06 + 1.30\n", "De Ketelaere: MV 5.82 ± 0.79; FV 5.88 + 0.90\n", "Saponara: MV 6.09 ± 1.12; FV 6.49 + 1.89\n", "Vecino: MV 5.90 ± 0.89; FV 6.01 + 1.22\n", "Locatelli: MV 6.09 ± 0.70; FV 6.20 + 0.87\n", "Zaniolo: MV 5.91 ± 1.00; FV 6.18 + 1.59\n", "Duda: MV 6.08 ± 0.87; FV 6.26 + 1.17\n", "Maldini: MV 5.96 ± 0.88; FV 6.24 + 1.39\n", "Marin: MV 6.08 ± 0.99; FV 6.44 + 1.63\n", "Zalewski: MV 6.01 ± 0.68; FV 6.11 + 0.74\n", "Bajrami: MV 6.11 ± 1.12; FV 6.70 + 2.19\n", "Coulibaly L.: MV 5.94 ± 1.15; FV 6.22 + 1.79\n", "Gonzalez J.: MV 6.04 ± 0.84; FV 6.27 + 1.26\n", "De Roon: MV 5.91 ± 0.75; FV 5.93 + 0.77\n", "Mandragora: MV 5.91 ± 0.88; FV 5.98 + 1.16\n", "Wijnaldum: MV 5.93 ± 0.91; FV 6.01 + 1.05\n", "Bourabia: MV 5.96 ± 0.78; FV 5.98 + 0.84\n", "Sottil: MV 6.07 ± 1.11; FV 6.45 + 1.84\n", "Aebischer: MV 6.02 ± 0.85; FV 6.30 + 1.39\n", "Ederson D.s.: MV 5.82 ± 0.79; FV 5.90 + 0.99\n", "Miretti: MV 6.03 ± 0.72; FV 6.18 + 0.90\n", "Blin: MV 6.01 ± 0.64; FV 5.99 + 0.59\n", "Hjulmand: MV 5.98 ± 1.07; FV 6.04 + 1.21\n", "Cataldi: MV 5.99 ± 0.79; FV 6.00 + 0.83\n", "Djuricic: MV 5.72 ± 0.90; FV 5.81 + 1.17\n", "Linetty: MV 5.96 ± 0.88; FV 6.12 + 1.28\n", "Haas: MV 6.02 ± 0.75; FV 6.27 + 1.11\n", "Walace: MV 5.92 ± 0.74; FV 5.88 + 0.68\n", "Agudelo: MV 5.89 ± 0.70; FV 5.91 + 0.72\n", "Pobega: MV 6.00 ± 0.88; FV 6.28 + 1.30\n", "Camara Ma.: MV 6.12 ± 0.70; FV 6.17 + 0.81\n", "Paredes: MV 5.87 ± 0.68; FV 5.86 + 0.57\n", "Ndombele': MV 6.05 ± 0.65; FV 5.99 + 0.58\n", "Nicolussi Caviglia: MV 5.87 ± 1.19; FV 6.24 + 1.99\n", "Rovella: MV 5.91 ± 0.95; FV 5.92 + 0.95\n", "Amrabat: MV 5.87 ± 0.89; FV 5.84 + 0.96\n", "Tameze: MV 5.96 ± 0.79; FV 6.03 + 0.94\n", "Gyasi: MV 5.89 ± 1.01; FV 6.04 + 1.49\n", "Ilic: MV 6.00 ± 0.99; FV 6.23 + 1.48\n", "Matheus Henrique: MV 5.89 ± 0.84; FV 6.03 + 1.16\n", "Harroui: MV 5.84 ± 0.80; FV 6.00 + 1.16\n", "Volpato: MV 6.02 ± 1.11; FV 6.60 + 2.21\n", "Pickel: MV 5.67 ± 0.80; FV 5.70 + 0.89\n", "Moro N.: MV 6.05 ± 0.66; FV 6.12 + 0.78\n", "Duncan: MV 5.88 ± 0.76; FV 5.92 + 0.90\n", "Machin: MV 5.86 ± 0.94; FV 5.94 + 1.23\n", "Cuadrado: MV 6.04 ± 0.88; FV 6.19 + 1.10\n", "Ekdal: MV 5.82 ± 0.71; FV 5.77 + 0.71\n", "Meite': MV 5.73 ± 1.03; FV 5.76 + 1.28\n", "Schouten: MV 6.01 ± 0.78; FV 6.02 + 0.84\n", "Obiang: MV 5.91 ± 0.65; FV 5.93 + 0.64\n", "Kovalenko: MV 5.97 ± 0.77; FV 6.07 + 0.95\n", "Crnigoj: MV 5.93 ± 0.89; FV 6.10 + 1.23\n", "Basic: MV 5.95 ± 0.67; FV 6.02 + 0.73\n", "Asllani: MV 6.07 ± 0.63; FV 6.08 + 0.65\n", "Sabiri: MV 5.76 ± 0.84; FV 5.80 + 1.04\n", "Terracciano F.: MV 6.09 ± 0.63; FV 6.13 + 0.72\n", "Castagnetti: MV 5.72 ± 0.70; FV 5.70 + 0.67\n", "Oudin: MV 5.82 ± 0.65; FV 5.86 + 0.60\n", "Grassi: MV 6.04 ± 0.67; FV 6.00 + 0.62\n", "Krunic: MV 5.89 ± 0.76; FV 5.95 + 0.78\n", "Rincon: MV 5.68 ± 0.79; FV 5.60 + 0.85\n", "Miguel Veloso: MV 6.01 ± 0.72; FV 6.05 + 0.79\n", "Leris: MV 5.70 ± 0.76; FV 5.66 + 0.87\n", "Esposito Sa.: MV 5.92 ± 0.95; FV 5.97 + 1.10\n", "Henderson L.: MV 6.01 ± 0.71; FV 6.16 + 0.90\n", "Lopez M.: MV 5.85 ± 0.90; FV 5.84 + 1.09\n", "Cuisance: MV 5.70 ± 0.72; FV 5.64 + 0.74\n", "Saelemaekers: MV 5.82 ± 0.78; FV 5.89 + 0.82\n", "Maggiore: MV 5.93 ± 0.81; FV 6.08 + 1.06\n", "Akpa Akpro: MV 6.05 ± 0.82; FV 6.20 + 1.05\n", "Maleh: MV 5.95 ± 0.74; FV 6.10 + 0.99\n", "Romero L.: MV 6.14 ± 1.06; FV 6.71 + 2.08\n", "Ceide: MV 5.80 ± 0.71; FV 5.83 + 0.73\n", "D'alessandro: MV 6.02 ± 0.67; FV 6.10 + 0.74\n", "Benassi: MV 5.71 ± 0.73; FV 5.75 + 0.81\n", "Gagliardini: MV 5.97 ± 0.63; FV 6.02 + 0.62\n", "Vieira: MV 5.87 ± 0.73; FV 5.91 + 0.98\n", "Bianco: MV 6.00 ± 0.85; FV 6.07 + 1.01\n", "Vranckx: MV 6.07 ± 0.74; FV 6.21 + 0.88\n", "Galdames: MV 5.76 ± 1.04; FV 5.84 + 1.35\n", "Marcos Antonio: MV 5.94 ± 0.61; FV 5.92 + 0.51\n", "Fazzini: MV 5.87 ± 0.63; FV 5.86 + 0.54\n", "Sulemana I.: MV 5.93 ± 0.64; FV 5.95 + 0.62\n", "Tahirovic: MV 5.96 ± 0.60; FV 5.97 + 0.50\n", "Abildgaard: MV 5.97 ± 0.85; FV 6.05 + 1.06\n", "Barberis: MV 5.87 ± 0.98; FV 5.92 + 1.14\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Kastanos: MV 5.82 ± 0.69; FV 5.83 + 0.69\n", "Vignato: MV 6.05 ± 0.68; FV 6.09 + 0.71\n", "Valoti: MV 5.72 ± 0.67; FV 5.66 + 0.65\n", "Winks: MV 5.79 ± 1.00; FV 5.78 + 1.19\n", "Askildsen: MV 5.72 ± 0.64; FV 5.69 + 0.58\n", "Bove: MV 5.73 ± 0.74; FV 5.74 + 0.82\n", "Bohinen: MV 5.75 ± 0.62; FV 5.73 + 0.52\n", "D'andrea: MV 5.89 ± 0.78; FV 6.05 + 1.09\n", "Iling-Junior: MV 6.09 ± 0.69; FV 6.25 + 0.94\n", "Cipot: MV 5.97 ± 0.96; FV 6.08 + 1.23\n", "Bakayoko: MV 5.82 ± 0.76; FV 5.79 + 0.68\n", "Gaetano: MV 6.05 ± 0.74; FV 6.09 + 0.81\n", "Zurkowski: MV 6.18 ± 1.08; FV 6.69 + 2.04\n", "Castrovilli: MV 6.01 ± 0.90; FV 6.23 + 1.34\n", "Demme: MV 6.07 ± 0.65; FV 6.24 + 0.90\n", "Darboe: MV 5.95 ± 0.90; FV 5.99 + 0.94\n", "Urbanski: MV 6.00 ± 0.88; FV 6.09 + 1.10\n", "Bertini: MV 5.93 ± 0.93; FV 6.01 + 1.20\n", "Yepes: MV 5.71 ± 1.15; FV 5.69 + 1.29\n", "Pyyhtia: MV 6.02 ± 0.76; FV 6.06 + 0.87\n", "Trimboli: MV 5.78 ± 0.94; FV 5.77 + 1.15\n", "Pafundi: MV 5.92 ± 0.85; FV 5.93 + 0.88\n", "Helgason: MV 5.80 ± 0.62; FV 5.80 + 0.54\n", "Adli: MV 5.87 ± 0.77; FV 5.93 + 0.83\n", "Vignato S.: MV 5.95 ± 0.91; FV 6.06 + 1.08\n", "Hrustic: MV 5.80 ± 0.74; FV 5.78 + 0.72\n", "Samek: MV 5.94 ± 0.86; FV 6.01 + 1.06\n", "Zerbin: MV 6.10 ± 0.74; FV 6.18 + 0.90\n", "Ilkhan: MV 5.85 ± 1.06; FV 5.92 + 1.34\n", "Degli Innocenti: MV 6.04 ± 0.81; FV 6.17 + 0.99\n", "Acella: MV 5.76 ± 1.04; FV 5.84 + 1.35\n", "Carboni V.: MV 6.01 ± 0.84; FV 6.13 + 1.00\n", "Paoletti: MV 5.97 ± 0.87; FV 6.05 + 1.08\n", "Malagrida: MV 5.80 ± 0.95; FV 5.80 + 1.17\n", "Faticanti: MV 5.95 ± 0.89; FV 6.06 + 1.04\n", "Osimhen: MV 6.59 ± 1.51; FV 7.92 + 4.46\n", "Martinez L.: MV 6.47 ± 1.44; FV 7.71 + 3.99\n", "Dybala: MV 6.43 ± 1.34; FV 7.49 + 3.41\n", "Rafael Leao: MV 6.29 ± 1.39; FV 7.41 + 3.60\n", "Lookman: MV 6.25 ± 1.40; FV 7.54 + 3.85\n", "Immobile: MV 6.29 ± 1.43; FV 7.63 + 4.01\n", "Vlahovic: MV 6.39 ± 1.45; FV 7.75 + 4.21\n", "Arnautovic: MV 6.28 ± 1.35; FV 7.45 + 3.62\n", "Dia: MV 6.18 ± 1.41; FV 7.42 + 3.75\n", "Dzeko: MV 6.30 ± 1.36; FV 7.47 + 3.65\n", "Milik: MV 6.36 ± 1.24; FV 7.27 + 2.98\n", "Nzola: MV 6.14 ± 1.34; FV 7.26 + 3.45\n", "Beto: MV 6.15 ± 1.23; FV 7.09 + 2.99\n", "Giroud: MV 6.13 ± 1.26; FV 6.97 + 2.88\n", "Abraham: MV 6.12 ± 1.30; FV 7.28 + 3.46\n", "Deulofeu: MV 6.38 ± 1.28; FV 7.28 + 2.98\n", "Lauriente': MV 6.20 ± 1.35; FV 7.06 + 3.08\n", "Simeone: MV 6.38 ± 1.43; FV 7.68 + 4.03\n", "Lozano: MV 6.35 ± 1.22; FV 7.12 + 2.50\n", "Correa: MV 6.26 ± 1.04; FV 7.08 + 2.46\n", "Berardi: MV 6.24 ± 1.42; FV 7.46 + 3.80\n", "Pedro: MV 6.15 ± 1.16; FV 6.78 + 2.36\n", "Lukaku: MV 6.08 ± 1.19; FV 6.87 + 2.65\n", "Sanabria: MV 6.00 ± 1.16; FV 6.52 + 2.14\n", "Thauvin: MV 6.44 ± 1.30; FV 7.38 + 3.08\n", "Cabral: MV 5.96 ± 1.10; FV 6.42 + 1.98\n", "Hojlund: MV 5.98 ± 1.11; FV 6.52 + 2.13\n", "Caprari: MV 5.95 ± 1.03; FV 6.48 + 2.03\n", "Di Maria: MV 6.33 ± 1.32; FV 7.28 + 3.16\n", "Piatek: MV 5.92 ± 1.16; FV 6.46 + 2.17\n", "Rebic: MV 6.18 ± 1.33; FV 6.97 + 2.88\n", "Bonazzoli: MV 6.05 ± 1.09; FV 6.56 + 2.03\n", "Zapata D.: MV 5.82 ± 0.93; FV 6.17 + 1.53\n", "Kouame': MV 5.97 ± 1.09; FV 6.37 + 1.88\n", "Gonzalez N.: MV 6.12 ± 1.18; FV 6.71 + 2.27\n", "Brekalo: MV 5.99 ± 1.06; FV 6.37 + 1.81\n", "Mota: MV 6.03 ± 1.21; FV 6.83 + 2.71\n", "Kean: MV 6.11 ± 1.22; FV 6.86 + 2.68\n", "Okereke: MV 5.76 ± 1.10; FV 6.24 + 1.89\n", "Ceesay: MV 5.95 ± 0.89; FV 6.32 + 1.48\n", "Colombo: MV 5.99 ± 1.10; FV 6.48 + 2.01\n", "Dessers: MV 5.79 ± 1.04; FV 6.25 + 1.81\n", "Muriel: MV 6.01 ± 1.19; FV 6.41 + 2.09\n", "Pinamonti: MV 5.88 ± 1.07; FV 6.35 + 1.94\n", "Di Francesco F.: MV 6.04 ± 0.95; FV 6.39 + 1.56\n", "Jovic: MV 5.90 ± 1.07; FV 6.31 + 1.88\n", "Origi: MV 5.92 ± 1.07; FV 6.26 + 1.78\n", "Caputo: MV 6.18 ± 1.27; FV 7.17 + 3.17\n", "Boga: MV 6.28 ± 1.22; FV 7.01 + 2.50\n", "Cambiaghi: MV 6.24 ± 0.95; FV 6.81 + 1.87\n", "Alvarez A.: MV 5.98 ± 1.08; FV 6.36 + 1.87\n", "Banda: MV 5.97 ± 0.73; FV 6.09 + 0.88\n", "Ciofani D.: MV 5.85 ± 1.05; FV 6.29 + 1.82\n", "Petagna: MV 5.95 ± 1.11; FV 6.48 + 2.09\n", "Barrow: MV 6.16 ± 1.24; FV 6.74 + 2.39\n", "Djuric: MV 6.03 ± 0.72; FV 6.23 + 0.99\n", "Henry: MV 6.10 ± 1.23; FV 6.66 + 2.33\n", "Success: MV 5.98 ± 0.70; FV 6.09 + 0.84\n", "Gabbiadini: MV 5.86 ± 1.16; FV 6.39 + 2.11\n", "Zirkzee: MV 6.13 ± 1.01; FV 6.63 + 1.86\n", "Lammers: MV 5.82 ± 0.80; FV 5.91 + 1.07\n", "Satriano: MV 5.92 ± 0.90; FV 6.13 + 1.35\n", "Kallon: MV 5.89 ± 0.84; FV 6.14 + 1.29\n", "Nestorovski: MV 6.28 ± 0.99; FV 7.11 + 2.37\n", "Raspadori: MV 6.17 ± 1.05; FV 6.79 + 2.11\n", "Botheim: MV 5.90 ± 1.02; FV 6.27 + 1.73\n", "Gytkjaer: MV 5.84 ± 0.90; FV 6.11 + 1.45\n", "Solbakken: MV 6.09 ± 0.99; FV 6.36 + 1.40\n", "Lasagna: MV 5.81 ± 0.90; FV 5.94 + 1.23\n", "Belotti: MV 5.70 ± 0.65; FV 5.71 + 0.63\n", "Pellegri: MV 5.94 ± 0.98; FV 6.24 + 1.62\n", "Buonaiuto: MV 5.90 ± 0.89; FV 6.21 + 1.42\n", "Verde: MV 6.08 ± 0.95; FV 6.46 + 1.66\n", "Destro: MV 6.09 ± 1.30; FV 7.00 + 3.01\n", "Seck: MV 6.10 ± 0.75; FV 6.37 + 1.16\n", "Sansone: MV 6.01 ± 1.03; FV 6.37 + 1.77\n", "Quagliarella: MV 5.83 ± 0.76; FV 5.93 + 1.04\n", "Defrel: MV 5.84 ± 0.92; FV 6.09 + 1.45\n", "Pjaca: MV 5.98 ± 0.81; FV 6.15 + 1.00\n", "Gaich: MV 6.01 ± 1.18; FV 6.50 + 2.17\n", "Soule': MV 6.18 ± 0.76; FV 6.57 + 1.40\n", "Tsadjout: MV 5.83 ± 0.83; FV 6.00 + 1.20\n", "Piccoli: MV 6.08 ± 1.23; FV 7.02 + 2.97\n", "Shomurodov: MV 6.03 ± 1.09; FV 6.56 + 2.07\n", "Afena-Gyan: MV 5.61 ± 0.76; FV 5.68 + 0.90\n", "Ngonge: MV 6.09 ± 0.88; FV 6.35 + 1.33\n", "Karamoh: MV 5.90 ± 0.98; FV 6.26 + 1.66\n", "Ibrahimovic: MV 6.21 ± 1.25; FV 7.21 + 3.12\n", "Pussetto: MV 5.85 ± 0.95; FV 6.13 + 1.53\n", "Cancellieri: MV 5.80 ± 0.59; FV 5.80 + 0.54\n", "Valencia D.: MV 5.76 ± 0.61; FV 5.64 + 0.62\n", "Oddei: MV 6.01 ± 0.91; FV 6.22 + 1.32\n", "Braaf: MV 5.97 ± 0.95; FV 6.16 + 1.41\n", "Raimondo: MV 6.05 ± 0.95; FV 6.23 + 1.31\n", "Kaio Jorge: MV 5.96 ± 0.60; FV 5.99 + 0.54\n", "De Luca: MV 5.78 ± 0.95; FV 5.83 + 1.22\n", "Voelkerling Persson: MV 5.84 ± 0.77; FV 5.87 + 0.82\n", "Montevago: MV 5.63 ± 0.63; FV 5.58 + 0.63\n", "Krollis: MV 5.95 ± 0.90; FV 6.04 + 1.14\n", "Vivaldo: MV 5.93 ± 0.89; FV 5.98 + 0.98\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
roleteamoppteamhomestartervote%MVMV stdFVFV stdMV locMV scaleMV skewnessMV tailweightFV locFV scaleFV skewnessFV tailweightClean Sheet %
player
Rossi F.PAtalantaLazio00.016.2400650.4138364.1523730.6566035.9964780.2503040.6213451.5898294.9945010.649063-0.8560580.9787610.057899
SportielloPAtalantaLazio00.056.2299340.4136063.8428240.7812135.9874150.2522970.6155001.5897754.6774170.889610-0.6578250.9622570.630536
MussoPAtalantaLazio01.0906.2413050.4136883.8050550.7454405.9976820.2499270.6221321.5898484.5882810.860939-0.6380860.9650510.630550
ToloiDAtalantaLazio01.0905.9941160.4856076.1789810.6445575.9571240.5640840.0483940.9989745.7783100.9544990.3019211.5998860.000000
ZappacostaDAtalantaLazio00.0505.9273810.3962256.0800740.5160575.8848010.4593640.0685731.1002375.7558980.7608670.3061171.5999050.000000
............................................................
