{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "f8c7d2fe",
"metadata": {
"_cell_guid": "b1076dfc-b9ad-4769-8c92-a6c4dae69d19",
"_uuid": "8f2839f25d086af736a60e9eeb907d3b93b6e0e5",
"execution": {
"iopub.execute_input": "2023-08-10T14:34:06.936668Z",
"iopub.status.busy": "2023-08-10T14:34:06.936191Z",
"iopub.status.idle": "2023-08-10T14:34:06.953212Z",
"shell.execute_reply": "2023-08-10T14:34:06.951527Z"
},
"papermill": {
"duration": 0.024378,
"end_time": "2023-08-10T14:34:06.956031",
"exception": false,
"start_time": "2023-08-10T14:34:06.931653",
"status": "completed"
},
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"/kaggle/input/icr-identify-age-related-conditions/sample_submission.csv\n",
"/kaggle/input/icr-identify-age-related-conditions/greeks.csv\n",
"/kaggle/input/icr-identify-age-related-conditions/train.csv\n",
"/kaggle/input/icr-identify-age-related-conditions/test.csv\n"
]
}
],
"source": [
"# This Python 3 environment comes with many helpful analytics libraries installed\n",
"# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n",
"# For example, here's several helpful packages to load\n",
"\n",
"import numpy as np # linear algebra\n",
"import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n",
"\n",
"# Input data files are available in the read-only \"../input/\" directory\n",
"# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n",
"\n",
"import os\n",
"for dirname, _, filenames in os.walk('/kaggle/input'):\n",
" for filename in filenames:\n",
" print(os.path.join(dirname, filename))\n",
"\n",
"# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n",
"# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "6074b35d",
"metadata": {
"execution": {
"iopub.execute_input": "2023-08-10T14:34:06.963637Z",
"iopub.status.busy": "2023-08-10T14:34:06.963182Z",
"iopub.status.idle": "2023-08-10T14:35:05.978942Z",
"shell.execute_reply": "2023-08-10T14:35:05.977938Z"
},
"papermill": {
"duration": 59.022726,
"end_time": "2023-08-10T14:35:05.981501",
"exception": false,
"start_time": "2023-08-10T14:34:06.958775",
"status": "completed"
},
"tags": []
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/opt/conda/lib/python3.10/site-packages/scipy/__init__.py:146: UserWarning: A NumPy version >=1.16.5 and <1.23.0 is required for this version of SciPy (detected version 1.23.5\n",
" warnings.warn(f\"A NumPy version >={np_minversion} and <{np_maxversion}\"\n",
"/opt/conda/lib/python3.10/site-packages/tensorflow_io/python/ops/__init__.py:98: UserWarning: unable to load libtensorflow_io_plugins.so: unable to open file: libtensorflow_io_plugins.so, from paths: ['/opt/conda/lib/python3.10/site-packages/tensorflow_io/python/ops/libtensorflow_io_plugins.so']\n",
"caused by: ['/opt/conda/lib/python3.10/site-packages/tensorflow_io/python/ops/libtensorflow_io_plugins.so: undefined symbol: _ZN3tsl6StatusC1EN10tensorflow5error4CodeESt17basic_string_viewIcSt11char_traitsIcEENS_14SourceLocationE']\n",
" warnings.warn(f\"unable to load libtensorflow_io_plugins.so: {e}\")\n",
"/opt/conda/lib/python3.10/site-packages/tensorflow_io/python/ops/__init__.py:104: UserWarning: file system plugins are not loaded: unable to open file: libtensorflow_io.so, from paths: ['/opt/conda/lib/python3.10/site-packages/tensorflow_io/python/ops/libtensorflow_io.so']\n",
"caused by: ['/opt/conda/lib/python3.10/site-packages/tensorflow_io/python/ops/libtensorflow_io.so: undefined symbol: _ZTVN10tensorflow13GcsFileSystemE']\n",
" warnings.warn(f\"file system plugins are not loaded: {e}\")\n",
"/tmp/ipykernel_21/30731265.py:16: FutureWarning: The default value of numeric_only in DataFrame.mean is deprecated. In a future version, it will default to False. In addition, specifying 'numeric_only=None' is deprecated. Select only valid columns or specify the value of numeric_only to silence this warning.\n",
" df.fillna(df.mean(), inplace=True)\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Model: \"sequential\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense (Dense) (None, 128) 7168 \n",
" \n",
" dense_1 (Dense) (None, 64) 8256 \n",
" \n",
" dense_2 (Dense) (None, 32) 2080 \n",
" \n",
" dense_3 (Dense) (None, 2) 66 \n",
" \n",
"=================================================================\n",
"Total params: 17,570\n",
"Trainable params: 17,570\n",
"Non-trainable params: 0\n",
"_________________________________________________________________\n",
"Epoch 1/100\n",
"5/5 [==============================] - 2s 80ms/step - loss: 0.2676 - accuracy: 0.7769 - val_loss: 0.2224 - val_accuracy: 0.8468\n",
"Epoch 2/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 0.1844 - accuracy: 0.8195 - val_loss: 0.1453 - val_accuracy: 0.8548\n",
"Epoch 3/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 0.1124 - accuracy: 0.8195 - val_loss: 0.0815 - val_accuracy: 0.8548\n",
"Epoch 4/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 0.0609 - accuracy: 0.8174 - val_loss: 0.0402 - val_accuracy: 0.8548\n",
"Epoch 5/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 0.0313 - accuracy: 0.8174 - val_loss: 0.0201 - val_accuracy: 0.8548\n",
"Epoch 6/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 0.0163 - accuracy: 0.8174 - val_loss: 0.0103 - val_accuracy: 0.8548\n",
"Epoch 7/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 0.0087 - accuracy: 0.8174 - val_loss: 0.0055 - val_accuracy: 0.8548\n",
"Epoch 8/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 0.0049 - accuracy: 0.8174 - val_loss: 0.0032 - val_accuracy: 0.8548\n",
"Epoch 9/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 0.0029 - accuracy: 0.8174 - val_loss: 0.0020 - val_accuracy: 0.8548\n",
"Epoch 10/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 0.0020 - accuracy: 0.8174 - val_loss: 0.0014 - val_accuracy: 0.8548\n",
"Epoch 11/100\n",
"5/5 [==============================] - 0s 10ms/step - loss: 0.0014 - accuracy: 0.8195 - val_loss: 0.0011 - val_accuracy: 0.8548\n",
"Epoch 12/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 0.0011 - accuracy: 0.8215 - val_loss: 8.3739e-04 - val_accuracy: 0.8548\n",
"Epoch 13/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 8.5167e-04 - accuracy: 0.8235 - val_loss: 6.9548e-04 - val_accuracy: 0.8548\n",
"Epoch 14/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 7.0541e-04 - accuracy: 0.8256 - val_loss: 5.9700e-04 - val_accuracy: 0.8548\n",
"Epoch 15/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 6.1248e-04 - accuracy: 0.8276 - val_loss: 5.2366e-04 - val_accuracy: 0.8548\n",
"Epoch 16/100\n",
"5/5 [==============================] - 0s 16ms/step - loss: 5.3804e-04 - accuracy: 0.8296 - val_loss: 4.6759e-04 - val_accuracy: 0.8468\n",
"Epoch 17/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 4.8452e-04 - accuracy: 0.8316 - val_loss: 4.2200e-04 - val_accuracy: 0.8468\n",
"Epoch 18/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 4.3384e-04 - accuracy: 0.8296 - val_loss: 3.8514e-04 - val_accuracy: 0.8468\n",
"Epoch 19/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 3.9703e-04 - accuracy: 0.8296 - val_loss: 3.5355e-04 - val_accuracy: 0.8468\n",
"Epoch 20/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 3.6569e-04 - accuracy: 0.8296 - val_loss: 3.2588e-04 - val_accuracy: 0.8468\n",
"Epoch 21/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 3.3747e-04 - accuracy: 0.8296 - val_loss: 3.0180e-04 - val_accuracy: 0.8468\n",
"Epoch 22/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 3.1269e-04 - accuracy: 0.8296 - val_loss: 2.8040e-04 - val_accuracy: 0.8468\n",
"Epoch 23/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.9041e-04 - accuracy: 0.8296 - val_loss: 2.6136e-04 - val_accuracy: 0.8468\n",
"Epoch 24/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.7136e-04 - accuracy: 0.8296 - val_loss: 2.4416e-04 - val_accuracy: 0.8468\n",
"Epoch 25/100\n",
"5/5 [==============================] - 0s 16ms/step - loss: 2.5325e-04 - accuracy: 0.8296 - val_loss: 2.2875e-04 - val_accuracy: 0.8468\n",
"Epoch 26/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 2.3718e-04 - accuracy: 0.8296 - val_loss: 2.1488e-04 - val_accuracy: 0.8468\n",
"Epoch 27/100\n",
"5/5 [==============================] - 0s 16ms/step - loss: 2.2411e-04 - accuracy: 0.8296 - val_loss: 2.0185e-04 - val_accuracy: 0.8468\n",
"Epoch 28/100\n",
"5/5 [==============================] - 0s 19ms/step - loss: 2.1075e-04 - accuracy: 0.8296 - val_loss: 1.8991e-04 - val_accuracy: 0.8468\n",
"Epoch 29/100\n",
"5/5 [==============================] - 0s 18ms/step - loss: 1.9802e-04 - accuracy: 0.8296 - val_loss: 1.7930e-04 - val_accuracy: 0.8468\n",
"Epoch 30/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 1.8732e-04 - accuracy: 0.8296 - val_loss: 1.6950e-04 - val_accuracy: 0.8468\n",
"Epoch 31/100\n",
"5/5 [==============================] - 0s 16ms/step - loss: 1.7733e-04 - accuracy: 0.8296 - val_loss: 1.6044e-04 - val_accuracy: 0.8468\n",
"Epoch 32/100\n",
"5/5 [==============================] - 0s 14ms/step - loss: 1.6830e-04 - accuracy: 0.8296 - val_loss: 1.5197e-04 - val_accuracy: 0.8468\n",
"Epoch 33/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.5942e-04 - accuracy: 0.8296 - val_loss: 1.4435e-04 - val_accuracy: 0.8468\n",
"Epoch 34/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.5124e-04 - accuracy: 0.8296 - val_loss: 1.3734e-04 - val_accuracy: 0.8468\n",
"Epoch 35/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.4381e-04 - accuracy: 0.8296 - val_loss: 1.3089e-04 - val_accuracy: 0.8468\n",
"Epoch 36/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 1.3768e-04 - accuracy: 0.8296 - val_loss: 1.2463e-04 - val_accuracy: 0.8468\n",
"Epoch 37/100\n",
"5/5 [==============================] - 0s 14ms/step - loss: 1.3091e-04 - accuracy: 0.8296 - val_loss: 1.1888e-04 - val_accuracy: 0.8468\n",
"Epoch 38/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.2538e-04 - accuracy: 0.8296 - val_loss: 1.1345e-04 - val_accuracy: 0.8468\n",
"Epoch 39/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 1.1968e-04 - accuracy: 0.8296 - val_loss: 1.0845e-04 - val_accuracy: 0.8468\n",