NgongeAVeronaSalernitana10.6606.0899630.4408746.3521810.6660916.0474860.5106300.0614381.0348305.9045080.9519720.3352371.5998920.000000
DjuricAVeronaSalernitana10.006.0332070.3616166.2300600.4966365.9835210.4157870.0884291.1362815.9244020.7384490.2980061.5999130.000000
BraafAVeronaSalernitana10.0555.9723260.4767096.1579600.7055975.9506810.5584650.0286161.0069615.6948271.0201010.3246051.5998760.000000
KallonAVeronaSalernitana10.0355.8940610.4205456.1435550.6454485.8155070.4739570.1223171.0853365.6341390.8335410.4236691.5998790.000000
LasagnaAVeronaSalernitana11.0705.8089270.4520285.9439230.6160455.7213140.5079060.1271941.0593285.4754300.8179980.4002291.5998800.000000
\n", "

520 rows × 19 columns

\n", "
" ], "text/plain": [ " role team oppteam home starter vote% MV \\\n", "player \n", "Rossi F. P Atalanta Lazio 0 0.0 1 6.240065 \n", "Sportiello P Atalanta Lazio 0 0.0 5 6.229934 \n", "Musso P Atalanta Lazio 0 1.0 90 6.241305 \n", "Toloi D Atalanta Lazio 0 1.0 90 5.994116 \n", "Zappacosta D Atalanta Lazio 0 0.0 50 5.927381 \n", "... ... ... ... ... ... ... ... \n", "Ngonge A Verona Salernitana 1 0.6 60 6.089963 \n", "Djuric A Verona Salernitana 1 0.0 0 6.033207 \n", "Braaf A Verona Salernitana 1 0.0 55 5.972326 \n", "Kallon A Verona Salernitana 1 0.0 35 5.894061 \n", "Lasagna A Verona Salernitana 1 1.0 70 5.808927 \n", "\n", " MV std FV FV std MV loc MV scale MV skewness \\\n", "player \n", "Rossi F. 0.413836 4.152373 0.656603 5.996478 0.250304 0.621345 \n", "Sportiello 0.413606 3.842824 0.781213 5.987415 0.252297 0.615500 \n", "Musso 0.413688 3.805055 0.745440 5.997682 0.249927 0.622132 \n", "Toloi 0.485607 6.178981 0.644557 5.957124 0.564084 0.048394 \n", "Zappacosta 0.396225 6.080074 0.516057 5.884801 0.459364 0.068573 \n", "... ... ... ... ... ... ... \n", "Ngonge 0.440874 6.352181 0.666091 6.047486 0.510630 0.061438 \n", "Djuric 0.361616 6.230060 0.496636 5.983521 0.415787 0.088429 \n", "Braaf 0.476709 6.157960 0.705597 5.950681 0.558465 0.028616 \n", "Kallon 0.420545 6.143555 0.645448 5.815507 0.473957 0.122317 \n", "Lasagna 0.452028 5.943923 0.616045 5.721314 0.507906 0.127194 \n", "\n", " MV tailweight FV loc FV scale FV skewness FV tailweight \\\n", "player \n", "Rossi F. 1.589829 4.994501 0.649063 -0.856058 0.978761 \n", "Sportiello 1.589775 4.677417 0.889610 -0.657825 0.962257 \n", "Musso 1.589848 4.588281 0.860939 -0.638086 0.965051 \n", "Toloi 0.998974 5.778310 0.954499 0.301921 1.599886 \n", "Zappacosta 1.100237 5.755898 0.760867 0.306117 1.599905 \n", "... ... ... ... ... ... \n", "Ngonge 1.034830 5.904508 0.951972 0.335237 1.599892 \n", "Djuric 1.136281 5.924402 0.738449 0.298006 1.599913 \n", "Braaf 1.006961 5.694827 1.020101 0.324605 1.599876 \n", "Kallon 1.085336 5.634139 0.833541 0.423669 1.599879 \n", "Lasagna 1.059328 5.475430 0.817998 0.400229 1.599880 \n", "\n", " Clean Sheet % \n", "player \n", "Rossi F. 0.057899 \n", "Sportiello 0.630536 \n", "Musso 0.630550 \n", "Toloi 0.000000 \n", "Zappacosta 0.000000 \n", "... ... \n", "Ngonge 0.000000 \n", "Djuric 0.000000 \n", "Braaf 0.000000 \n", "Kallon 0.000000 \n", "Lasagna 0.000000 \n", "\n", "[520 rows x 19 columns]" ] }, "execution_count": 58, "metadata": {}, "output_type": "execute_result" } ], "source": [ "matchday_out = 22\n", "\n", "output = pd.DataFrame(columns = ['player', 'role', 'team', 'oppteam', 'home', 'starter', 'vote%', 'MV', 'MV std', 'FV', 'FV std', 'MV loc', 'MV scale', 'MV skewness', 'MV tailweight', 'FV loc', 'FV scale', 'FV skewness', 'FV tailweight', 'Clean Sheet %'])\n", "\n", "for i in range(players.shape[0]):\n", " try:\n", " [player, team, oppteam, home] = PlayerMatch(players.index[i], matchday_out)\n", " \n", " [mean, std, dist] = vote_predict_NNb(player, team, oppteam, home = home, log = 1)\n", " \n", " role = players['r'][player] \n", " \n", " starter = 0\n", " voteperc = 0\n", " \n", " cs = 0\n", " if(role == 'P'):\n", " cs = dist[2].probs.numpy()[0] * 100\n", " \n", " if(player in probables.index):\n", " starter = probables['starter'][player]\n", " voteperc = probables['percentage'][player]\n", " \n", " row = [player, role, team, oppteam, home, \n", " starter, voteperc, \n", " mean[0], std[0], \n", " mean[1], std[1], \n", " dist[0].loc.numpy()[0], dist[0].scale.numpy()[0], \n", " dist[0].skewness.numpy()[0], dist[0].tailweight.numpy()[0], \n", " dist[1].loc.numpy()[0], dist[1].scale.numpy()[0], \n", " dist[1].skewness.numpy()[0], dist[1].tailweight.numpy()[0],\n", " cs]\n", " \n", " row_df = pd.DataFrame(data = [row], columns = output.columns)\n", " \n", " output = pd.concat([output, row_df])\n", " \n", " except:\n", " print(players.index[i] + ' no data')\n", "\n", "output = output.set_index('player')\n", "\n", "output = output.sort_values(['team', 'role', 'FV'], ascending = [True, False, False])\n", "#output.to_excel('outputs/pred_matchday_' + str(matchday_out) + '.xlsx')\n", "\n", "output" ] }, { "cell_type": "code", "execution_count": 59, "id": "6befd611", "metadata": {}, "outputs": [], "source": [ "import shutil\n", "\n", "template_file = 'outputs/pred_matchday_base.xlsx'\n", "dest_file = 'outputs/pred_matchday_' + str(matchday_out) + '.xlsx'\n", "\n", "shutil.copyfile(template_file, dest_file)\n", "\n", "with pd.ExcelWriter(dest_file, mode = 'a', engine=\"openpyxl\", if_sheet_exists = 'replace') as writer: \n", " output.to_excel(writer, sheet_name='data')" ] }, { "cell_type": "markdown", "id": "eed7a7ac", "metadata": {}, "source": [ "Predict average Serie A performance for each player" ] }, { "cell_type": "code", "execution_count": 60, "id": "2b637a15", "metadata": {}, "outputs": [], "source": [ "gk_starters = ['Maignan', 'Ochoa', 'Silvestri', 'Consigli', 'Provedel', 'Di Gregorio', 'Meret', 'Milinkovic-Savic V.',\n", " 'Terracciano', 'Onana', 'Szczesny', 'Skorupski', 'Vicario', 'Musso', 'Carnesecchi', 'Rui Patricio',\n", " 'Montipo\\'', 'Falcone', 'Dragowski', 'Audero']" ] }, { "cell_type": "code", "execution_count": 61, "id": "60d73507", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Meret (6.24, 0.41); (5.58, 0.42)\n", "Provedel (6.24, 0.41); (5.95, 0.36)\n", "Vicario (6.24, 0.41); (5.36, 0.42)\n", "Szczesny (6.24, 0.41); (6.01, 0.36)\n", "Falcone (6.24, 0.41); (4.85, 0.45)\n", "Silvestri (6.24, 0.41); (5.11, 0.44)\n", "Rui Patricio (6.24, 0.41); (5.50, 0.38)\n", "Onana (6.19, 0.42); (4.75, 0.59)\n", "Sepe (6.24, 0.41); (5.10, 0.46)\n", "Milinkovic-Savic V. (6.24, 0.41); (4.90, 0.41)\n", "Musso (6.24, 0.41); (4.99, 0.63)\n", "Maignan (6.24, 0.41); (5.81, 0.41)\n", "Carnesecchi (6.24, 0.41); (5.22, 0.48)\n", "Di Gregorio (6.25, 0.41); (5.01, 0.61)\n", "Audero (6.24, 0.41); (4.75, 0.48)\n", "Montipo' (6.24, 0.41); (4.72, 0.52)\n", "Skorupski (6.24, 0.41); (4.76, 0.59)\n", "Consigli (6.24, 0.41); (4.91, 0.50)\n", "Dragowski (6.24, 0.41); (4.97, 0.54)\n", "Terracciano (6.18, 0.42); (4.50, 0.65)\n", "Tatarusanu (6.18, 0.43); (3.89, 0.76)\n", "Handanovic (5.87, 0.50); (4.47, 0.71)\n", "Sportiello (6.23, 0.42); (5.75, 0.47)\n", "Perin (6.24, 0.41); (5.57, 0.41)\n", "Zoet (6.24, 0.41); (5.55, 0.43)\n", "Ochoa (6.23, 0.42); (4.02, 0.95)\n", "Pegolo (6.24, 0.41); (5.55, 0.40)\n", "Gollini (6.24, 0.41); (5.16, 0.43)\n", "Mirante no data\n", "Sarr M. no data\n", "Lamanna no data\n", "Ujkani no data\n", "Berisha (6.24, 0.41); (5.29, 0.44)\n", "Marchetti no data\n", "Perilli no data\n", "Padelli (6.24, 0.41); (4.83, 0.48)\n", "Perisan no data\n", "Bardi (6.24, 0.41); (5.27, 0.54)\n", "Cordaz no data\n", "Pinsoglio (6.24, 0.41); (5.06, 0.42)\n", "Fiorillo (6.17, 0.43); (3.83, 0.97)\n", "Cragno (6.24, 0.41); (4.42, 0.63)\n", "Sirigu (6.24, 0.41); (4.39, 0.64)\n", "Cerofolini no data\n", "Rossi F. (6.00, 0.46); (3.42, 1.07)\n", "Ravaglia F. no data\n", "Brancolini no data\n", "Bleve no data\n", "Berardi A. (6.24, 0.41); (4.34, 0.60)\n", "Russo A. no data\n", "Gemello (6.24, 0.41); (5.79, 0.40)\n", "Ravaglia (6.24, 0.41); (4.34, 0.66)\n", "Boer no data\n", "Adamonis no data\n", "Marfella (6.24, 0.41); (5.13, 0.46)\n", "Zovko (5.74, 0.52); (2.94, 1.36)\n", "Piana no data\n", "Bagnolini no data\n", "Luis Maximiano (6.30, 0.40); (6.35, 0.47)\n", "Svilar no data\n", "Sorrentino A. no data\n", "Ciezkowski no data\n", "Saro no data\n", "Vasquez D. no data\n", "Turk no data\n", "Dimarco (6.22, 0.50); (6.73, 0.92)\n", "Smalling (6.24, 0.51); (6.68, 0.89)\n", "Doig (6.21, 0.58); (6.85, 1.17)\n", "Carlos Augusto (6.10, 0.55); (6.59, 1.02)\n", "Kim (6.26, 0.48); (6.60, 0.80)\n", "Posch (6.12, 0.59); (6.78, 1.23)\n", "Di Lorenzo (6.23, 0.43); (6.55, 0.72)\n", "Danilo (6.27, 0.51); (6.68, 0.87)\n", "Hernandez T. (6.03, 0.60); (6.44, 1.02)\n", "Udogie (6.09, 0.55); (6.55, 1.01)\n", "Parisi (6.21, 0.44); (6.63, 0.79)\n", "Mario Rui (6.22, 0.44); (6.47, 0.67)\n", "Romagnoli (6.19, 0.47); (6.42, 0.68)\n", "Bastoni S. (6.14, 0.50); (6.58, 0.92)\n", "Mazzocchi (6.12, 0.50); (6.55, 0.89)\n", "Valeri (6.08, 0.37); (6.31, 0.55)\n", "Tomori (6.12, 0.48); (6.37, 0.69)\n", "Scalvini (6.11, 0.54); (6.48, 0.89)\n", "Toloi (6.18, 0.50); (6.51, 0.77)\n", "Demiral (6.08, 0.46); (6.33, 0.68)\n", "Maehle (5.98, 0.50); (6.22, 0.76)\n", "Dumfries (6.04, 0.55); (6.44, 0.97)\n", "Baschirotto (6.19, 0.54); (6.64, 0.96)\n", "Bijol (5.92, 0.53); (6.12, 0.77)\n", "Schuurs (6.15, 0.37); (6.23, 0.47)\n", "Juan Jesus (6.19, 0.38); (6.45, 0.62)\n", "Depaoli (5.96, 0.48); (6.19, 0.75)\n", "Mancini (6.11, 0.36); (6.14, 0.40)\n", "Ibanez (6.11, 0.52); (6.47, 0.85)\n", "Rodrigo Becao (6.14, 0.47); (6.42, 0.71)\n", "Ebuehi (6.09, 0.43); (6.38, 0.65)\n", "Gosens (5.98, 0.34); (6.21, 0.50)\n", "Darmian (6.08, 0.41); (6.46, 0.71)\n", "Reca (5.89, 0.55); (6.13, 0.80)\n", "Bremer (5.97, 0.54); (6.12, 0.68)\n", "Sernicola (5.94, 0.40); (6.07, 0.55)\n", "Rrahmani (6.26, 0.49); (6.56, 0.78)\n", "Vojvoda (6.03, 0.46); (6.18, 0.59)\n", "Holm (6.00, 0.44); (6.22, 0.66)\n", "Bastoni (6.10, 0.46); (6.21, 0.56)\n", "Milenkovic (5.91, 0.53); (6.07, 0.73)\n", "Kalulu (5.78, 0.56); (5.83, 0.68)\n", "Martinez Quarta (6.04, 0.52); (6.26, 0.73)\n", "Casale (6.01, 0.45); (6.12, 0.56)\n", "Perez N. (6.07, 0.46); (6.20, 0.57)\n", "Olivera (6.15, 0.38); (6.48, 0.65)\n", "Izzo (6.01, 0.39); (6.00, 0.39)\n", "Luperto (5.82, 0.53); (5.82, 0.56)\n", "Skriniar (5.84, 0.42); (5.81, 0.41)\n", "Rodriguez R. (6.00, 0.39); (5.98, 0.39)\n", "Marusic (6.03, 0.39); (6.05, 0.41)\n", "Lazzari (6.05, 0.41); (6.08, 0.44)\n", "Kyriakopoulos (5.91, 0.50); (6.00, 0.59)\n", "Ampadu (5.84, 0.47); (5.86, 0.57)\n", "Ismajli (6.06, 0.40); (6.03, 0.40)\n", "Llorente D. (5.93, 0.52); (6.10, 0.72)\n", "Cambiaso (5.96, 0.41); (5.99, 0.45)\n", "Hysaj (6.00, 0.35); (6.05, 0.36)\n", "Biraghi (6.00, 0.39); (6.05, 0.41)\n", "Medel (5.95, 0.39); (5.91, 0.38)\n", "Bonucci (6.21, 0.54); (6.66, 0.94)\n", "Calabria (5.87, 0.53); (6.06, 0.77)\n", "Acerbi (6.06, 0.41); (6.12, 0.46)\n", "Spinazzola (6.00, 0.34); (6.05, 0.35)\n", "Lykogiannis (5.97, 0.37); (6.04, 0.40)\n", "Pellegrini Lu. (6.04, 0.37); (6.09, 0.41)\n", "Djidji (5.92, 0.45); (5.99, 0.57)\n", "Lazaro (6.02, 0.48); (6.16, 0.60)\n", "Augello (5.83, 0.46); (5.93, 0.61)\n", "Gallo (5.96, 0.38); (5.93, 0.36)\n", "Singo (6.04, 0.42); (6.18, 0.53)\n", "Mari' (5.83, 0.57); (5.94, 0.75)\n", "Caldirola (5.81, 0.48); (5.77, 0.49)\n", "Dodo' (5.78, 0.48); (5.70, 0.51)\n", "De Vrij (5.87, 0.43); (5.90, 0.48)\n", "Patric (6.04, 0.43); (6.05, 0.46)\n", "Faraoni (5.98, 0.43); (6.16, 0.62)\n", "Ceccherini (5.87, 0.52); (5.98, 0.71)\n", "Hateboer (5.87, 0.48); (5.99, 0.69)\n", "Rogerio (5.77, 0.45); (5.71, 0.49)\n", "Umtiti (5.91, 0.50); (5.98, 0.56)\n", "Aina (6.07, 0.53); (6.38, 0.80)\n", "Birindelli (5.83, 0.37); (5.84, 0.40)\n", "Lucumi' (5.91, 0.43); (5.89, 0.46)\n", "Ehizibue (5.85, 0.45); (5.98, 0.65)\n", "Bianchetti (5.76, 0.48); (5.78, 0.61)\n", "Ferrari G. (5.77, 0.56); (5.83, 0.72)\n", "Fazio (5.66, 0.63); (5.72, 0.71)\n", "Gravillon (5.97, 0.45); (6.04, 0.54)\n", "Buongiorno (5.95, 0.41); (5.90, 0.39)\n", "Gunter (5.79, 0.50); (5.78, 0.62)\n", "Troost-Ekong (5.77, 0.57); (5.78, 0.63)\n", "Soumaoro (5.86, 0.50); (5.83, 0.52)\n", "Ceccaroni (5.89, 0.53); (5.99, 0.66)\n", "Pongracic (5.95, 0.40); (5.91, 0.38)\n", "Soppy (5.85, 0.40); (5.87, 0.42)\n", "Gendrey (5.87, 0.36); (5.83, 0.33)\n", "Hien (5.81, 0.42); (5.74, 0.44)\n", "Ferrari A. (5.77, 0.54); (5.80, 0.67)\n", "Masina (6.05, 0.53); (6.51, 0.98)\n", "Zappacosta (6.08, 0.41); (6.31, 0.59)\n", "Gyomber (5.79, 0.46); (5.72, 0.46)\n", "Alex Sandro (5.83, 0.49); (5.74, 0.45)\n", "Pezzella Giu. (5.93, 0.35); (5.93, 0.32)\n", "Bereszynski (5.89, 0.34); (5.86, 0.31)\n", "Venuti (5.84, 0.41); (5.83, 0.43)\n", "Palomino (6.08, 0.50); (6.25, 0.63)\n", "Nuytinck (5.85, 0.51); (5.85, 0.56)\n", "Marlon (5.81, 0.38); (5.77, 0.36)\n", "Magnani (5.82, 0.47); (5.74, 0.47)\n", "Colley (5.77, 0.57); (5.84, 0.72)\n", "Nikolaou (5.70, 0.43); (5.60, 0.43)\n", "Terzic (6.04, 0.28); (5.97, 0.22)\n", "Igor (5.79, 0.48); (5.68, 0.48)\n", "Toljan (5.71, 0.43); (5.62, 0.44)\n", "Zortea (5.84, 0.44); (5.89, 0.56)\n", "Dawidowicz (5.82, 0.52); (5.87, 0.68)\n", "Celik (5.79, 0.39); (5.75, 0.39)\n", "Bellanova (5.90, 0.42); (5.96, 0.50)\n", "Erlic (5.82, 0.50); (5.76, 0.52)\n", "Ballo-Toure' (6.13, 0.41); (6.50, 0.69)\n", "Dest (5.78, 0.44); (5.77, 0.48)\n", "Stojanovic (5.76, 0.43); (5.71, 0.47)\n", "Amian (5.78, 0.43); (5.72, 0.47)\n", "Bradaric (5.73, 0.44); (5.71, 0.50)\n", "Daniliuc (5.75, 0.57); (5.77, 0.65)\n", "Zima (5.94, 0.41); (5.94, 0.42)\n", "De Winter (5.75, 0.43); (5.67, 0.40)\n", "Quagliata (5.94, 0.32); (5.96, 0.29)\n", "Ebosse (5.77, 0.36); (5.69, 0.34)\n", "Aiwu (5.89, 0.48); (5.96, 0.64)\n", "Lochoshvili (5.77, 0.40); (5.70, 0.43)\n", "Bronn (5.77, 0.37); (5.72, 0.34)\n", "Thiaw (6.00, 0.43); (6.02, 0.44)\n", "Zeefuik (5.90, 0.45); (5.93, 0.55)\n", "Romagnoli S. (5.98, 0.59); (6.34, 0.96)\n", "Ghiglione (5.82, 0.45); (5.83, 0.57)\n", "Rugani (6.00, 0.32); (5.93, 0.27)\n", "De Sciglio (5.87, 0.34); (5.87, 0.29)\n", "Djimsiti (5.97, 0.39); (5.99, 0.40)\n", "Caldara (5.73, 0.52); (5.66, 0.56)\n", "Karsdorp (5.90, 0.40); (5.90, 0.40)\n", "Marchizza (5.84, 0.38); (5.80, 0.37)\n", "Kjaer (5.90, 0.38); (5.84, 0.35)\n", "Okoli (5.75, 0.46); (5.71, 0.45)\n", "Amione (5.67, 0.42); (5.60, 0.45)\n", "Ruggeri (5.87, 0.33); (5.85, 0.28)\n", "Zanoli (5.81, 0.37); (5.78, 0.34)\n", "Wisniewski (5.88, 0.47); (5.91, 0.57)\n", "Radovanovic (5.64, 0.40); (5.53, 0.39)\n", "Dermaku (5.94, 0.45); (5.99, 0.53)\n", "D'ambrosio (6.13, 0.37); (6.31, 0.52)\n", "De Silvestri (5.90, 0.51); (6.04, 0.72)\n", "Chiriches (5.76, 0.52); (5.70, 0.54)\n", "Murru (5.64, 0.40); (5.58, 0.44)\n", "Bonifazi (5.80, 0.42); (5.72, 0.41)\n", "Donati (5.79, 0.44); (5.75, 0.47)\n", "Walukiewicz (5.78, 0.39); (5.73, 0.38)\n", "Ranieri L. (5.83, 0.43); (5.85, 0.55)\n", "Gabbia (5.67, 0.47); (5.56, 0.47)\n", "Kumbulla (5.92, 0.33); (5.90, 0.29)\n", "Adopo (5.82, 0.31); (5.78, 0.27)\n", "Pirola (5.60, 0.49); (5.49, 0.49)\n", "Lovato (5.67, 0.54); (5.55, 0.52)\n", "Tuia (5.83, 0.48); (5.89, 0.63)\n", "Ferrer (5.84, 0.48); (5.85, 0.55)\n", "Antov (5.75, 0.53); (5.71, 0.56)\n", "Vasquez (5.79, 0.43); (5.72, 0.47)\n", "Ruan (5.78, 0.51); (5.63, 0.47)\n", "Ostigard (6.10, 0.34); (6.07, 0.35)\n", "Coppola D. (5.74, 0.38); (5.64, 0.39)\n", "Cacace (5.78, 0.40); (5.71, 0.37)\n", "Gatti (5.89, 0.40); (5.85, 0.38)\n", "Gila (5.90, 0.41); (5.88, 0.41)\n", "Bayeye (5.95, 0.44); (6.00, 0.51)\n", "Sambia (5.75, 0.43); (5.73, 0.44)\n", "Moutinho J. (5.76, 0.44); (5.69, 0.47)\n", "Conti (5.96, 0.45); (6.15, 0.68)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Marrone (5.60, 0.44); (5.50, 0.45)\n", "Tonelli (5.75, 0.45); (5.66, 0.43)\n", "Murillo (5.63, 0.35); (5.53, 0.33)\n", "Radu (6.08, 0.36); (5.94, 0.30)\n", "Paletta (5.89, 0.47); (5.96, 0.59)\n", "Florenzi (6.15, 0.44); (6.40, 0.63)\n", "Sala (5.85, 0.37); (5.86, 0.39)\n", "Fares (5.81, 0.39); (5.80, 0.42)\n", "Romagna (5.88, 0.48); (5.88, 0.55)\n", "Cassandro (5.94, 0.45); (6.00, 0.54)\n", "Muldur (5.75, 0.43); (5.67, 0.44)\n", "Amey (6.02, 0.45); (6.13, 0.55)\n", "Zanotti (5.93, 0.45); (6.00, 0.54)\n", "Ebosele (5.99, 0.34); (6.02, 0.34)\n", "Buta (5.94, 0.45); (6.01, 0.56)\n", "Abankwah (5.94, 0.45); (6.01, 0.56)\n", "Guessand A. (5.94, 0.45); (6.01, 0.56)\n", "Cabal (5.88, 0.48); (5.91, 0.57)\n", "Sosa (5.77, 0.48); (5.76, 0.56)\n", "Guarino (5.89, 0.46); (5.92, 0.53)\n", "Carboni F. (5.93, 0.46); (6.01, 0.54)\n", "Zaccagni (6.44, 0.66); (7.42, 1.59)\n", "Kvaratskhelia (6.57, 0.72); (7.58, 1.69)\n", "Milinkovic-Savic (6.28, 0.61); (7.10, 1.39)\n", "Barella (6.29, 0.58); (7.02, 1.24)\n", "Zielinski (6.34, 0.55); (7.00, 1.10)\n", "Luis Alberto (6.33, 0.53); (7.07, 1.15)\n", "Strefezza (6.33, 0.50); (7.15, 1.19)\n", "Felipe Anderson (6.20, 0.61); (7.07, 1.43)\n", "Koopmeiners (6.26, 0.60); (7.06, 1.35)\n", "Calhanoglu (6.27, 0.50); (6.81, 0.95)\n", "Frattesi (6.18, 0.62); (6.92, 1.32)\n", "Diaz B. (6.21, 0.63); (6.95, 1.31)\n", "Vlasic (6.18, 0.57); (6.83, 1.16)\n", "Zambo Anguissa (6.32, 0.55); (6.90, 1.04)\n", "Elmas (6.25, 0.53); (6.89, 1.06)\n", "Miranchuk (6.27, 0.59); (7.02, 1.26)\n", "Samardzic (6.19, 0.57); (6.84, 1.15)\n", "Pereyra (6.18, 0.55); (6.74, 1.06)\n", "Politano (6.24, 0.45); (6.80, 0.91)\n", "Rabiot (6.16, 0.57); (6.71, 1.08)\n", "Ciurria (6.07, 0.59); (6.68, 1.18)\n", "Lazovic (6.16, 0.55); (6.71, 1.03)\n", "Lobotka (6.20, 0.38); (6.56, 0.70)\n", "Radonjic (6.16, 0.48); (6.65, 0.88)\n", "Ferguson (6.20, 0.48); (6.73, 0.93)\n", "Bonaventura (6.14, 0.50); (6.57, 0.86)\n", "Pessina (6.17, 0.56); (6.72, 1.05)\n", "Tonali (6.10, 0.58); (6.57, 1.05)\n", "Kostic (6.17, 0.53); (6.69, 0.96)\n", "Baldanzi (6.31, 0.53); (7.11, 1.20)\n", "Lovric (6.12, 0.41); (6.50, 0.71)\n", "Pellegrini Lo. (6.10, 0.59); (6.68, 1.17)\n", "El Shaarawy (6.24, 0.49); (6.90, 1.04)\n", "Orsolini (6.23, 0.67); (7.12, 1.56)\n", "Ikone' (6.03, 0.57); (6.49, 1.02)\n", "Candreva (5.88, 0.57); (6.14, 0.84)\n", "Bennacer (6.12, 0.42); (6.37, 0.60)\n", "Pasalic (6.08, 0.59); (6.68, 1.17)\n", "Mkhitaryan (6.02, 0.46); (6.39, 0.78)\n", "Colpani (5.99, 0.43); (6.43, 0.82)\n", "Pogba (5.97, 0.44); (6.05, 0.52)\n", "Chiesa (6.17, 0.53); (6.62, 0.92)\n", "Bandinelli (5.98, 0.44); (6.19, 0.65)\n", "Matic (6.16, 0.40); (6.48, 0.66)\n", "Fagioli (6.18, 0.52); (6.69, 0.95)\n", "Messias (5.97, 0.54); (6.41, 0.98)\n", "Arslan (5.97, 0.38); (6.11, 0.48)\n", "Ricci S. (6.17, 0.42); (6.45, 0.66)\n", "Ranocchia F. (6.07, 0.45); (6.48, 0.79)\n", "Verdi (6.10, 0.41); (6.45, 0.68)\n", "Sensi (5.99, 0.58); (6.36, 0.97)\n", "Barak (5.86, 0.45); (6.03, 0.67)\n", "Soriano (6.02, 0.38); (6.17, 0.51)\n", "Dominguez (6.18, 0.53); (6.69, 1.00)\n", "Vilhena (5.87, 0.50); (6.08, 0.76)\n", "Brozovic (6.18, 0.46); (6.56, 0.77)\n", "Cristante (5.98, 0.43); (6.12, 0.57)\n", "Thorstvedt (5.92, 0.46); (6.11, 0.68)\n", "De Ketelaere (5.87, 0.40); (6.00, 0.54)\n", "Saponara (6.07, 0.57); (6.58, 1.05)\n", "Vecino (5.95, 0.44); (6.09, 0.59)\n", "Locatelli (6.07, 0.37); (6.14, 0.42)\n", "Zaniolo (5.91, 0.50); (6.16, 0.79)\n", "Duda (6.02, 0.46); (6.15, 0.59)\n", "Maldini (5.94, 0.45); (6.25, 0.72)\n", "Marin (5.90, 0.53); (6.08, 0.76)\n", "Zalewski (6.06, 0.35); (6.13, 0.40)\n", "Bajrami (6.21, 0.58); (6.85, 1.16)\n", "Coulibaly L. (5.83, 0.56); (6.03, 0.77)\n", "Gonzalez J. (6.07, 0.46); (6.40, 0.76)\n", "De Roon (6.03, 0.37); (6.08, 0.41)\n", "Mandragora (5.93, 0.46); (6.08, 0.68)\n", "Wijnaldum (5.91, 0.47); (5.98, 0.57)\n", "Bourabia (5.91, 0.41); (5.94, 0.46)\n", "Sottil (6.09, 0.58); (6.56, 1.03)\n", "Aebischer (5.99, 0.45); (6.25, 0.70)\n", "Ederson D.s. (5.88, 0.44); (6.04, 0.64)\n", "Miretti (5.98, 0.38); (6.10, 0.44)\n", "Blin (6.02, 0.33); (6.00, 0.31)\n", "Hjulmand (5.98, 0.54); (6.09, 0.63)\n", "Cataldi (6.02, 0.38); (6.03, 0.39)\n", "Djuricic (5.82, 0.46); (5.94, 0.65)\n", "Linetty (5.97, 0.43); (6.14, 0.62)\n", "Haas (5.92, 0.41); (6.08, 0.58)\n", "Walace (5.93, 0.38); (5.93, 0.40)\n", "Agudelo (5.86, 0.36); (5.91, 0.42)\n", "Pobega (5.99, 0.44); (6.28, 0.70)\n", "Camara Ma. (6.13, 0.35); (6.18, 0.42)\n", "Paredes (5.85, 0.35); (5.83, 0.31)\n", "Ndombele' (5.96, 0.34); (5.94, 0.30)\n", "Nicolussi Caviglia (5.76, 0.56); (5.92, 0.79)\n", "Rovella (5.92, 0.48); (5.94, 0.48)\n", "Amrabat (5.89, 0.44); (5.88, 0.48)\n", "Tameze (5.91, 0.41); (5.94, 0.48)\n", "Gyasi (5.88, 0.51); (6.07, 0.77)\n", "Ilic (6.01, 0.45); (6.13, 0.56)\n", "Matheus Henrique (5.94, 0.44); (6.07, 0.59)\n", "Harroui (5.88, 0.42); (6.03, 0.59)\n", "Volpato (6.05, 0.56); (6.58, 1.09)\n", "Pickel (5.79, 0.38); (5.81, 0.47)\n", "Moro N. (6.03, 0.34); (6.11, 0.40)\n", "Duncan (5.92, 0.41); (6.05, 0.58)\n", "Machin (5.91, 0.47); (6.02, 0.63)\n", "Cuadrado (5.95, 0.48); (6.05, 0.57)\n", "Ekdal (5.84, 0.37); (5.81, 0.38)\n", "Meite' (5.85, 0.46); (5.88, 0.59)\n", "Schouten (5.99, 0.40); (6.02, 0.44)\n", "Obiang (5.98, 0.33); (5.98, 0.31)\n", "Kovalenko (5.92, 0.39); (6.01, 0.50)\n", "Crnigoj (5.93, 0.44); (6.13, 0.64)\n", "Basic (5.98, 0.33); (6.05, 0.35)\n", "Asllani (5.96, 0.33); (5.99, 0.32)\n", "Sabiri (5.85, 0.46); (5.99, 0.66)\n", "Terracciano F. (6.06, 0.32); (6.09, 0.34)\n", "Castagnetti (5.87, 0.32); (5.87, 0.27)\n", "Oudin (5.87, 0.34); (5.92, 0.33)\n", "Grassi (5.92, 0.35); (5.91, 0.32)\n", "Krunic (5.93, 0.40); (6.02, 0.49)\n", "Rincon (5.80, 0.40); (5.76, 0.45)\n", "Miguel Veloso (5.95, 0.37); (5.97, 0.38)\n", "Leris (5.78, 0.40); (5.79, 0.51)\n", "Esposito Sa. (5.83, 0.52); (5.90, 0.61)\n", "Henderson L. (5.92, 0.39); (6.03, 0.49)\n", "Lopez M. (5.90, 0.44); (5.89, 0.49)\n", "Cuisance (5.79, 0.37); (5.75, 0.39)\n", "Saelemaekers (5.85, 0.40); (5.97, 