"Epoch 40/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.1449e-04 - accuracy: 0.8296 - val_loss: 1.0376e-04 - val_accuracy: 0.8468\n",
"Epoch 41/100\n",
"5/5 [==============================] - 0s 14ms/step - loss: 1.0942e-04 - accuracy: 0.8296 - val_loss: 9.9425e-05 - val_accuracy: 0.8468\n",
"Epoch 42/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.0512e-04 - accuracy: 0.8276 - val_loss: 9.5334e-05 - val_accuracy: 0.8468\n",
"Epoch 43/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 1.0078e-04 - accuracy: 0.8276 - val_loss: 9.1480e-05 - val_accuracy: 0.8468\n",
"Epoch 44/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 9.6694e-05 - accuracy: 0.8276 - val_loss: 8.7891e-05 - val_accuracy: 0.8468\n",
"Epoch 45/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 9.3148e-05 - accuracy: 0.8276 - val_loss: 8.4419e-05 - val_accuracy: 0.8468\n",
"Epoch 46/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 8.9508e-05 - accuracy: 0.8296 - val_loss: 8.1205e-05 - val_accuracy: 0.8468\n",
"Epoch 47/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 8.6037e-05 - accuracy: 0.8296 - val_loss: 7.8212e-05 - val_accuracy: 0.8548\n",
"Epoch 48/100\n",
"5/5 [==============================] - 0s 16ms/step - loss: 8.2928e-05 - accuracy: 0.8256 - val_loss: 7.5347e-05 - val_accuracy: 0.8548\n",
"Epoch 49/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 7.9936e-05 - accuracy: 0.8276 - val_loss: 7.2651e-05 - val_accuracy: 0.8548\n",
"Epoch 50/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 7.7057e-05 - accuracy: 0.8276 - val_loss: 7.0099e-05 - val_accuracy: 0.8548\n",
"Epoch 51/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 7.4514e-05 - accuracy: 0.8256 - val_loss: 6.7626e-05 - val_accuracy: 0.8548\n",
"Epoch 52/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 7.1958e-05 - accuracy: 0.8256 - val_loss: 6.5286e-05 - val_accuracy: 0.8548\n",
"Epoch 53/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 6.9452e-05 - accuracy: 0.8256 - val_loss: 6.3110e-05 - val_accuracy: 0.8548\n",
"Epoch 54/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 6.7217e-05 - accuracy: 0.8256 - val_loss: 6.0996e-05 - val_accuracy: 0.8548\n",
"Epoch 55/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 6.5019e-05 - accuracy: 0.8256 - val_loss: 5.9015e-05 - val_accuracy: 0.8548\n",
"Epoch 56/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 6.2917e-05 - accuracy: 0.8256 - val_loss: 5.7140e-05 - val_accuracy: 0.8548\n",
"Epoch 57/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 6.0888e-05 - accuracy: 0.8276 - val_loss: 5.5359e-05 - val_accuracy: 0.8548\n",
"Epoch 58/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 5.8994e-05 - accuracy: 0.8256 - val_loss: 5.3672e-05 - val_accuracy: 0.8548\n",
"Epoch 59/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 5.7184e-05 - accuracy: 0.8256 - val_loss: 5.2054e-05 - val_accuracy: 0.8548\n",
"Epoch 60/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 5.5525e-05 - accuracy: 0.8235 - val_loss: 5.0478e-05 - val_accuracy: 0.8548\n",
"Epoch 61/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 5.3909e-05 - accuracy: 0.8256 - val_loss: 4.8973e-05 - val_accuracy: 0.8548\n",
"Epoch 62/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 5.2348e-05 - accuracy: 0.8235 - val_loss: 4.7518e-05 - val_accuracy: 0.8548\n",
"Epoch 63/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 5.0841e-05 - accuracy: 0.8256 - val_loss: 4.6131e-05 - val_accuracy: 0.8548\n",
"Epoch 64/100\n",
"5/5 [==============================] - 0s 16ms/step - loss: 4.9345e-05 - accuracy: 0.8256 - val_loss: 4.4827e-05 - val_accuracy: 0.8548\n",
"Epoch 65/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 4.8035e-05 - accuracy: 0.8256 - val_loss: 4.3553e-05 - val_accuracy: 0.8548\n",
"Epoch 66/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 4.6618e-05 - accuracy: 0.8256 - val_loss: 4.2365e-05 - val_accuracy: 0.8548\n",
"Epoch 67/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 4.5410e-05 - accuracy: 0.8256 - val_loss: 4.1206e-05 - val_accuracy: 0.8548\n",
"Epoch 68/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 4.4182e-05 - accuracy: 0.8256 - val_loss: 4.0086e-05 - val_accuracy: 0.8548\n",
"Epoch 69/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 4.2981e-05 - accuracy: 0.8256 - val_loss: 3.9030e-05 - val_accuracy: 0.8548\n",
"Epoch 70/100\n",
"5/5 [==============================] - 0s 16ms/step - loss: 4.1842e-05 - accuracy: 0.8235 - val_loss: 3.8014e-05 - val_accuracy: 0.8548\n",
"Epoch 71/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 4.0810e-05 - accuracy: 0.8256 - val_loss: 3.7024e-05 - val_accuracy: 0.8548\n",
"Epoch 72/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 3.9720e-05 - accuracy: 0.8235 - val_loss: 3.6091e-05 - val_accuracy: 0.8548\n",
"Epoch 73/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.8764e-05 - accuracy: 0.8256 - val_loss: 3.5177e-05 - val_accuracy: 0.8548\n",
"Epoch 74/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.7769e-05 - accuracy: 0.8256 - val_loss: 3.4311e-05 - val_accuracy: 0.8548\n",
"Epoch 75/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.6870e-05 - accuracy: 0.8256 - val_loss: 3.3465e-05 - val_accuracy: 0.8548\n",
"Epoch 76/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 3.5959e-05 - accuracy: 0.8256 - val_loss: 3.2657e-05 - val_accuracy: 0.8548\n",
"Epoch 77/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.5112e-05 - accuracy: 0.8235 - val_loss: 3.1866e-05 - val_accuracy: 0.8548\n",
"Epoch 78/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 3.4309e-05 - accuracy: 0.8235 - val_loss: 3.1104e-05 - val_accuracy: 0.8548\n",
"Epoch 79/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 3.3438e-05 - accuracy: 0.8256 - val_loss: 3.0390e-05 - val_accuracy: 0.8548\n",
"Epoch 80/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.2712e-05 - accuracy: 0.8235 - val_loss: 2.9686e-05 - val_accuracy: 0.8548\n",
"Epoch 81/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 3.1946e-05 - accuracy: 0.8235 - val_loss: 2.9012e-05 - val_accuracy: 0.8548\n",
"Epoch 82/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 3.1235e-05 - accuracy: 0.8256 - val_loss: 2.8350e-05 - val_accuracy: 0.8548\n",
"Epoch 83/100\n",
"5/5 [==============================] - 0s 14ms/step - loss: 3.0568e-05 - accuracy: 0.8256 - val_loss: 2.7704e-05 - val_accuracy: 0.8548\n",
"Epoch 84/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.9852e-05 - accuracy: 0.8235 - val_loss: 2.7099e-05 - val_accuracy: 0.8548\n",
"Epoch 85/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.9180e-05 - accuracy: 0.8235 - val_loss: 2.6517e-05 - val_accuracy: 0.8548\n",
"Epoch 86/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.8590e-05 - accuracy: 0.8215 - val_loss: 2.5932e-05 - val_accuracy: 0.8548\n",
"Epoch 87/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.7979e-05 - accuracy: 0.8235 - val_loss: 2.5374e-05 - val_accuracy: 0.8548\n",
"Epoch 88/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.7406e-05 - accuracy: 0.8215 - val_loss: 2.4825e-05 - val_accuracy: 0.8548\n",
"Epoch 89/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.6840e-05 - accuracy: 0.8215 - val_loss: 2.4293e-05 - val_accuracy: 0.8548\n",
"Epoch 90/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.6237e-05 - accuracy: 0.8215 - val_loss: 2.3797e-05 - val_accuracy: 0.8548\n",
"Epoch 91/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.5686e-05 - accuracy: 0.8215 - val_loss: 2.3322e-05 - val_accuracy: 0.8548\n",
"Epoch 92/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.5195e-05 - accuracy: 0.8235 - val_loss: 2.2850e-05 - val_accuracy: 0.8548\n",
"Epoch 93/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 2.4680e-05 - accuracy: 0.8215 - val_loss: 2.2396e-05 - val_accuracy: 0.8548\n",
"Epoch 94/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.4216e-05 - accuracy: 0.8215 - val_loss: 2.1946e-05 - val_accuracy: 0.8548\n",
"Epoch 95/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.3719e-05 - accuracy: 0.8235 - val_loss: 2.1517e-05 - val_accuracy: 0.8548\n",
"Epoch 96/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.3294e-05 - accuracy: 0.8215 - val_loss: 2.1086e-05 - val_accuracy: 0.8548\n",
"Epoch 97/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 2.2819e-05 - accuracy: 0.8215 - val_loss: 2.0677e-05 - val_accuracy: 0.8548\n",
"Epoch 98/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.2380e-05 - accuracy: 0.8215 - val_loss: 2.0282e-05 - val_accuracy: 0.8548\n",
"Epoch 99/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.1950e-05 - accuracy: 0.8215 - val_loss: 1.9899e-05 - val_accuracy: 0.8548\n",
"Epoch 100/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.1559e-05 - accuracy: 0.8215 - val_loss: 1.9524e-05 - val_accuracy: 0.8548\n",
"Epoch 1/100\n",
"5/5 [==============================] - 1s 61ms/step - loss: 0.3409 - accuracy: 0.7525 - val_loss: 0.2493 - val_accuracy: 0.8145\n",
"Epoch 2/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 0.2079 - accuracy: 0.8337 - val_loss: 0.1612 - val_accuracy: 0.8226\n",
"Epoch 3/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 0.1281 - accuracy: 0.8499 - val_loss: 0.0979 - val_accuracy: 0.8387\n",
"Epoch 4/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 0.0748 - accuracy: 0.8458 - val_loss: 0.0557 - val_accuracy: 0.8468\n",
"Epoch 5/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 0.0413 - accuracy: 0.8458 - val_loss: 0.0309 - val_accuracy: 0.8468\n",
"Epoch 6/100\n",
"5/5 [==============================] - 0s 18ms/step - loss: 0.0220 - accuracy: 0.8458 - val_loss: 0.0174 - val_accuracy: 0.8468\n",
"Epoch 7/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 0.0120 - accuracy: 0.8438 - val_loss: 0.0102 - val_accuracy: 0.8548\n",
"Epoch 8/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 0.0069 - accuracy: 0.8418 - val_loss: 0.0062 - val_accuracy: 0.8548\n",
"Epoch 9/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 0.0043 - accuracy: 0.8418 - val_loss: 0.0041 - val_accuracy: 0.8629\n",
"Epoch 10/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 0.0028 - accuracy: 0.8458 - val_loss: 0.0029 - val_accuracy: 0.8629\n",