0.52)\n", "Maggiore (5.93, 0.40); (6.05, 0.51)\n", "Akpa Akpro (5.91, 0.46); (5.95, 0.56)\n", "Maleh (5.97, 0.39); (6.17, 0.56)\n", "Romero L. (6.20, 0.52); (6.80, 1.04)\n", "Ceide (5.87, 0.36); (5.88, 0.36)\n", "D'alessandro (6.06, 0.33); (6.15, 0.39)\n", "Benassi (5.80, 0.34); (5.81, 0.35)\n", "Gagliardini (5.84, 0.32); (5.86, 0.32)\n", "Vieira (5.86, 0.35); (5.85, 0.42)\n", "Bianco (6.03, 0.42); (6.15, 0.53)\n", "Vranckx (6.07, 0.39); (6.25, 0.50)\n", "Galdames (5.90, 0.47); (5.98, 0.64)\n", "Marcos Antonio (5.94, 0.30); (5.91, 0.24)\n", "Fazzini (5.79, 0.33); (5.73, 0.30)\n", "Sulemana I. (5.87, 0.32); (5.86, 0.32)\n", "Tahirovic (6.00, 0.30); (5.99, 0.27)\n", "Abildgaard (5.90, 0.44); (5.93, 0.55)\n", "Barberis (5.87, 0.49); (5.91, 0.57)\n", "Kastanos (5.80, 0.33); (5.80, 0.32)\n", "Vignato (5.95, 0.36); (5.98, 0.35)\n", "Valoti (5.77, 0.33); (5.71, 0.32)\n", "Winks (5.88, 0.45); (5.89, 0.51)\n", "Askildsen (5.74, 0.33); (5.69, 0.32)\n", "Bove (5.75, 0.37); (5.73, 0.41)\n", "Bohinen (5.75, 0.31); (5.71, 0.26)\n", "D'andrea (5.97, 0.39); (6.10, 0.50)\n", "Iling-Junior (6.06, 0.36); (6.19, 0.45)\n", "Cipot (5.87, 0.52); (6.00, 0.70)\n", "Bakayoko (5.81, 0.39); (5.78, 0.36)\n", "Gaetano (6.00, 0.42); (6.08, 0.51)\n", "Zurkowski (6.12, 0.55); (6.66, 1.08)\n", "Castrovilli (6.00, 0.46); (6.28, 0.72)\n", "Demme (6.03, 0.37); (6.20, 0.48)\n", "Darboe (5.95, 0.46); (5.98, 0.49)\n", "Urbanski (5.98, 0.46); (6.09, 0.59)\n", "Bertini (5.97, 0.45); (6.08, 0.56)\n", "Yepes (5.79, 0.55); (5.79, 0.61)\n", "Pyyhtia (6.00, 0.39); (6.07, 0.46)\n", "Trimboli (5.88, 0.46); (5.92, 0.58)\n", "Pafundi (5.95, 0.45); (6.04, 0.57)\n", "Helgason (5.82, 0.32); (5.82, 0.28)\n", "Adli (5.92, 0.40); (6.02, 0.52)\n", "Vignato S. (6.04, 0.45); (6.18, 0.57)\n", "Hrustic (5.75, 0.37); (5.72, 0.37)\n", "Samek (5.96, 0.45); (6.05, 0.57)\n", "Zerbin (6.05, 0.42); (6.19, 0.53)\n", "Ilkhan (5.92, 0.49); (5.99, 0.57)\n", "Degli Innocenti (5.90, 0.45); (5.94, 0.53)\n", "Acella (5.90, 0.47); (5.98, 0.64)\n", "Carboni V. (5.89, 0.47); (5.97, 0.59)\n", "Paoletti (6.03, 0.40); (6.10, 0.45)\n", "Malagrida (5.90, 0.46); (5.95, 0.58)\n", "Faticanti (5.96, 0.45); (6.05, 0.56)\n", "Osimhen (6.49, 0.75); (7.89, 2.22)\n", "Martinez L. (6.32, 0.71); (7.68, 2.04)\n", "Dybala (6.49, 0.67); (7.48, 1.61)\n", "Rafael Leao (6.32, 0.71); (7.44, 1.82)\n", "Lookman (6.40, 0.72); (7.68, 2.00)\n", "Immobile (6.30, 0.71); (7.65, 2.02)\n", "Vlahovic (6.29, 0.72); (7.73, 2.12)\n", "Arnautovic (6.21, 0.67); (7.33, 1.73)\n", "Dia (6.12, 0.68); (7.25, 1.73)\n", "Dzeko (6.20, 0.67); (7.31, 1.71)\n", "Milik (6.29, 0.62); (7.19, 1.48)\n", "Nzola (6.11, 0.66); (7.22, 1.69)\n", "Beto (6.06, 0.61); (6.94, 1.42)\n", "Giroud (6.13, 0.65); (6.97, 1.45)\n", "Abraham (6.19, 0.65); (7.28, 1.69)\n", "Deulofeu (6.30, 0.64); (7.19, 1.48)\n", "Lauriente' (6.28, 0.68); (7.19, 1.59)\n", "Simeone (6.25, 0.70); (7.47, 1.86)\n", "Lozano (6.15, 0.59); (6.89, 1.27)\n", "Correa (6.11, 0.50); (6.81, 1.10)\n", "Berardi (6.28, 0.71); (7.53, 1.94)\n", "Pedro (6.20, 0.57); (6.86, 1.19)\n", "Lukaku (5.96, 0.56); (6.48, 1.04)\n", "Sanabria (6.01, 0.58); (6.58, 1.11)\n", "Thauvin (6.38, 0.65); (7.30, 1.52)\n", "Cabral (6.01, 0.57); (6.57, 1.10)\n", "Hojlund (6.07, 0.62); (6.88, 1.38)\n", "Caprari (5.99, 0.54); (6.51, 1.03)\n", "Di Maria (6.26, 0.67); (7.21, 1.61)\n", "Piatek (5.89, 0.54); (6.34, 0.96)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Rebic (6.19, 0.67); (6.98, 1.46)\n", "Bonazzoli (6.01, 0.50); (6.43, 0.88)\n", "Zapata D. (5.89, 0.50); (6.25, 0.84)\n", "Kouame' (6.01, 0.58); (6.51, 1.07)\n", "Gonzalez N. (6.23, 0.62); (7.02, 1.36)\n", "Brekalo (6.05, 0.58); (6.64, 1.14)\n", "Mota (6.07, 0.63); (6.87, 1.38)\n", "Kean (6.06, 0.62); (6.74, 1.27)\n", "Okereke (5.95, 0.55); (6.41, 1.00)\n", "Ceesay (5.99, 0.49); (6.46, 0.90)\n", "Colombo (6.06, 0.60); (6.68, 1.20)\n", "Dessers (5.95, 0.50); (6.38, 0.91)\n", "Muriel (6.12, 0.63); (6.76, 1.28)\n", "Pinamonti (5.90, 0.55); (6.37, 0.99)\n", "Di Francesco F. (6.05, 0.52); (6.45, 0.91)\n", "Jovic (5.96, 0.56); (6.37, 0.98)\n", "Origi (5.96, 0.56); (6.39, 0.99)\n", "Caputo (6.01, 0.59); (6.72, 1.26)\n", "Boga (6.42, 0.65); (7.26, 1.40)\n", "Cambiaghi (6.10, 0.48); (6.53, 0.84)\n", "Alvarez A. (6.03, 0.56); (6.50, 1.03)\n", "Banda (5.99, 0.39); (6.18, 0.53)\n", "Ciofani D. (5.98, 0.52); (6.44, 0.96)\n", "Petagna (5.97, 0.56); (6.46, 1.03)\n", "Barrow (6.05, 0.60); (6.58, 1.12)\n", "Djuric (5.98, 0.38); (6.17, 0.51)\n", "Henry (5.89, 0.52); (6.25, 0.87)\n", "Success (5.94, 0.37); (6.10, 0.50)\n", "Gabbiadini (5.96, 0.58); (6.45, 1.06)\n", "Zirkzee (6.04, 0.51); (6.50, 0.89)\n", "Lammers (5.83, 0.41); (5.94, 0.55)\n", "Satriano (5.86, 0.45); (6.00, 0.62)\n", "Kallon (5.87, 0.41); (6.02, 0.58)\n", "Nestorovski (6.23, 0.50); (7.01, 1.13)\n", "Raspadori (6.02, 0.52); (6.50, 0.96)\n", "Botheim (5.90, 0.49); (6.28, 0.84)\n", "Gytkjaer (5.85, 0.44); (6.08, 0.67)\n", "Solbakken (6.12, 0.51); (6.38, 0.73)\n", "Lasagna (5.78, 0.43); (5.89, 0.56)\n", "Belotti (5.69, 0.33); (5.71, 0.33)\n", "Pellegri (5.94, 0.47); (6.20, 0.75)\n", "Buonaiuto (5.92, 0.37); (6.05, 0.48)\n", "Verde (6.01, 0.48); (6.45, 0.89)\n", "Destro (5.95, 0.59); (6.47, 1.09)\n", "Seck (6.10, 0.35); (6.23, 0.45)\n", "Sansone (5.96, 0.50); (6.23, 0.80)\n", "Quagliarella (5.83, 0.39); (5.91, 0.50)\n", "Defrel (5.87, 0.48); (6.10, 0.73)\n", "Pjaca (5.87, 0.43); (6.01, 0.56)\n", "Gaich (5.86, 0.52); (6.23, 0.88)\n", "Soule' (6.18, 0.40); (6.49, 0.65)\n", "Tsadjout (5.83, 0.39); (5.91, 0.51)\n", "Piccoli (5.96, 0.56); (6.53, 1.09)\n", "Shomurodov (6.01, 0.53); (6.52, 1.01)\n", "Afena-Gyan (5.68, 0.33); (5.65, 0.33)\n", "Ngonge (6.01, 0.46); (6.19, 0.64)\n", "Karamoh (5.92, 0.49); (6.24, 0.78)\n", "Ibrahimovic (6.23, 0.64); (7.23, 1.56)\n", "Pussetto (5.90, 0.51); (6.26, 0.87)\n", "Cancellieri (5.77, 0.29); (5.79, 0.24)\n", "Valencia D. (5.73, 0.29); (5.68, 0.30)\n", "Oddei (6.08, 0.45); (6.28, 0.62)\n", "Braaf (5.89, 0.50); (5.99, 0.69)\n", "Raimondo (6.00, 0.48); (6.18, 0.66)\n", "Kaio Jorge (5.87, 0.30); (5.93, 0.26)\n", "De Luca (5.90, 0.47); (5.99, 0.63)\n", "Voelkerling Persson (5.86, 0.41); (5.88, 0.45)\n", "Montevago (5.66, 0.32); (5.61, 0.32)\n", "Krollis (5.91, 0.49); (6.02, 0.67)\n", "Vivaldo (5.94, 0.47); (6.07, 0.63)\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
roleteamoppteamhomestartervote%MVMV stdFVFV stdMV locMV scaleMV skewnessMV tailweightFV locFV scaleFV skewnessFV tailweightClean Sheet %
player
SportielloPAtalantaAvg1006.2316510.4153215.7522000.4663985.9918270.2614920.5936561.5897646.1556900.590086-0.4689421.05647451.863781
MussoPAtalantaAvg111006.2360960.4067234.9877620.6286556.0060060.2658510.5673401.5901645.4374330.847580-0.3824341.02644725.157676
Rossi F.PAtalantaAvg1006.0001380.4557283.4212531.0693725.7434560.3022200.5592171.5849534.5156150.947310-0.8582680.9713220.053009
ToloiDAtalantaAvg11766.1824710.4970416.5101970.7675266.1182150.5683530.0832370.9741075.9491161.0457150.3767681.5998780.000000
ScalviniDAtalantaAvg11806.1063350.5422636.4845680.8881506.0352030.6188260.0843940.9432025.8001931.1675020.4074051.5998530.000000
............................................................