"Epoch 11/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 0.0020 - accuracy: 0.8519 - val_loss: 0.0021 - val_accuracy: 0.8629\n",
"Epoch 12/100\n",
"5/5 [==============================] - 0s 16ms/step - loss: 0.0015 - accuracy: 0.8540 - val_loss: 0.0017 - val_accuracy: 0.8629\n",
"Epoch 13/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 0.0012 - accuracy: 0.8540 - val_loss: 0.0014 - val_accuracy: 0.8710\n",
"Epoch 14/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 0.0010 - accuracy: 0.8540 - val_loss: 0.0012 - val_accuracy: 0.8629\n",
"Epoch 15/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 8.5718e-04 - accuracy: 0.8600 - val_loss: 0.0010 - val_accuracy: 0.8548\n",
"Epoch 16/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 7.4404e-04 - accuracy: 0.8621 - val_loss: 9.1241e-04 - val_accuracy: 0.8548\n",
"Epoch 17/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 6.5829e-04 - accuracy: 0.8621 - val_loss: 8.1874e-04 - val_accuracy: 0.8548\n",
"Epoch 18/100\n",
"5/5 [==============================] - 0s 16ms/step - loss: 5.8958e-04 - accuracy: 0.8621 - val_loss: 7.4245e-04 - val_accuracy: 0.8548\n",
"Epoch 19/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 5.3382e-04 - accuracy: 0.8621 - val_loss: 6.7772e-04 - val_accuracy: 0.8468\n",
"Epoch 20/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 4.8442e-04 - accuracy: 0.8621 - val_loss: 6.2316e-04 - val_accuracy: 0.8548\n",
"Epoch 21/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 4.4404e-04 - accuracy: 0.8600 - val_loss: 5.7565e-04 - val_accuracy: 0.8468\n",
"Epoch 22/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 4.0959e-04 - accuracy: 0.8600 - val_loss: 5.3291e-04 - val_accuracy: 0.8548\n",
"Epoch 23/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.7761e-04 - accuracy: 0.8600 - val_loss: 4.9527e-04 - val_accuracy: 0.8629\n",
"Epoch 24/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.5010e-04 - accuracy: 0.8600 - val_loss: 4.6157e-04 - val_accuracy: 0.8629\n",
"Epoch 25/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.2451e-04 - accuracy: 0.8600 - val_loss: 4.3145e-04 - val_accuracy: 0.8629\n",
"Epoch 26/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 3.0286e-04 - accuracy: 0.8580 - val_loss: 4.0372e-04 - val_accuracy: 0.8629\n",
"Epoch 27/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.8140e-04 - accuracy: 0.8600 - val_loss: 3.7937e-04 - val_accuracy: 0.8548\n",
"Epoch 28/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.6412e-04 - accuracy: 0.8580 - val_loss: 3.5651e-04 - val_accuracy: 0.8548\n",
"Epoch 29/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.4687e-04 - accuracy: 0.8560 - val_loss: 3.3607e-04 - val_accuracy: 0.8548\n",
"Epoch 30/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.3273e-04 - accuracy: 0.8560 - val_loss: 3.1655e-04 - val_accuracy: 0.8548\n",
"Epoch 31/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.1749e-04 - accuracy: 0.8560 - val_loss: 2.9963e-04 - val_accuracy: 0.8548\n",
"Epoch 32/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.0562e-04 - accuracy: 0.8540 - val_loss: 2.8354e-04 - val_accuracy: 0.8548\n",
"Epoch 33/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.9391e-04 - accuracy: 0.8519 - val_loss: 2.6859e-04 - val_accuracy: 0.8548\n",
"Epoch 34/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.8327e-04 - accuracy: 0.8519 - val_loss: 2.5471e-04 - val_accuracy: 0.8548\n",
"Epoch 35/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 1.7310e-04 - accuracy: 0.8519 - val_loss: 2.4208e-04 - val_accuracy: 0.8548\n",
"Epoch 36/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.6422e-04 - accuracy: 0.8519 - val_loss: 2.3024e-04 - val_accuracy: 0.8548\n",
"Epoch 37/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.5557e-04 - accuracy: 0.8519 - val_loss: 2.1938e-04 - val_accuracy: 0.8548\n",
"Epoch 38/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.4769e-04 - accuracy: 0.8519 - val_loss: 2.0934e-04 - val_accuracy: 0.8548\n",
"Epoch 39/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.4054e-04 - accuracy: 0.8519 - val_loss: 1.9988e-04 - val_accuracy: 0.8548\n",
"Epoch 40/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.3386e-04 - accuracy: 0.8519 - val_loss: 1.9104e-04 - val_accuracy: 0.8629\n",
"Epoch 41/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.2729e-04 - accuracy: 0.8519 - val_loss: 1.8287e-04 - val_accuracy: 0.8629\n",
"Epoch 42/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.2148e-04 - accuracy: 0.8540 - val_loss: 1.7525e-04 - val_accuracy: 0.8629\n",
"Epoch 43/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.1622e-04 - accuracy: 0.8540 - val_loss: 1.6789e-04 - val_accuracy: 0.8629\n",
"Epoch 44/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.1100e-04 - accuracy: 0.8519 - val_loss: 1.6107e-04 - val_accuracy: 0.8548\n",
"Epoch 45/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.0612e-04 - accuracy: 0.8540 - val_loss: 1.5468e-04 - val_accuracy: 0.8548\n",
"Epoch 46/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.0185e-04 - accuracy: 0.8519 - val_loss: 1.4850e-04 - val_accuracy: 0.8548\n",
"Epoch 47/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 9.7362e-05 - accuracy: 0.8519 - val_loss: 1.4286e-04 - val_accuracy: 0.8548\n",
"Epoch 48/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 9.3378e-05 - accuracy: 0.8540 - val_loss: 1.3756e-04 - val_accuracy: 0.8548\n",
"Epoch 49/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 8.9638e-05 - accuracy: 0.8540 - val_loss: 1.3252e-04 - val_accuracy: 0.8548\n",
"Epoch 50/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 8.6222e-05 - accuracy: 0.8540 - val_loss: 1.2769e-04 - val_accuracy: 0.8548\n",
"Epoch 51/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 8.2733e-05 - accuracy: 0.8540 - val_loss: 1.2320e-04 - val_accuracy: 0.8548\n",
"Epoch 52/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 7.9811e-05 - accuracy: 0.8540 - val_loss: 1.1880e-04 - val_accuracy: 0.8548\n",
"Epoch 53/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 7.6607e-05 - accuracy: 0.8560 - val_loss: 1.1479e-04 - val_accuracy: 0.8548\n",
"Epoch 54/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 7.3920e-05 - accuracy: 0.8560 - val_loss: 1.1089e-04 - val_accuracy: 0.8548\n",
"Epoch 55/100\n",
"5/5 [==============================] - 0s 16ms/step - loss: 7.1202e-05 - accuracy: 0.8560 - val_loss: 1.0725e-04 - val_accuracy: 0.8548\n",
"Epoch 56/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 6.8755e-05 - accuracy: 0.8560 - val_loss: 1.0370e-04 - val_accuracy: 0.8548\n",
"Epoch 57/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 6.6357e-05 - accuracy: 0.8540 - val_loss: 1.0033e-04 - val_accuracy: 0.8548\n",
"Epoch 58/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 6.4047e-05 - accuracy: 0.8560 - val_loss: 9.7142e-05 - val_accuracy: 0.8548\n",
"Epoch 59/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 6.1862e-05 - accuracy: 0.8560 - val_loss: 9.4127e-05 - val_accuracy: 0.8548\n",
"Epoch 60/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 5.9745e-05 - accuracy: 0.8560 - val_loss: 9.1293e-05 - val_accuracy: 0.8548\n",
"Epoch 61/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 5.7851e-05 - accuracy: 0.8560 - val_loss: 8.8544e-05 - val_accuracy: 0.8548\n",
"Epoch 62/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 5.5946e-05 - accuracy: 0.8540 - val_loss: 8.5920e-05 - val_accuracy: 0.8548\n",
"Epoch 63/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 5.4225e-05 - accuracy: 0.8540 - val_loss: 8.3376e-05 - val_accuracy: 0.8548\n",
"Epoch 64/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 5.2543e-05 - accuracy: 0.8540 - val_loss: 8.0963e-05 - val_accuracy: 0.8548\n",
"Epoch 65/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 5.0843e-05 - accuracy: 0.8540 - val_loss: 7.8691e-05 - val_accuracy: 0.8548\n",
"Epoch 66/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 4.9302e-05 - accuracy: 0.8540 - val_loss: 7.6512e-05 - val_accuracy: 0.8548\n",
"Epoch 67/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 4.7833e-05 - accuracy: 0.8540 - val_loss: 7.4413e-05 - val_accuracy: 0.8548\n",
"Epoch 68/100\n",
"5/5 [==============================] - 0s 16ms/step - loss: 4.6383e-05 - accuracy: 0.8540 - val_loss: 7.2419e-05 - val_accuracy: 0.8548\n",
"Epoch 69/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 4.5072e-05 - accuracy: 0.8540 - val_loss: 7.0461e-05 - val_accuracy: 0.8548\n",
"Epoch 70/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 4.3741e-05 - accuracy: 0.8540 - val_loss: 6.8622e-05 - val_accuracy: 0.8548\n",
"Epoch 71/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 4.2533e-05 - accuracy: 0.8519 - val_loss: 6.6823e-05 - val_accuracy: 0.8548\n",
"Epoch 72/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 4.1337e-05 - accuracy: 0.8540 - val_loss: 6.5099e-05 - val_accuracy: 0.8548\n",
"Epoch 73/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 4.0167e-05 - accuracy: 0.8540 - val_loss: 6.3453e-05 - val_accuracy: 0.8548\n",
"Epoch 74/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.9082e-05 - accuracy: 0.8519 - val_loss: 6.1844e-05 - val_accuracy: 0.8548\n",
"Epoch 75/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.8014e-05 - accuracy: 0.8540 - val_loss: 6.0312e-05 - val_accuracy: 0.8548\n",
"Epoch 76/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 3.7028e-05 - accuracy: 0.8479 - val_loss: 5.8820e-05 - val_accuracy: 0.8548\n",
"Epoch 77/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.6035e-05 - accuracy: 0.8479 - val_loss: 5.7391e-05 - val_accuracy: 0.8548\n",
"Epoch 78/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.5081e-05 - accuracy: 0.8499 - val_loss: 5.6032e-05 - val_accuracy: 0.8548\n",
"Epoch 79/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.4216e-05 - accuracy: 0.8479 - val_loss: 5.4690e-05 - val_accuracy: 0.8548\n",
"Epoch 80/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 3.3286e-05 - accuracy: 0.8458 - val_loss: 5.3446e-05 - val_accuracy: 0.8548\n",
"Epoch 81/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.2458e-05 - accuracy: 0.8458 - val_loss: 5.2227e-05 - val_accuracy: 0.8548\n",
"Epoch 82/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.1701e-05 - accuracy: 0.8458 - val_loss: 5.1020e-05 - val_accuracy: 0.8548\n",
"Epoch 83/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 3.0922e-05 - accuracy: 0.8458 - val_loss: 4.9858e-05 - val_accuracy: 0.8548\n",
"Epoch 84/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.0153e-05 - accuracy: 0.8458 - val_loss: 4.8739e-05 - val_accuracy: 0.8548\n",
"Epoch 85/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.9424e-05 - accuracy: 0.8458 - val_loss: 4.7675e-05 - val_accuracy: 0.8548\n",
"Epoch 86/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.8746e-05 - accuracy: 0.8458 - val_loss: 4.6618e-05 - val_accuracy: 0.8548\n",
"Epoch 87/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.8038e-05 - accuracy: 0.8458 - val_loss: 4.5637e-05 - val_accuracy: 0.8548\n",
"Epoch 88/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.7397e-05 - accuracy: 0.8458 - val_loss: 4.4668e-05 - val_accuracy: 0.8548\n",
"Epoch 89/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.6759e-05 - accuracy: 0.8458 - val_loss: 4.3746e-05 - val_accuracy: 0.8548\n",
"Epoch 90/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.6170e-05 - accuracy: 0.8438 - val_loss: 4.2832e-05 - val_accuracy: 0.8548\n",
"Epoch 91/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.5562e-05 - accuracy: 0.8458 - val_loss: 4.1955e-05 - val_accuracy: 0.8548\n",
"Epoch 92/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.5002e-05 - accuracy: 0.8479 - val_loss: 4.1099e-05 - val_accuracy: 0.8548\n",
"Epoch 93/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.4457e-05 - accuracy: 0.8458 - val_loss: 4.0275e-05 - val_accuracy: 0.8548\n",
"Epoch 94/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.3918e-05 - accuracy: 0.8458 - val_loss: 3.9473e-05 - val_accuracy: 0.8548\n",
"Epoch 95/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.3410e-05 - accuracy: 0.8479 - val_loss: 3.8682e-05 - val_accuracy: 0.8548\n",
"Epoch 96/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 2.2920e-05 - accuracy: 0.8438 - val_loss: 3.7918e-05 - val_accuracy: 0.8548\n",
"Epoch 97/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.2416e-05 - accuracy: 0.8438 - val_loss: 3.7188e-05 - val_accuracy: 0.8548\n",
"Epoch 98/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 2.1969e-05 - accuracy: 0.8438 - val_loss: 3.6461e-05 - val_accuracy: 0.8548\n",
"Epoch 99/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 2.1499e-05 - accuracy: 0.8458 - val_loss: 3.5772e-05 - val_accuracy: 0.8548\n",
"Epoch 100/100\n",
"5/5 [==============================] - 0s 16ms/step - loss: 2.1072e-05 - accuracy: 0.8418 - val_loss: 3.5088e-05 - val_accuracy: 0.8548\n",
"Epoch 1/100\n",
"5/5 [==============================] - 1s 63ms/step - loss: 0.2095 - accuracy: 0.6599 - val_loss: 0.1487 - val_accuracy: 0.8211\n",
"Epoch 2/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 0.1092 - accuracy: 0.8259 - val_loss: 0.0771 - val_accuracy: 0.8211\n",
"Epoch 3/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 0.0532 - accuracy: 0.8259 - val_loss: 0.0385 - val_accuracy: 0.8211\n",
"Epoch 4/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 0.0252 - accuracy: 0.8259 - val_loss: 0.0194 - val_accuracy: 0.8211\n",
"Epoch 5/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 0.0120 - accuracy: 0.8259 - val_loss: 0.0103 - val_accuracy: 0.8211\n",
"Epoch 6/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 0.0063 - accuracy: 0.8259 - val_loss: 0.0057 - val_accuracy: 0.8211\n",
"Epoch 7/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 0.0033 - accuracy: 0.8259 - val_loss: 0.0034 - val_accuracy: 0.8211\n",
"Epoch 8/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 0.0020 - accuracy: 0.8259 - val_loss: 0.0021 - val_accuracy: 0.8211\n",
"Epoch 9/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 0.0013 - accuracy: 0.8259 - val_loss: 0.0015 - val_accuracy: 0.8211\n",
"Epoch 10/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 8.9558e-04 - accuracy: 0.8259 - val_loss: 0.0011 - val_accuracy: 0.8211\n",
"Epoch 11/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 6.9294e-04 - accuracy: 0.8259 - val_loss: 8.8965e-04 - val_accuracy: 0.8211\n",
"Epoch 12/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 5.5404e-04 - accuracy: 0.8259 - val_loss: 7.3989e-04 - val_accuracy: 0.8211\n",
"Epoch 13/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 4.6532e-04 - accuracy: 0.8259 - val_loss: 6.3622e-04 - val_accuracy: 0.8211\n",
"Epoch 14/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 4.0157e-04 - accuracy: 0.8259 - val_loss: 5.6111e-04 - val_accuracy: 0.8211\n",
"Epoch 15/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.5443e-04 - accuracy: 0.8259 - val_loss: 5.0439e-04 - val_accuracy: 0.8211\n",
"Epoch 16/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.1859e-04 - accuracy: 0.8259 - val_loss: 4.5934e-04 - val_accuracy: 0.8211\n",
"Epoch 17/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.9202e-04 - accuracy: 0.8259 - val_loss: 4.2122e-04 - val_accuracy: 0.8211\n",
"Epoch 18/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.6810e-04 - accuracy: 0.8259 - val_loss: 3.8882e-04 - val_accuracy: 0.8211\n",
"Epoch 19/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.4669e-04 - accuracy: 0.8259 - val_loss: 3.6133e-04 - val_accuracy: 0.8211\n",
"Epoch 20/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.2887e-04 - accuracy: 0.8259 - val_loss: 3.3735e-04 - val_accuracy: 0.8211\n",
"Epoch 21/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.1341e-04 - accuracy: 0.8259 - val_loss: 3.1584e-04 - val_accuracy: 0.8211\n",
"Epoch 22/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.9982e-04 - accuracy: 0.8259 - val_loss: 2.9638e-04 - val_accuracy: 0.8211\n",
"Epoch 23/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.8701e-04 - accuracy: 0.8259 - val_loss: 2.7900e-04 - val_accuracy: 0.8211\n",
"Epoch 24/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.7605e-04 - accuracy: 0.8259 - val_loss: 2.6294e-04 - val_accuracy: 0.8211\n",
"Epoch 25/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.6524e-04 - accuracy: 0.8259 - val_loss: 2.4853e-04 - val_accuracy: 0.8211\n",
"Epoch 26/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.5618e-04 - accuracy: 0.8259 - val_loss: 2.3507e-04 - val_accuracy: 0.8211\n",
"Epoch 27/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.4705e-04 - accuracy: 0.8259 - val_loss: 2.2297e-04 - val_accuracy: 0.8211\n",
"Epoch 28/100\n",
"5/5 [==============================] - 0s 14ms/step - loss: 1.3918e-04 - accuracy: 0.8259 - val_loss: 2.1175e-04 - val_accuracy: 0.8211\n",
"Epoch 29/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.3219e-04 - accuracy: 0.8259 - val_loss: 2.0116e-04 - val_accuracy: 0.8211\n",
"Epoch 30/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.2519e-04 - accuracy: 0.8259 - val_loss: 1.9149e-04 - val_accuracy: 0.8211\n",
"Epoch 31/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.1915e-04 - accuracy: 0.8259 - val_loss: 1.8237e-04 - val_accuracy: 0.8211\n",
"Epoch 32/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 1.1331e-04 - accuracy: 0.8259 - val_loss: 1.7392e-04 - val_accuracy: 0.8211\n",
"Epoch 33/100\n",
"5/5 [==============================] - 0s 16ms/step - loss: 1.0770e-04 - accuracy: 0.8259 - val_loss: 1.6619e-04 - val_accuracy: 0.8211\n",
"Epoch 34/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.0268e-04 - accuracy: 0.8259 - val_loss: 1.5893e-04 - val_accuracy: 0.8211\n",
"Epoch 35/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 9.7918e-05 - accuracy: 0.8259 - val_loss: 1.5217e-04 - val_accuracy: 0.8211\n",
"Epoch 36/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 9.3645e-05 - accuracy: 0.8259 - val_loss: 1.4575e-04 - val_accuracy: 0.8211\n",
"Epoch 37/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 8.9519e-05 - accuracy: 0.8259 - val_loss: 1.3973e-04 - val_accuracy: 0.8211\n",
"Epoch 38/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 8.5535e-05 - accuracy: 0.8259 - val_loss: 1.3416e-04 - val_accuracy: 0.8211\n",
"Epoch 39/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 8.1934e-05 - accuracy: 0.8259 - val_loss: 1.2894e-04 - val_accuracy: 0.8211\n",
"Epoch 40/100\n",
"5/5 [==============================] - 0s 16ms/step - loss: 7.8621e-05 - accuracy: 0.8259 - val_loss: 1.2396e-04 - val_accuracy: 0.8211\n",
"Epoch 41/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 7.5420e-05 - accuracy: 0.8259 - val_loss: 1.1929e-04 - val_accuracy: 0.8211\n",
"Epoch 42/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 7.2397e-05 - accuracy: 0.8259 - val_loss: 1.1488e-04 - val_accuracy: 0.8211\n",
"Epoch 43/100\n",
"5/5 [==============================] - 0s 16ms/step - loss: 6.9578e-05 - accuracy: 0.8259 - val_loss: 1.1072e-04 - val_accuracy: 0.8211\n",
"Epoch 44/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 6.6825e-05 - accuracy: 0.8259 - val_loss: 1.0686e-04 - val_accuracy: 0.8211\n",
"Epoch 45/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 6.4439e-05 - accuracy: 0.8259 - val_loss: 1.0311e-04 - val_accuracy: 0.8211\n",
"Epoch 46/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 6.1956e-05 - accuracy: 0.8259 - val_loss: 9.9625e-05 - val_accuracy: 0.8211\n",
"Epoch 47/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 5.9786e-05 - accuracy: 0.8259 - val_loss: 9.6261e-05 - val_accuracy: 0.8211\n",
"Epoch 48/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 5.7661e-05 - accuracy: 0.8259 - val_loss: 9.3069e-05 - val_accuracy: 0.8211\n",
"Epoch 49/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 5.5706e-05 - accuracy: 0.8259 - val_loss: 8.9984e-05 - val_accuracy: 0.8211\n",
"Epoch 50/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 5.3666e-05 - accuracy: 0.8259 - val_loss: 8.7149e-05 - val_accuracy: 0.8211\n",