NgongeAVeronaAvg1096.0123850.4609146.1927690.6422345.9485070.5269570.0894401.0271535.7537530.9098690.3430631.5998840.000000
DjuricAVeronaAvg10765.9832040.3825596.1697580.5139845.9213250.4355830.1049661.1182635.8214420.7313870.3390151.5999050.000000
KallonAVeronaAvg10765.8726360.4126386.0247730.5804595.8015790.4676570.1121881.0942015.5841900.7714890.3988691.5998870.000000
BraafAVeronaAvg1045.8904890.4995805.9897700.6871505.8540360.5808560.0462501.0004025.5307680.9848640.3323061.5998530.000000
LasagnaAVeronaAvg11805.7785220.4289155.8883830.5595435.7078190.4872410.1070391.0832485.4726440.7542830.3861471.5998870.000000
\n", "

520 rows × 19 columns

\n", "
" ], "text/plain": [ " role team oppteam home starter vote% MV MV std \\\n", "player \n", "Sportiello P Atalanta Avg 1 0 0 6.231651 0.415321 \n", "Musso P Atalanta Avg 1 1 100 6.236096 0.406723 \n", "Rossi F. P Atalanta Avg 1 0 0 6.000138 0.455728 \n", "Toloi D Atalanta Avg 1 1 76 6.182471 0.497041 \n", "Scalvini D Atalanta Avg 1 1 80 6.106335 0.542263 \n", "... ... ... ... ... ... ... ... ... \n", "Ngonge A Verona Avg 1 0 9 6.012385 0.460914 \n", "Djuric A Verona Avg 1 0 76 5.983204 0.382559 \n", "Kallon A Verona Avg 1 0 76 5.872636 0.412638 \n", "Braaf A Verona Avg 1 0 4 5.890489 0.499580 \n", "Lasagna A Verona Avg 1 1 80 5.778522 0.428915 \n", "\n", " FV FV std MV loc MV scale MV skewness \\\n", "player \n", "Sportiello 5.752200 0.466398 5.991827 0.261492 0.593656 \n", "Musso 4.987762 0.628655 6.006006 0.265851 0.567340 \n", "Rossi F. 3.421253 1.069372 5.743456 0.302220 0.559217 \n", "Toloi 6.510197 0.767526 6.118215 0.568353 0.083237 \n", "Scalvini 6.484568 0.888150 6.035203 0.618826 0.084394 \n", "... ... ... ... ... ... \n", "Ngonge 6.192769 0.642234 5.948507 0.526957 0.089440 \n", "Djuric 6.169758 0.513984 5.921325 0.435583 0.104966 \n", "Kallon 6.024773 0.580459 5.801579 0.467657 0.112188 \n", "Braaf 5.989770 0.687150 5.854036 0.580856 0.046250 \n", "Lasagna 5.888383 0.559543 5.707819 0.487241 0.107039 \n", "\n", " MV tailweight FV loc FV scale FV skewness FV tailweight \\\n", "player \n", "Sportiello 1.589764 6.155690 0.590086 -0.468942 1.056474 \n", "Musso 1.590164 5.437433 0.847580 -0.382434 1.026447 \n", "Rossi F. 1.584953 4.515615 0.947310 -0.858268 0.971322 \n", "Toloi 0.974107 5.949116 1.045715 0.376768 1.599878 \n", "Scalvini 0.943202 5.800193 1.167502 0.407405 1.599853 \n", "... ... ... ... ... ... \n", "Ngonge 1.027153 5.753753 0.909869 0.343063 1.599884 \n", "Djuric 1.118263 5.821442 0.731387 0.339015 1.599905 \n", "Kallon 1.094201 5.584190 0.771489 0.398869 1.599887 \n", "Braaf 1.000402 5.530768 0.984864 0.332306 1.599853 \n", "Lasagna 1.083248 5.472644 0.754283 0.386147 1.599887 \n", "\n", " Clean Sheet % \n", "player \n", "Sportiello 51.863781 \n", "Musso 25.157676 \n", "Rossi F. 0.053009 \n", "Toloi 0.000000 \n", "Scalvini 0.000000 \n", "... ... \n", "Ngonge 0.000000 \n", "Djuric 0.000000 \n", "Kallon 0.000000 \n", "Braaf 0.000000 \n", "Lasagna 0.000000 \n", "\n", "[520 rows x 19 columns]" ] }, "execution_count": 61, "metadata": {}, "output_type": "execute_result" } ], "source": [ "output = pd.DataFrame(columns = ['player', 'role', 'team', 'oppteam', 'home', 'starter', 'vote%', 'MV', 'MV std', 'FV', 'FV std', 'MV loc', 'MV scale', 'MV skewness', 'MV tailweight', 'FV loc', 'FV scale', 'FV skewness', 'FV tailweight', 'Clean Sheet %'])\n", "\n", "tot_matches = 2 # home and not home\n", "\n", "current_season_games = max(players_orig['games'])\n", "\n", "for i in range(players.shape[0]):\n", " try:\n", " home = 0\n", "\n", " for k in range(tot_matches):\n", " #matchday_out = k + 1\n", " #[player, team, oppteam, home] = PlayerMatch(players.index[i], matchday_out)\n", "\n", " player = players.index[i]\n", " team = players['team'][i]\n", " oppteam = 'Avg'\n", " home = not home\n", "\n", " [mean, std, dist] = vote_predict_NNb(player, team, oppteam, home = home)\n", "\n", " role = players['r'][player] \n", "\n", " starter = 0\n", " voteperc = 0\n", "\n", " games = max( players_orig['games'][i], players_orig['gk_games'][i] )\n", " mins = max( players_orig['minutes'][i], players_orig['gk_minutes'][i] )\n", "\n", " cs = 0\n", " if(role == 'P'):\n", " cs = dist[2].probs.numpy()[0] * 100\n", "\n", " starter = int( player in gk_starters )\n", " if(starter):\n", " voteperc = 100\n", " else:\n", " voteperc = 0\n", " else:\n", " starter = int ( 1 * (games >= current_season_games * 2/3 and mins / games >= 45 ) )\n", " voteperc = int( min( 1, games / current_season_games ) * 100) \n", "\n", " if(k == 0):\n", " row = [player, role, team, 'Avg', 1, starter, voteperc]\n", "\n", " numrow_ = [mean[0], std[0], \n", " mean[1], std[1], \n", " dist[0].loc.numpy()[0], dist[0].scale.numpy()[0], \n", " dist[0].skewness.numpy()[0], dist[0].tailweight.numpy()[0], \n", " dist[1].loc.numpy()[0], dist[1].scale.numpy()[0], \n", " dist[1].skewness.numpy()[0], dist[1].tailweight.numpy()[0],\n", " cs] \n", "\n", " if(k == 0):\n", " numrow = numrow_\n", " else:\n", " for j in range(len(numrow)):\n", " numrow[j] += numrow_[j]\n", "\n", " for j in range(len(numrow)):\n", " numrow[j] /= tot_matches\n", "\n", " print(players.index[i] + ' (' + \"{:.2f}\".format(numrow[0]) + ', ' + \"{:.2f}\".format(numrow[1]) + \n", " '); (' + \"{:.2f}\".format(numrow[2]) + ', ' + \"{:.2f}\".format(numrow[3]) + ')' )\n", "\n", " row += numrow # list concat\n", "\n", " row_df = pd.DataFrame(data = [row], columns = output.columns)\n", "\n", " output = pd.concat([output, row_df])\n", " except:\n", " print(players.index[i] + ' no data')\n", " \n", " \n", "\n", "output = output.set_index('player')\n", "\n", "output = output.sort_values(['team', 'role', 'FV'], ascending = [True, False, False])\n", "#output.to_excel('outputs/pred_matchday_' + str(matchday_out) + '.xlsx')\n", "\n", "output" ] }, { "cell_type": "code", "execution_count": 62, "id": "b47cbd63", "metadata": {}, "outputs": [], "source": [ "import shutil\n", "\n", "output = output.sort_values(['role', 'FV'], ascending = [False, False])\n", "\n", "template_file = 'outputs/pred_matchday_base.xlsx'\n", "dest_file = 'outputs/pred_avg_seriea.xlsx'\n", "\n", "shutil.copyfile(template_file, dest_file)\n", "\n", "with pd.ExcelWriter(dest_file, mode = 'a', engine=\"openpyxl\", if_sheet_exists = 'replace') as writer: \n", " output.to_excel(writer, sheet_name='data')" ] }, { "cell_type": "markdown", "id": "cf9df3bb", "metadata": {}, "source": [ "Various predictions." ] }, { "cell_type": "code", "execution_count": 34, "id": "7300f3c2", "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Meret: MV 6.28 ± 0.85; FV 5.50 + 1.44 (51.2% cs)\n", "Szczesny: MV 6.24 ± 0.82; FV 5.66 + 1.20 (64.1% cs)\n", "Provedel: MV 6.25 ± 0.83; FV 5.65 + 1.27 (62.9% cs)\n", "Maignan: MV 6.51 ± 0.90; FV 5.93 + 1.10 (45.0% cs)\n", "Rui Patricio: MV 6.05 ± 0.77; FV 5.38 + 1.25 (53.8% cs)\n", "Onana: MV 6.37 ± 0.78; FV 5.16 + 1.17 (18.4% cs)\n", "Milinkovic-Savic V.: MV 6.20 ± 0.77; FV 5.35 + 0.89 (26.9% cs)\n", "Musso: MV 6.36 ± 0.86; FV 5.64 + 1.24 (43.8% cs)\n", "Vicario: MV 6.46 ± 0.87; FV 5.88 + 1.21 (60.8% cs)\n", "Silvestri: MV 6.39 ± 0.83; FV 5.71 + 1.16 (46.2% cs)\n", "Terracciano: MV 6.19 ± 0.77; FV 4.58 + 1.10 (4.1% cs)\n", "Skorupski: MV 6.17 ± 0.71; FV 4.56 + 0.94 (5.2% cs)\n", "Falcone: MV 6.37 ± 0.84; FV 5.13 + 1.02 (8.7% cs)\n", "Di Gregorio: MV 6.42 ± 0.87; FV 5.69 + 0.99 (36.9% cs)\n", "Consigli: MV 6.39 ± 0.78; FV 4.83 + 1.19 (7.7% cs)\n", "Carnesecchi: MV 6.33 ± 0.82; FV 5.49 + 1.28 (37.1% cs)\n", "Montipo': MV 6.30 ± 0.89; FV 4.39 + 1.24 (2.4% cs)\n", "Audero: MV 6.26 ± 0.81; FV 4.60 + 1.03 (4.2% cs)\n", "Dragowski: MV 6.37 ± 0.81; FV 4.71 + 1.13 (3.1% cs)\n", "Ochoa: MV 6.44 ± 0.82; FV 5.12 + 1.19 (6.2% cs)\n", "Tatarusanu: MV 5.86 ± 0.65; FV 3.31 + 2.21 (0.9% cs)\n", "Handanovic: MV 6.09 ± 0.70; FV 4.79 + 1.18 (11.7% cs)\n", "Sportiello: MV 6.22 ± 0.78; FV 5.37 + 1.22 (27.8% cs)\n", "Sepe: MV 6.52 ± 0.80; FV 5.22 + 1.24 (12.7% cs)\n" ] }, { "data": { "text/plain": [ "[array([6.51791594, 5.21583604]),\n", " array([0.40012765, 0.61914635], dtype=float32),\n", " [,\n", " ,\n", " ]]" ] }, "execution_count": 34, "metadata": {}, "output_type": "execute_result" } ], "source": [ "predict_player('Meret', log = 1, plot = 0)\n", "predict_player('Szczesny', log = 1, plot = 0)\n", "predict_player('Provedel', log = 1, plot = 0)\n", "predict_player('Maignan', log = 1, plot = 0)\n", "predict_player('Rui Patricio', log = 1, plot = 0)\n", "predict_player('Onana', log = 1, plot = 0)\n", "predict_player('Milinkovic-Savic V.', log = 1, plot = 0)\n", "predict_player('Musso', log = 1, plot = 0)\n", "predict_player('Vicario', log = 1, plot = 0)\n", "predict_player('Silvestri', log = 1, plot = 0)\n", "predict_player('Terracciano', log = 1, plot = 0)\n", "predict_player('Skorupski', log = 1, plot = 0)\n", "predict_player('Falcone', log = 1, plot = 0)\n", "predict_player('Di Gregorio', log = 1, plot = 0)\n", "predict_player('Consigli', log = 1, plot = 0)\n", "predict_player('Carnesecchi', log = 1, plot = 0)\n", "predict_player('Montipo\\'', log = 1, plot = 0)\n", "predict_player('Audero', log = 1, plot = 0)\n", "predict_player('Dragowski', log = 1, plot = 0)\n", "predict_player('Ochoa', log = 1, plot = 0)\n", "predict_player('Tatarusanu', log = 1, plot = 0)\n", "predict_player('Handanovic', log = 1, plot = 0)\n", "predict_player('Sportiello', log = 1, plot = 0)\n", "predict_player('Sepe', log = 1, plot = 