"Epoch 51/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 5.1880e-05 - accuracy: 0.8259 - val_loss: 8.4434e-05 - val_accuracy: 0.8211\n",
"Epoch 52/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 5.0168e-05 - accuracy: 0.8259 - val_loss: 8.1834e-05 - val_accuracy: 0.8211\n",
"Epoch 53/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 4.8561e-05 - accuracy: 0.8259 - val_loss: 7.9332e-05 - val_accuracy: 0.8211\n",
"Epoch 54/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 4.6972e-05 - accuracy: 0.8259 - val_loss: 7.6962e-05 - val_accuracy: 0.8211\n",
"Epoch 55/100\n",
"5/5 [==============================] - 0s 18ms/step - loss: 4.5431e-05 - accuracy: 0.8259 - val_loss: 7.4758e-05 - val_accuracy: 0.8211\n",
"Epoch 56/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 4.4067e-05 - accuracy: 0.8259 - val_loss: 7.2609e-05 - val_accuracy: 0.8211\n",
"Epoch 57/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 4.2743e-05 - accuracy: 0.8259 - val_loss: 7.0537e-05 - val_accuracy: 0.8211\n",
"Epoch 58/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 4.1419e-05 - accuracy: 0.8259 - val_loss: 6.8577e-05 - val_accuracy: 0.8211\n",
"Epoch 59/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 4.0133e-05 - accuracy: 0.8259 - val_loss: 6.6735e-05 - val_accuracy: 0.8211\n",
"Epoch 60/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 3.9060e-05 - accuracy: 0.8259 - val_loss: 6.4887e-05 - val_accuracy: 0.8211\n",
"Epoch 61/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.7893e-05 - accuracy: 0.8259 - val_loss: 6.3157e-05 - val_accuracy: 0.8211\n",
"Epoch 62/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 3.6842e-05 - accuracy: 0.8259 - val_loss: 6.1476e-05 - val_accuracy: 0.8211\n",
"Epoch 63/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 3.5772e-05 - accuracy: 0.8259 - val_loss: 5.9894e-05 - val_accuracy: 0.8211\n",
"Epoch 64/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 3.4776e-05 - accuracy: 0.8259 - val_loss: 5.8382e-05 - val_accuracy: 0.8211\n",
"Epoch 65/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.3825e-05 - accuracy: 0.8259 - val_loss: 5.6923e-05 - val_accuracy: 0.8211\n",
"Epoch 66/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.2933e-05 - accuracy: 0.8259 - val_loss: 5.5509e-05 - val_accuracy: 0.8211\n",
"Epoch 67/100\n",
"5/5 [==============================] - 0s 14ms/step - loss: 3.2114e-05 - accuracy: 0.8259 - val_loss: 5.4106e-05 - val_accuracy: 0.8211\n",
"Epoch 68/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.1223e-05 - accuracy: 0.8259 - val_loss: 5.2800e-05 - val_accuracy: 0.8211\n",
"Epoch 69/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 3.0413e-05 - accuracy: 0.8259 - val_loss: 5.1544e-05 - val_accuracy: 0.8211\n",
"Epoch 70/100\n",
"5/5 [==============================] - 0s 14ms/step - loss: 2.9649e-05 - accuracy: 0.8259 - val_loss: 5.0323e-05 - val_accuracy: 0.8211\n",
"Epoch 71/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.8866e-05 - accuracy: 0.8259 - val_loss: 4.9177e-05 - val_accuracy: 0.8211\n",
"Epoch 72/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.8188e-05 - accuracy: 0.8259 - val_loss: 4.8038e-05 - val_accuracy: 0.8211\n",
"Epoch 73/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.7464e-05 - accuracy: 0.8259 - val_loss: 4.6966e-05 - val_accuracy: 0.8211\n",
"Epoch 74/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.6783e-05 - accuracy: 0.8259 - val_loss: 4.5937e-05 - val_accuracy: 0.8211\n",
"Epoch 75/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.6179e-05 - accuracy: 0.8259 - val_loss: 4.4910e-05 - val_accuracy: 0.8211\n",
"Epoch 76/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.5548e-05 - accuracy: 0.8259 - val_loss: 4.3924e-05 - val_accuracy: 0.8211\n",
"Epoch 77/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.4958e-05 - accuracy: 0.8259 - val_loss: 4.2963e-05 - val_accuracy: 0.8211\n",
"Epoch 78/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 2.4372e-05 - accuracy: 0.8259 - val_loss: 4.2038e-05 - val_accuracy: 0.8211\n",
"Epoch 79/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.3795e-05 - accuracy: 0.8259 - val_loss: 4.1162e-05 - val_accuracy: 0.8211\n",
"Epoch 80/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.3240e-05 - accuracy: 0.8259 - val_loss: 4.0321e-05 - val_accuracy: 0.8211\n",
"Epoch 81/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.2767e-05 - accuracy: 0.8259 - val_loss: 3.9472e-05 - val_accuracy: 0.8211\n",
"Epoch 82/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.2234e-05 - accuracy: 0.8259 - val_loss: 3.8673e-05 - val_accuracy: 0.8211\n",
"Epoch 83/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.1746e-05 - accuracy: 0.8259 - val_loss: 3.7895e-05 - val_accuracy: 0.8211\n",
"Epoch 84/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.1300e-05 - accuracy: 0.8259 - val_loss: 3.7121e-05 - val_accuracy: 0.8211\n",
"Epoch 85/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.0811e-05 - accuracy: 0.8259 - val_loss: 3.6396e-05 - val_accuracy: 0.8211\n",
"Epoch 86/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 2.0373e-05 - accuracy: 0.8259 - val_loss: 3.5690e-05 - val_accuracy: 0.8211\n",
"Epoch 87/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.9964e-05 - accuracy: 0.8259 - val_loss: 3.4994e-05 - val_accuracy: 0.8211\n",
"Epoch 88/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 1.9537e-05 - accuracy: 0.8259 - val_loss: 3.4324e-05 - val_accuracy: 0.8211\n",
"Epoch 89/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 1.9140e-05 - accuracy: 0.8259 - val_loss: 3.3672e-05 - val_accuracy: 0.8211\n",
"Epoch 90/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 1.8735e-05 - accuracy: 0.8259 - val_loss: 3.3049e-05 - val_accuracy: 0.8211\n",
"Epoch 91/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.8349e-05 - accuracy: 0.8259 - val_loss: 3.2453e-05 - val_accuracy: 0.8211\n",
"Epoch 92/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 1.8007e-05 - accuracy: 0.8259 - val_loss: 3.1856e-05 - val_accuracy: 0.8211\n",
"Epoch 93/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 1.7644e-05 - accuracy: 0.8259 - val_loss: 3.1286e-05 - val_accuracy: 0.8211\n",
"Epoch 94/100\n",
"5/5 [==============================] - 0s 16ms/step - loss: 1.7302e-05 - accuracy: 0.8259 - val_loss: 3.0726e-05 - val_accuracy: 0.8211\n",
"Epoch 95/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.6973e-05 - accuracy: 0.8259 - val_loss: 3.0170e-05 - val_accuracy: 0.8211\n",
"Epoch 96/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.6654e-05 - accuracy: 0.8259 - val_loss: 2.9630e-05 - val_accuracy: 0.8211\n",
"Epoch 97/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.6328e-05 - accuracy: 0.8259 - val_loss: 2.9115e-05 - val_accuracy: 0.8211\n",
"Epoch 98/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 1.6025e-05 - accuracy: 0.8259 - val_loss: 2.8607e-05 - val_accuracy: 0.8211\n",
"Epoch 99/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.5713e-05 - accuracy: 0.8259 - val_loss: 2.8126e-05 - val_accuracy: 0.8211\n",
"Epoch 100/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.5431e-05 - accuracy: 0.8259 - val_loss: 2.7650e-05 - val_accuracy: 0.8211\n",
"Epoch 1/100\n",
"5/5 [==============================] - 1s 59ms/step - loss: 0.2156 - accuracy: 0.7692 - val_loss: 0.1409 - val_accuracy: 0.7967\n",
"Epoch 2/100\n",
"5/5 [==============================] - 0s 16ms/step - loss: 0.1095 - accuracy: 0.8320 - val_loss: 0.0705 - val_accuracy: 0.7967\n",
"Epoch 3/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 0.0530 - accuracy: 0.8320 - val_loss: 0.0355 - val_accuracy: 0.7967\n",
"Epoch 4/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 0.0262 - accuracy: 0.8320 - val_loss: 0.0181 - val_accuracy: 0.7967\n",
"Epoch 5/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 0.0129 - accuracy: 0.8320 - val_loss: 0.0093 - val_accuracy: 0.7967\n",
"Epoch 6/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 0.0066 - accuracy: 0.8320 - val_loss: 0.0049 - val_accuracy: 0.7967\n",
"Epoch 7/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 0.0035 - accuracy: 0.8320 - val_loss: 0.0028 - val_accuracy: 0.7967\n",
"Epoch 8/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 0.0021 - accuracy: 0.8320 - val_loss: 0.0017 - val_accuracy: 0.7967\n",
"Epoch 9/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 0.0013 - accuracy: 0.8320 - val_loss: 0.0012 - val_accuracy: 0.7967\n",
"Epoch 10/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 9.2941e-04 - accuracy: 0.8320 - val_loss: 8.5511e-04 - val_accuracy: 0.7967\n",
"Epoch 11/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 6.9148e-04 - accuracy: 0.8320 - val_loss: 6.7457e-04 - val_accuracy: 0.7967\n",
"Epoch 12/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 5.5398e-04 - accuracy: 0.8320 - val_loss: 5.5885e-04 - val_accuracy: 0.7967\n",
"Epoch 13/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 4.7278e-04 - accuracy: 0.8320 - val_loss: 4.7719e-04 - val_accuracy: 0.7967\n",
"Epoch 14/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 4.0425e-04 - accuracy: 0.8320 - val_loss: 4.1883e-04 - val_accuracy: 0.7967\n",
"Epoch 15/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.5834e-04 - accuracy: 0.8320 - val_loss: 3.7399e-04 - val_accuracy: 0.7967\n",
"Epoch 16/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.2108e-04 - accuracy: 0.8320 - val_loss: 3.3892e-04 - val_accuracy: 0.7967\n",
"Epoch 17/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.9077e-04 - accuracy: 0.8320 - val_loss: 3.1040e-04 - val_accuracy: 0.7967\n",
"Epoch 18/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.6718e-04 - accuracy: 0.8320 - val_loss: 2.8601e-04 - val_accuracy: 0.7967\n",
"Epoch 19/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.4618e-04 - accuracy: 0.8320 - val_loss: 2.6509e-04 - val_accuracy: 0.7967\n",
"Epoch 20/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 2.2716e-04 - accuracy: 0.8320 - val_loss: 2.4712e-04 - val_accuracy: 0.7967\n",
"Epoch 21/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.1259e-04 - accuracy: 0.8320 - val_loss: 2.3071e-04 - val_accuracy: 0.7967\n",