0)" ] }, { "cell_type": "code", "execution_count": 36, "id": "bd126870", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Muriel: MV 6.20 ± 1.32; FV 7.29 + 3.53\n", "Tonali: MV 6.23 ± 0.95; FV 6.69 + 1.86\n", "Lobotka: MV 6.17 ± 0.72; FV 6.42 + 1.16\n", "Politano: MV 6.19 ± 0.77; FV 6.62 + 1.48\n", "Zapata D.: MV 6.09 ± 1.19; FV 7.18 + 3.36\n", "Frattesi: MV 6.23 ± 1.19; FV 7.37 + 3.58\n", "Gonzalez N.: MV 6.05 ± 1.07; FV 6.65 + 2.25\n", "Abraham: MV 6.20 ± 1.30; FV 7.66 + 4.26\n", "Pobega: MV 6.02 ± 0.68; FV 6.13 + 0.92\n", "Mario Rui: MV 6.10 ± 0.77; FV 6.25 + 0.98\n", "Cuadrado: MV 5.82 ± 0.95; FV 5.80 + 0.92\n", "Skriniar: MV 5.75 ± 0.68; FV 5.70 + 0.58\n", "Lukaku: MV 6.41 ± 1.42; FV 8.29 + 5.46\n" ] }, { "data": { "text/plain": [ "[array([6.41176047, 8.29456946]),\n", " array([0.70926785, 2.7289915 ], dtype=float32),\n", " [,\n", " ]]" ] }, "execution_count": 36, "metadata": {}, "output_type": "execute_result" } ], "source": [ "predict_player('Muriel', plot = 0, log = 1)\n", "predict_player('Tonali', plot = 0, log = 1)\n", "predict_player('Lobotka', plot = 0, log = 1)\n", "predict_player('Politano', plot = 0, log = 1)\n", "predict_player('Zapata D.', plot = 0, log = 1)\n", "predict_player('Frattesi', plot = 0, log = 1)\n", "predict_player('Gonzalez N.', plot = 0, log = 1)\n", "predict_player('Abraham', plot = 0, log = 1)\n", "predict_player('Pobega', plot = 0, log = 1)\n", "predict_player('Mario Rui', plot = 0, log = 1)\n", "predict_player('Cuadrado', plot = 0, log = 1)\n", "predict_player('Skriniar', plot = 0, log = 1)\n", "predict_player('Lukaku', plot = 0, log = 1)" ] }, { "cell_type": "code", "execution_count": 37, "id": "4b9f5a7d", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Skriniar: MV 6.14 ± 0.82; FV 6.38 + 1.13\n", "Cuadrado: MV 6.29 ± 0.96; FV 6.83 + 1.94\n", "Bastoni: MV 6.13 ± 0.73; FV 6.32 + 0.98\n", "Barak: MV 6.31 ± 1.41; FV 7.50 + 3.97\n", "Politano: MV 6.18 ± 0.82; FV 6.57 + 1.55\n", "Smalling: MV 6.17 ± 0.86; FV 6.56 + 1.43\n", "Gosens: MV 6.05 ± 0.54; FV 6.11 + 0.66\n" ] }, { "data": { "text/plain": [ "[array([6.04807256, 6.10812885]),\n", " array([0.27137518, 0.32888246], dtype=float32),\n", " [,\n", " ]]" ] }, "execution_count": 37, "metadata": {}, "output_type": "execute_result" } ], "source": [ "predict_player('Skriniar', log = 1, oldseason= True)\n", "predict_player('Cuadrado', log = 1, oldseason= True)\n", "predict_player('Bastoni', log = 1, oldseason= True)\n", "predict_player('Barak', log = 1, oldseason= True)\n", "predict_player('Politano', log = 1, oldseason= True)\n", "predict_player('Smalling', log = 1, oldseason= True)\n", "predict_player('Gosens', log = 1, oldseason= True)\n", "\n", "predict_player('Skriniar', log = 1, oldseason= False)\n", "predict_player('Cuadrado', log = 1, oldseason= False)\n", "predict_player('Bastoni', log = 1, oldseason= False)\n", "predict_player('Barak', log = 1, oldseason= False)\n", "predict_player('Politano', log = 1, oldseason= False)\n", "predict_player('Smalling', log = 1, oldseason= False)\n", "predict_player('Gosens', log = 1, oldseason= False)" ] }, { "cell_type": "code", "execution_count": 34, "id": "10c7ad3e", "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "Rafael Leao: MV 6.34 ± 1.43; FV 7.95 + 4.79\n" ] }, { "data": { "text/plain": [ "[array([6.3442238 , 7.94607029]),\n", " array([0.71331024, 2.395806 ], dtype=float32),\n", " [,\n", " ]]" ] }, "execution_count": 34, "metadata": {}, "output_type": "execute_result" } ], "source": [ "predict_player('Rafael Leao', plot = 1, log = 1)" ] }, { "cell_type": "markdown", "id": "0a5de8a1", "metadata": {}, "source": [ "Code for predicting the probability distribution of total team points" ] }, { "cell_type": "code", "execution_count": 98, "id": "65f9a572", "metadata": {}, "outputs": [], "source": [ "squad = ['Szczesny',\n", " 'Demiral',\n", " 'Kim',\n", " 'Di Lorenzo',\n", " 'Valeri',\n", " 'Kostic',\n", " 'Frattesi',\n", " 'Barella',\n", " 'Strefezza',\n", " 'Rafael Leao',\n", " 'Hojlund']\n", "\n", "\n", "dist = [None] * len(squad)\n", "\n", "defenders = list([0]) * len(squad)\n", "\n", "\n", "for i in range(len(squad)):\n", " [X, y, dist[i]] = predict_player(squad[i], plot = 0, log = 0) \n", " \n", " if(players['r'][squad[i]] == 'D'):\n", " defenders[i] = 1" ] }, { "cell_type": "code", "execution_count": 99, "id": "2e78f674", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Avg Total Points = 76.45314080810547\n", "Avg Mod Points = 1.548\n", "Avg Clean Sheets = 0.34\n" ] } ], "source": [ "ITERS = 500\n", "\n", "MOD = True\n", "\n", "total_points = np.zeros(ITERS)\n", "clean_sheets = np.zeros(ITERS)\n", "mod_points = np.zeros(ITERS)\n", "\n", "mv_samples = [None] * len(squad)\n", "fv_samples = [None] * len(squad)\n", "\n", "for i in range(len(squad)):\n", " mv_samples[i] = dist[i][0].sample(ITERS)\n", " fv_samples[i] = dist[i][1].sample(ITERS)\n", " \n", "cs_samples = dist[0][2].sample(ITERS)\n", "\n", "for k in range(ITERS):\n", " d_points = list([0]) * len(squad)\n", " \n", " cleansheet = float(cs_samples[k])\n", " total_points[k] += cleansheet\n", " clean_sheets[k] += cleansheet\n", " \n", " for i in range(len(squad)): \n", " if(defenders[i] == 1):\n", " d_points[i] = float(mv_samples[i][k])\n", "\n", " total_points[k] += float(fv_samples[i][k])\n", " \n", " d_points.sort(reverse = True)\n", "\n", " if(MOD and d_points[3] > 0): # minimum 3 defenders to get MOD\n", " mod_avg = 0\n", " for j in range(3):\n", " mod_avg += round(d_points[j] * 2) / 2\n", " mod_avg /= 3\n", "\n", " if(mod_avg >= 7):\n", " mod_points[k] = 6\n", " elif(mod_avg >= 6.5):\n", " mod_points[k] = 3\n", " elif(mod_avg >= 6):\n", " mod_points[k] = 1\n", "\n", " total_points[k] += mod_points[k]\n", " \n", " \n", "print('Avg Total Points = ' + str(total_points.mean()))\n", "print('Avg Mod Points = ' + str(mod_points.mean()))\n", "print('Avg Clean Sheets = ' + str(clean_sheets.mean()))\n" ] }, { "cell_type": "code", "execution_count": 100, "id": "c5d752d8", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 100, "metadata": {}, "output_type": "execute_result" } ], "source": [ "loc_0 = total_points.mean()\n", "\n", "squad_model = tf.keras.Sequential(\n", " [\n", " tf.keras.layers.Dense(3),\n", " tfp.layers.DistributionLambda(\n", " lambda t: tfp.distributions.SinhArcsinh(loc= loc_0 + t[..., 0], scale = 1e-3 + tf.math.softplus(t[..., 1]), \n", " skewness = t[..., 2], tailweight = 0.8) # fixed tailweight seems ok\n", " )\n", " ]\n", ")\n", "\n", "def negloglik(y, distr):\n", " return -distr.log_prob(y)\n", "\n", "squad_model.compile(optimizer=tf.optimizers.Adam(learning_rate=1), loss=negloglik)\n", "\n", "dummy_input = np.zeros(total_points.shape)[:, np.newaxis]\n", "squad_model.fit(dummy_input, total_points, epochs=100, verbose=False)" ] }, { "cell_type": "code", "execution_count": 101, "id": "9754ec4c", "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "squad_points_dist = squad_model(np.zeros(1)[:, np.newaxis])\n", "\n", "\n", "x = np.arange(start = 0, stop = 200, step = 0.001)\n", "prb = squad_points_dist.prob(x)\n", "\n", "mn = total_points.mean()\n", "\n", "f, ax = plt.subplots(1, 2)\n", "\n", "ax[0].plot(x, prb)\n", "ax[0].fill_between(x, prb, color = 'lightblue')\n", "ax[0].vlines(x = mn, color = 'grey', ymin = 0, ymax = 3, linestyle = 'dashed', label = 'mean = ' + \"{:.2f}\".format(mn))\n", "\n", "ax[0].set_xlim([40, 120])\n", "ax[0].set_ylim([0, 0.12])\n", "\n", "ax[0].legend()\n", "\n", "#ax[0].hist(total_points, bins = 20, density = True)\n", "\n", "\n", "ax[1].text(0.1, 0.8, \"\\n\".join(squad), fontsize=10, transform=ax[1].transAxes, verticalalignment = 'top')\n", "\n", "text = \"\\n\".join(['Avg Total Points = ' + \"{:.2f}\".format(total_points.mean()), \n", " 'Avg Mod Points = ' + \"{:.2f}\".format(mod_points.mean()), \n", " 'Avg Clean Sheets = ' + \"{:.2f}\".format(clean_sheets.mean())])\n", "\n", "ax[1].text(0.5, 0.8, text, fontsize=10, transform=ax[1].transAxes, verticalalignment = 'top')\n", "\n", "ax[1].axis('off')\n", "\n", "\n", "\n", "plt.subplots_adjust(right=1.5)\n", "\n", "plt.show()" ] }, { "cell_type": "markdown", "id": "30744d7a", "metadata": {}, "source": [ "Tensorflow seems to have a custom definition for SinhArcsinh distribution. \n", "\n", "Here the code to generate the probability density function is reproduced." ] }, { "cell_type": "code", "execution_count": 110, "id": "3ec6c3dc", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[]" ] }, "execution_count": 110, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# custom franction to calculate the probability density function\n", "\n", "def sinh_archsinh_pdf(x, mu, sigma, eps, delta):\n", "\n", " mul = np.sinh( np.arcsinh(2) * delta)\n", " \n", " mul = 2 / mul\n", " \n", " sigma_corr = sigma * mul\n", " \n", " z = (x - mu) / sigma_corr\n", " \n", " \n", " \n", " S = np.sinh( -eps + (1/delta) * np.arcsinh(z))\n", " \n", " f = np.exp(-0.5 * S * S)\n", "\n", " f /= np.sqrt(2 * np.pi)\n", " \n", " f *= 1 / ( sigma_corr * delta )\n", " \n", " f *= np.sqrt(1 + S * S)\n", " \n", " f /= np.sqrt(1 + z * z)\n", " \n", " return f\n", " \n", "\n", "x = np.arange(start = 0, stop = 15, step = 0.001)\n", "\n", "\n", "plt.plot(x, sinh_archsinh_pdf(x, 5.54, 1.4, 0.8, 1.68))\n", "\n", "\n" ] }, { "cell_type": "code", "execution_count": null, "id": "605dc968", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.9.13" } }, "nbformat": 4, "nbformat_minor": 5 }