"Epoch 22/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.9759e-04 - accuracy: 0.8320 - val_loss: 2.1632e-04 - val_accuracy: 0.7967\n",
"Epoch 23/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.8454e-04 - accuracy: 0.8320 - val_loss: 2.0354e-04 - val_accuracy: 0.7967\n",
"Epoch 24/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.7373e-04 - accuracy: 0.8320 - val_loss: 1.9161e-04 - val_accuracy: 0.7967\n",
"Epoch 25/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.6343e-04 - accuracy: 0.8320 - val_loss: 1.8069e-04 - val_accuracy: 0.7967\n",
"Epoch 26/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.5408e-04 - accuracy: 0.8320 - val_loss: 1.7072e-04 - val_accuracy: 0.7967\n",
"Epoch 27/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.4485e-04 - accuracy: 0.8320 - val_loss: 1.6183e-04 - val_accuracy: 0.7967\n",
"Epoch 28/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.3724e-04 - accuracy: 0.8320 - val_loss: 1.5347e-04 - val_accuracy: 0.7967\n",
"Epoch 29/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 1.3016e-04 - accuracy: 0.8320 - val_loss: 1.4568e-04 - val_accuracy: 0.7967\n",
"Epoch 30/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.2306e-04 - accuracy: 0.8320 - val_loss: 1.3867e-04 - val_accuracy: 0.7967\n",
"Epoch 31/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.1691e-04 - accuracy: 0.8320 - val_loss: 1.3214e-04 - val_accuracy: 0.7967\n",
"Epoch 32/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.1136e-04 - accuracy: 0.8320 - val_loss: 1.2598e-04 - val_accuracy: 0.7967\n",
"Epoch 33/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 1.0581e-04 - accuracy: 0.8320 - val_loss: 1.2037e-04 - val_accuracy: 0.7967\n",
"Epoch 34/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.0094e-04 - accuracy: 0.8320 - val_loss: 1.1510e-04 - val_accuracy: 0.7967\n",
"Epoch 35/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 9.6509e-05 - accuracy: 0.8320 - val_loss: 1.1007e-04 - val_accuracy: 0.7967\n",
"Epoch 36/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 9.1906e-05 - accuracy: 0.8320 - val_loss: 1.0552e-04 - val_accuracy: 0.7967\n",
"Epoch 37/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 8.8316e-05 - accuracy: 0.8320 - val_loss: 1.0103e-04 - val_accuracy: 0.7967\n",
"Epoch 38/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 8.4173e-05 - accuracy: 0.8320 - val_loss: 9.6977e-05 - val_accuracy: 0.7967\n",
"Epoch 39/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 8.0652e-05 - accuracy: 0.8320 - val_loss: 9.3173e-05 - val_accuracy: 0.7967\n",
"Epoch 40/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 7.7370e-05 - accuracy: 0.8320 - val_loss: 8.9587e-05 - val_accuracy: 0.7967\n",
"Epoch 41/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 7.4173e-05 - accuracy: 0.8320 - val_loss: 8.6252e-05 - val_accuracy: 0.7967\n",
"Epoch 42/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 7.1361e-05 - accuracy: 0.8320 - val_loss: 8.3038e-05 - val_accuracy: 0.7967\n",
"Epoch 43/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 6.8677e-05 - accuracy: 0.8320 - val_loss: 7.9983e-05 - val_accuracy: 0.7967\n",
"Epoch 44/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 6.5857e-05 - accuracy: 0.8320 - val_loss: 7.7215e-05 - val_accuracy: 0.7967\n",
"Epoch 45/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 6.3480e-05 - accuracy: 0.8320 - val_loss: 7.4552e-05 - val_accuracy: 0.7967\n",
"Epoch 46/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 6.1218e-05 - accuracy: 0.8320 - val_loss: 7.1979e-05 - val_accuracy: 0.7967\n",
"Epoch 47/100\n",
"5/5 [==============================] - 0s 16ms/step - loss: 5.9121e-05 - accuracy: 0.8320 - val_loss: 6.9503e-05 - val_accuracy: 0.7967\n",
"Epoch 48/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 5.6941e-05 - accuracy: 0.8320 - val_loss: 6.7209e-05 - val_accuracy: 0.7967\n",
"Epoch 49/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 5.4981e-05 - accuracy: 0.8320 - val_loss: 6.5030e-05 - val_accuracy: 0.7967\n",
"Epoch 50/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 5.3119e-05 - accuracy: 0.8320 - val_loss: 6.2944e-05 - val_accuracy: 0.7967\n",
"Epoch 51/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 5.1278e-05 - accuracy: 0.8320 - val_loss: 6.0994e-05 - val_accuracy: 0.7967\n",
"Epoch 52/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 4.9694e-05 - accuracy: 0.8320 - val_loss: 5.9080e-05 - val_accuracy: 0.7967\n",
"Epoch 53/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 4.8085e-05 - accuracy: 0.8320 - val_loss: 5.7260e-05 - val_accuracy: 0.7967\n",
"Epoch 54/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 4.6435e-05 - accuracy: 0.8320 - val_loss: 5.5595e-05 - val_accuracy: 0.7967\n",
"Epoch 55/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 4.5074e-05 - accuracy: 0.8320 - val_loss: 5.3952e-05 - val_accuracy: 0.7967\n",
"Epoch 56/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 4.3686e-05 - accuracy: 0.8320 - val_loss: 5.2380e-05 - val_accuracy: 0.7967\n",
"Epoch 57/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 4.2365e-05 - accuracy: 0.8320 - val_loss: 5.0873e-05 - val_accuracy: 0.7967\n",
"Epoch 58/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 4.1085e-05 - accuracy: 0.8320 - val_loss: 4.9454e-05 - val_accuracy: 0.7967\n",
"Epoch 59/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 3.9871e-05 - accuracy: 0.8320 - val_loss: 4.8096e-05 - val_accuracy: 0.7967\n",
"Epoch 60/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 3.8732e-05 - accuracy: 0.8320 - val_loss: 4.6784e-05 - val_accuracy: 0.7967\n",
"Epoch 61/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 3.7605e-05 - accuracy: 0.8320 - val_loss: 4.5543e-05 - val_accuracy: 0.7967\n",
"Epoch 62/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 3.6546e-05 - accuracy: 0.8320 - val_loss: 4.4351e-05 - val_accuracy: 0.7967\n",
"Epoch 63/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 3.5563e-05 - accuracy: 0.8320 - val_loss: 4.3189e-05 - val_accuracy: 0.7967\n",
"Epoch 64/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 3.4594e-05 - accuracy: 0.8320 - val_loss: 4.2078e-05 - val_accuracy: 0.7967\n",
"Epoch 65/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 3.3607e-05 - accuracy: 0.8320 - val_loss: 4.1036e-05 - val_accuracy: 0.7967\n",
"Epoch 66/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 3.2778e-05 - accuracy: 0.8320 - val_loss: 3.9999e-05 - val_accuracy: 0.7967\n",
"Epoch 67/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 3.1849e-05 - accuracy: 0.8320 - val_loss: 3.9042e-05 - val_accuracy: 0.7967\n",
"Epoch 68/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.1075e-05 - accuracy: 0.8320 - val_loss: 3.8093e-05 - val_accuracy: 0.7967\n",
"Epoch 69/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 3.0300e-05 - accuracy: 0.8320 - val_loss: 3.7175e-05 - val_accuracy: 0.7967\n",
"Epoch 70/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.9526e-05 - accuracy: 0.8320 - val_loss: 3.6295e-05 - val_accuracy: 0.7967\n",
"Epoch 71/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.8773e-05 - accuracy: 0.8320 - val_loss: 3.5455e-05 - val_accuracy: 0.7967\n",
"Epoch 72/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.8090e-05 - accuracy: 0.8320 - val_loss: 3.4627e-05 - val_accuracy: 0.7967\n",
"Epoch 73/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.7365e-05 - accuracy: 0.8320 - val_loss: 3.3853e-05 - val_accuracy: 0.7967\n",
"Epoch 74/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.6739e-05 - accuracy: 0.8320 - val_loss: 3.3093e-05 - val_accuracy: 0.7967\n",
"Epoch 75/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.6142e-05 - accuracy: 0.8320 - val_loss: 3.2343e-05 - val_accuracy: 0.7967\n",
"Epoch 76/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.5467e-05 - accuracy: 0.8320 - val_loss: 3.1654e-05 - val_accuracy: 0.7967\n",
"Epoch 77/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.4914e-05 - accuracy: 0.8320 - val_loss: 3.0965e-05 - val_accuracy: 0.7967\n",
"Epoch 78/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.4305e-05 - accuracy: 0.8320 - val_loss: 3.0323e-05 - val_accuracy: 0.7967\n",
"Epoch 79/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.3809e-05 - accuracy: 0.8320 - val_loss: 2.9674e-05 - val_accuracy: 0.7967\n",
"Epoch 80/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.3262e-05 - accuracy: 0.8320 - val_loss: 2.9059e-05 - val_accuracy: 0.7967\n",
"Epoch 81/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.2727e-05 - accuracy: 0.8320 - val_loss: 2.8470e-05 - val_accuracy: 0.7967\n",
"Epoch 82/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.2267e-05 - accuracy: 0.8320 - val_loss: 2.7884e-05 - val_accuracy: 0.7967\n",
"Epoch 83/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.1789e-05 - accuracy: 0.8320 - val_loss: 2.7315e-05 - val_accuracy: 0.7967\n",
"Epoch 84/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.1315e-05 - accuracy: 0.8320 - val_loss: 2.6768e-05 - val_accuracy: 0.7967\n",
"Epoch 85/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.0857e-05 - accuracy: 0.8320 - val_loss: 2.6242e-05 - val_accuracy: 0.7967\n",
"Epoch 86/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.0414e-05 - accuracy: 0.8320 - val_loss: 2.5737e-05 - val_accuracy: 0.7967\n",
"Epoch 87/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.9982e-05 - accuracy: 0.8320 - val_loss: 2.5254e-05 - val_accuracy: 0.7967\n",
"Epoch 88/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.9594e-05 - accuracy: 0.8320 - val_loss: 2.4769e-05 - val_accuracy: 0.7967\n",
"Epoch 89/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.9206e-05 - accuracy: 0.8320 - val_loss: 2.4298e-05 - val_accuracy: 0.7967\n",
"Epoch 90/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.8814e-05 - accuracy: 0.8320 - val_loss: 2.3845e-05 - val_accuracy: 0.7967\n",
"Epoch 91/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.8438e-05 - accuracy: 0.8320 - val_loss: 2.3405e-05 - val_accuracy: 0.7967\n",
"Epoch 92/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.8089e-05 - accuracy: 0.8320 - val_loss: 2.2974e-05 - val_accuracy: 0.7967\n",
"Epoch 93/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.7713e-05 - accuracy: 0.8320 - val_loss: 2.2567e-05 - val_accuracy: 0.7967\n",
"Epoch 94/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.7389e-05 - accuracy: 0.8320 - val_loss: 2.2162e-05 - val_accuracy: 0.7967\n",
"Epoch 95/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.7056e-05 - accuracy: 0.8320 - val_loss: 2.1772e-05 - val_accuracy: 0.7967\n",
"Epoch 96/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 1.6733e-05 - accuracy: 0.8320 - val_loss: 2.1391e-05 - val_accuracy: 0.7967\n",
"Epoch 97/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.6414e-05 - accuracy: 0.8320 - val_loss: 2.1027e-05 - val_accuracy: 0.7967\n",
"Epoch 98/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.6117e-05 - accuracy: 0.8320 - val_loss: 2.0666e-05 - val_accuracy: 0.7967\n",
"Epoch 99/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.5835e-05 - accuracy: 0.8320 - val_loss: 2.0307e-05 - val_accuracy: 0.7967\n",
"Epoch 100/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.5535e-05 - accuracy: 0.8320 - val_loss: 1.9967e-05 - val_accuracy: 0.7967\n",
"Epoch 1/100\n",
"5/5 [==============================] - 1s 61ms/step - loss: 0.2651 - accuracy: 0.3704 - val_loss: 0.2147 - val_accuracy: 0.6016\n",
"Epoch 2/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 0.1713 - accuracy: 0.6296 - val_loss: 0.1303 - val_accuracy: 0.8211\n",
"Epoch 3/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 0.0971 - accuracy: 0.7874 - val_loss: 0.0673 - val_accuracy: 0.8780\n",
"Epoch 4/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 0.0474 - accuracy: 0.8401 - val_loss: 0.0298 - val_accuracy: 0.8455\n",
"Epoch 5/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 0.0205 - accuracy: 0.8401 - val_loss: 0.0122 - val_accuracy: 0.8537\n",
"Epoch 6/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 0.0085 - accuracy: 0.8300 - val_loss: 0.0052 - val_accuracy: 0.8374\n",
"Epoch 7/100\n",
"5/5 [==============================] - 0s 16ms/step - loss: 0.0038 - accuracy: 0.8279 - val_loss: 0.0026 - val_accuracy: 0.8374\n",
"Epoch 8/100\n",
"5/5 [==============================] - 0s 18ms/step - loss: 0.0020 - accuracy: 0.8279 - val_loss: 0.0015 - val_accuracy: 0.8293\n",
"Epoch 9/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 0.0012 - accuracy: 0.8279 - val_loss: 9.5875e-04 - val_accuracy: 0.8293\n",
"Epoch 10/100\n",
"5/5 [==============================] - 0s 17ms/step - loss: 7.8793e-04 - accuracy: 0.8279 - val_loss: 6.9188e-04 - val_accuracy: 0.8293\n",
"Epoch 11/100\n",
"5/5 [==============================] - 0s 16ms/step - loss: 5.8164e-04 - accuracy: 0.8279 - val_loss: 5.3763e-04 - val_accuracy: 0.8293\n",
"Epoch 12/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 4.6130e-04 - accuracy: 0.8279 - val_loss: 4.4003e-04 - val_accuracy: 0.8293\n",
"Epoch 13/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 3.8249e-04 - accuracy: 0.8279 - val_loss: 3.7346e-04 - val_accuracy: 0.8293\n",
"Epoch 14/100\n",
"5/5 [==============================] - 0s 18ms/step - loss: 3.2161e-04 - accuracy: 0.8279 - val_loss: 3.2638e-04 - val_accuracy: 0.8293\n",
"Epoch 15/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.8472e-04 - accuracy: 0.8279 - val_loss: 2.8970e-04 - val_accuracy: 0.8293\n",
"Epoch 16/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 2.5239e-04 - accuracy: 0.8279 - val_loss: 2.6051e-04 - val_accuracy: 0.8293\n",
"Epoch 17/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.2638e-04 - accuracy: 0.8279 - val_loss: 2.3642e-04 - val_accuracy: 0.8293\n",
"Epoch 18/100\n",
"5/5 [==============================] - 0s 14ms/step - loss: 2.0437e-04 - accuracy: 0.8279 - val_loss: 2.1601e-04 - val_accuracy: 0.8293\n",
"Epoch 19/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 1.8487e-04 - accuracy: 0.8259 - val_loss: 1.9860e-04 - val_accuracy: 0.8293\n",
"Epoch 20/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.7046e-04 - accuracy: 0.8239 - val_loss: 1.8273e-04 - val_accuracy: 0.8293\n",
"Epoch 21/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 1.5533e-04 - accuracy: 0.8239 - val_loss: 1.6891e-04 - val_accuracy: 0.8293\n",
"Epoch 22/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.4333e-04 - accuracy: 0.8239 - val_loss: 1.5634e-04 - val_accuracy: 0.8293\n",
"Epoch 23/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.3179e-04 - accuracy: 0.8239 - val_loss: 1.4507e-04 - val_accuracy: 0.8293\n",
"Epoch 24/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.2124e-04 - accuracy: 0.8239 - val_loss: 1.3503e-04 - val_accuracy: 0.8293\n",
"Epoch 25/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 1.1223e-04 - accuracy: 0.8239 - val_loss: 1.2593e-04 - val_accuracy: 0.8293\n",
"Epoch 26/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.0407e-04 - accuracy: 0.8239 - val_loss: 1.1759e-04 - val_accuracy: 0.8293\n",
"Epoch 27/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 9.6814e-05 - accuracy: 0.8239 - val_loss: 1.0991e-04 - val_accuracy: 0.8293\n",
"Epoch 28/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 8.9962e-05 - accuracy: 0.8239 - val_loss: 1.0293e-04 - val_accuracy: 0.8293\n",
"Epoch 29/100\n",
"5/5 [==============================] - 0s 17ms/step - loss: 8.3907e-05 - accuracy: 0.8239 - val_loss: 9.6505e-05 - val_accuracy: 0.8293\n",
"Epoch 30/100\n",
"5/5 [==============================] - 0s 14ms/step - loss: 7.8229e-05 - accuracy: 0.8239 - val_loss: 9.0669e-05 - val_accuracy: 0.8293\n",
"Epoch 31/100\n",
"5/5 [==============================] - 0s 16ms/step - loss: 7.3020e-05 - accuracy: 0.8239 - val_loss: 8.5355e-05 - val_accuracy: 0.8293\n",
"Epoch 32/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 6.8551e-05 - accuracy: 0.8239 - val_loss: 8.0397e-05 - val_accuracy: 0.8293\n",
"Epoch 33/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 6.3827e-05 - accuracy: 0.8239 - val_loss: 7.6018e-05 - val_accuracy: 0.8293\n",
"Epoch 34/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 6.0200e-05 - accuracy: 0.8239 - val_loss: 7.1870e-05 - val_accuracy: 0.8293\n",
"Epoch 35/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 5.6764e-05 - accuracy: 0.8239 - val_loss: 6.7950e-05 - val_accuracy: 0.8293\n",
"Epoch 36/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 5.3251e-05 - accuracy: 0.8239 - val_loss: 6.4399e-05 - val_accuracy: 0.8293\n",
"Epoch 37/100\n",
"5/5 [==============================] - 0s 16ms/step - loss: 5.0200e-05 - accuracy: 0.8239 - val_loss: 6.1113e-05 - val_accuracy: 0.8293\n",
"Epoch 38/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 4.7530e-05 - accuracy: 0.8239 - val_loss: 5.8025e-05 - val_accuracy: 0.8293\n",
"Epoch 39/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 4.4844e-05 - accuracy: 0.8239 - val_loss: 5.5201e-05 - val_accuracy: 0.8293\n",
"Epoch 40/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 4.2346e-05 - accuracy: 0.8239 - val_loss: 5.2588e-05 - val_accuracy: 0.8293\n",
"Epoch 41/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 4.0262e-05 - accuracy: 0.8239 - val_loss: 5.0089e-05 - val_accuracy: 0.8293\n",
"Epoch 42/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.7959e-05 - accuracy: 0.8239 - val_loss: 4.7858e-05 - val_accuracy: 0.8293\n",
"Epoch 43/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 3.6235e-05 - accuracy: 0.8239 - val_loss: 4.5681e-05 - val_accuracy: 0.8293\n",
"Epoch 44/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 3.4433e-05 - accuracy: 0.8239 - val_loss: 4.3654e-05 - val_accuracy: 0.8293\n",
"Epoch 45/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 3.2738e-05 - accuracy: 0.8239 - val_loss: 4.1786e-05 - val_accuracy: 0.8293\n",
"Epoch 46/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 3.1195e-05 - accuracy: 0.8239 - val_loss: 4.0020e-05 - val_accuracy: 0.8293\n",
"Epoch 47/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.9615e-05 - accuracy: 0.8239 - val_loss: 3.8424e-05 - val_accuracy: 0.8293\n",
"Epoch 48/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.8398e-05 - accuracy: 0.8239 - val_loss: 3.6862e-05 - val_accuracy: 0.8293\n",
"Epoch 49/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.7106e-05 - accuracy: 0.8239 - val_loss: 3.5403e-05 - val_accuracy: 0.8293\n",
"Epoch 50/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 2.5957e-05 - accuracy: 0.8239 - val_loss: 3.4007e-05 - val_accuracy: 0.8293\n",
"Epoch 51/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.4761e-05 - accuracy: 0.8239 - val_loss: 3.2734e-05 - val_accuracy: 0.8293\n",
"Epoch 52/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.3705e-05 - accuracy: 0.8239 - val_loss: 3.1530e-05 - val_accuracy: 0.8293\n",
"Epoch 53/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 2.2736e-05 - accuracy: 0.8239 - val_loss: 3.0386e-05 - val_accuracy: 0.8293\n",
"Epoch 54/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 2.1785e-05 - accuracy: 0.8239 - val_loss: 2.9315e-05 - val_accuracy: 0.8293\n",
"Epoch 55/100\n",
"5/5 [==============================] - 0s 16ms/step - loss: 2.0978e-05 - accuracy: 0.8239 - val_loss: 2.8272e-05 - val_accuracy: 0.8293\n",
"Epoch 56/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 2.0154e-05 - accuracy: 0.8239 - val_loss: 2.7277e-05 - val_accuracy: 0.8293\n",
"Epoch 57/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.9337e-05 - accuracy: 0.8239 - val_loss: 2.6357e-05 - val_accuracy: 0.8293\n",
"Epoch 58/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.8604e-05 - accuracy: 0.8239 - val_loss: 2.5475e-05 - val_accuracy: 0.8293\n",
"Epoch 59/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.7939e-05 - accuracy: 0.8239 - val_loss: 2.4629e-05 - val_accuracy: 0.8293\n",
"Epoch 60/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.7240e-05 - accuracy: 0.8239 - val_loss: 2.3842e-05 - val_accuracy: 0.8293\n",
"Epoch 61/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.6614e-05 - accuracy: 0.8239 - val_loss: 2.3094e-05 - val_accuracy: 0.8293\n",
"Epoch 62/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.6051e-05 - accuracy: 0.8239 - val_loss: 2.2364e-05 - val_accuracy: 0.8293\n",
"Epoch 63/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.5483e-05 - accuracy: 0.8239 - val_loss: 2.1674e-05 - val_accuracy: 0.8293\n",
"Epoch 64/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.4936e-05 - accuracy: 0.8239 - val_loss: 2.1022e-05 - val_accuracy: 0.8293\n",
"Epoch 65/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.4420e-05 - accuracy: 0.8239 - val_loss: 2.0401e-05 - val_accuracy: 0.8293\n",
"Epoch 66/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.3958e-05 - accuracy: 0.8239 - val_loss: 1.9797e-05 - val_accuracy: 0.8293\n",
"Epoch 67/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.3463e-05 - accuracy: 0.8239 - val_loss: 1.9238e-05 - val_accuracy: 0.8293\n",
"Epoch 68/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.3060e-05 - accuracy: 0.8239 - val_loss: 1.8685e-05 - val_accuracy: 0.8293\n",
"Epoch 69/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.2627e-05 - accuracy: 0.8239 - val_loss: 1.8162e-05 - val_accuracy: 0.8293\n",
"Epoch 70/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.2241e-05 - accuracy: 0.8239 - val_loss: 1.7656e-05 - val_accuracy: 0.8293\n",
"Epoch 71/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.1856e-05 - accuracy: 0.8239 - val_loss: 1.7174e-05 - val_accuracy: 0.8293\n",
"Epoch 72/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 1.1485e-05 - accuracy: 0.8239 - val_loss: 1.6715e-05 - val_accuracy: 0.8293\n",
"Epoch 73/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.1118e-05 - accuracy: 0.8239 - val_loss: 1.6289e-05 - val_accuracy: 0.8293\n",
"Epoch 74/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.0834e-05 - accuracy: 0.8239 - val_loss: 1.5853e-05 - val_accuracy: 0.8293\n",
"Epoch 75/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.0483e-05 - accuracy: 0.8239 - val_loss: 1.5447e-05 - val_accuracy: 0.8293\n",
"Epoch 76/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 1.0189e-05 - accuracy: 0.8239 - val_loss: 1.5059e-05 - val_accuracy: 0.8293\n",
"Epoch 77/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 9.8878e-06 - accuracy: 0.8239 - val_loss: 1.4687e-05 - val_accuracy: 0.8293\n",
"Epoch 78/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 9.6118e-06 - accuracy: 0.8239 - val_loss: 1.4327e-05 - val_accuracy: 0.8293\n",
"Epoch 79/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 9.3518e-06 - accuracy: 0.8239 - val_loss: 1.3977e-05 - val_accuracy: 0.8293\n",
"Epoch 80/100\n",
"5/5 [==============================] - 0s 15ms/step - loss: 9.0947e-06 - accuracy: 0.8239 - val_loss: 1.3641e-05 - val_accuracy: 0.8293\n",
"Epoch 81/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 8.8246e-06 - accuracy: 0.8239 - val_loss: 1.3328e-05 - val_accuracy: 0.8293\n",
"Epoch 82/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 8.5966e-06 - accuracy: 0.8239 - val_loss: 1.3021e-05 - val_accuracy: 0.8293\n",
"Epoch 83/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 8.3798e-06 - accuracy: 0.8239 - val_loss: 1.2718e-05 - val_accuracy: 0.8293\n",
"Epoch 84/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 8.1564e-06 - accuracy: 0.8239 - val_loss: 1.2430e-05 - val_accuracy: 0.8293\n",
"Epoch 85/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 7.9472e-06 - accuracy: 0.8239 - val_loss: 1.2151e-05 - val_accuracy: 0.8293\n",
"Epoch 86/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 7.7504e-06 - accuracy: 0.8239 - val_loss: 1.1874e-05 - val_accuracy: 0.8293\n",
"Epoch 87/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 7.5508e-06 - accuracy: 0.8239 - val_loss: 1.1612e-05 - val_accuracy: 0.8293\n",
"Epoch 88/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 7.3643e-06 - accuracy: 0.8239 - val_loss: 1.1360e-05 - val_accuracy: 0.8293\n",
"Epoch 89/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 7.1696e-06 - accuracy: 0.8239 - val_loss: 1.1120e-05 - val_accuracy: 0.8293\n",
"Epoch 90/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 6.9955e-06 - accuracy: 0.8239 - val_loss: 1.0892e-05 - val_accuracy: 0.8293\n",
"Epoch 91/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 6.8251e-06 - accuracy: 0.8239 - val_loss: 1.0670e-05 - val_accuracy: 0.8293\n",
"Epoch 92/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 6.6783e-06 - accuracy: 0.8239 - val_loss: 1.0444e-05 - val_accuracy: 0.8293\n",
"Epoch 93/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 6.5128e-06 - accuracy: 0.8239 - val_loss: 1.0231e-05 - val_accuracy: 0.8293\n",
"Epoch 94/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 6.3587e-06 - accuracy: 0.8239 - val_loss: 1.0027e-05 - val_accuracy: 0.8293\n",
"Epoch 95/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 6.2138e-06 - accuracy: 0.8239 - val_loss: 9.8272e-06 - val_accuracy: 0.8293\n",
"Epoch 96/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 6.0758e-06 - accuracy: 0.8239 - val_loss: 9.6314e-06 - val_accuracy: 0.8293\n",
"Epoch 97/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 5.9381e-06 - accuracy: 0.8239 - val_loss: 9.4424e-06 - val_accuracy: 0.8293\n",
"Epoch 98/100\n",
"5/5 [==============================] - 0s 11ms/step - loss: 5.8075e-06 - accuracy: 0.8239 - val_loss: 9.2590e-06 - val_accuracy: 0.8293\n",
"Epoch 99/100\n",
"5/5 [==============================] - 0s 13ms/step - loss: 5.6704e-06 - accuracy: 0.8239 - val_loss: 9.0852e-06 - val_accuracy: 0.8293\n",
"Epoch 100/100\n",
"5/5 [==============================] - 0s 12ms/step - loss: 5.5500e-06 - accuracy: 0.8239 - val_loss: 8.9151e-06 - val_accuracy: 0.8293\n",
"Epoch 1/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 6.0948e-06 - accuracy: 0.8250\n",
"Epoch 2/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 5.9109e-06 - accuracy: 0.8250\n",
"Epoch 3/100\n",
"7/7 [==============================] - 0s 4ms/step - loss: 5.7291e-06 - accuracy: 0.8250\n",
"Epoch 4/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 5.5591e-06 - accuracy: 0.8250\n",
"Epoch 5/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 5.3859e-06 - accuracy: 0.8250\n",
"Epoch 6/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 5.2283e-06 - accuracy: 0.8250\n",
"Epoch 7/100\n",
"7/7 [==============================] - 0s 4ms/step - loss: 5.0567e-06 - accuracy: 0.8250\n",
"Epoch 8/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 4.9139e-06 - accuracy: 0.8250\n",
"Epoch 9/100\n",
"7/7 [==============================] - 0s 4ms/step - loss: 4.7737e-06 - accuracy: 0.8250\n",
"Epoch 10/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 4.6305e-06 - accuracy: 0.8250\n",
"Epoch 11/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 4.5069e-06 - accuracy: 0.8250\n",
"Epoch 12/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 4.3871e-06 - accuracy: 0.8250\n",
"Epoch 13/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 4.2696e-06 - accuracy: 0.8250\n",
"Epoch 14/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 4.1591e-06 - accuracy: 0.8250\n",
"Epoch 15/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 4.0514e-06 - accuracy: 0.8250\n",
"Epoch 16/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 3.9512e-06 - accuracy: 0.8250\n",
"Epoch 17/100\n",
"7/7 [==============================] - 0s 5ms/step - loss: 3.8481e-06 - accuracy: 0.8250\n",
"Epoch 18/100\n",
"7/7 [==============================] - 0s 4ms/step - loss: 3.7440e-06 - accuracy: 0.8250\n",
"Epoch 19/100\n",
"7/7 [==============================] - 0s 4ms/step - loss: 3.6545e-06 - accuracy: 0.8250\n",
"Epoch 20/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 3.5614e-06 - accuracy: 0.8250\n",
"Epoch 21/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 3.4682e-06 - accuracy: 0.8250\n",
"Epoch 22/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 3.3837e-06 - accuracy: 0.8250\n",
"Epoch 23/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 3.3057e-06 - accuracy: 0.8250\n",
"Epoch 24/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 3.2294e-06 - accuracy: 0.8250\n",
"Epoch 25/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 3.1601e-06 - accuracy: 0.8250\n",
"Epoch 26/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 3.0861e-06 - accuracy: 0.8250\n",
"Epoch 27/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 3.0178e-06 - accuracy: 0.8250\n",
"Epoch 28/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 2.9575e-06 - accuracy: 0.8250\n",
"Epoch 29/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 2.8896e-06 - accuracy: 0.8250\n",
"Epoch 30/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 2.8250e-06 - accuracy: 0.8250\n",
"Epoch 31/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 2.7704e-06 - accuracy: 0.8250\n",
"Epoch 32/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 2.7134e-06 - accuracy: 0.8250\n",
"Epoch 33/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 2.6540e-06 - accuracy: 0.8250\n",
"Epoch 34/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 2.5966e-06 - accuracy: 0.8250\n",
"Epoch 35/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 2.5401e-06 - accuracy: 0.8250\n",
"Epoch 36/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 2.4861e-06 - accuracy: 0.8250\n",
"Epoch 37/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 2.4368e-06 - accuracy: 0.8250\n",
"Epoch 38/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 2.3857e-06 - accuracy: 0.8250\n",
"Epoch 39/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 2.3380e-06 - accuracy: 0.8250\n",
"Epoch 40/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 2.2917e-06 - accuracy: 0.8250\n",
"Epoch 41/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 2.2502e-06 - accuracy: 0.8250\n",
"Epoch 42/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 2.2035e-06 - accuracy: 0.8250\n",
"Epoch 43/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 2.1614e-06 - accuracy: 0.8250\n",
"Epoch 44/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 2.1184e-06 - accuracy: 0.8250\n",
"Epoch 45/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 2.0761e-06 - accuracy: 0.8250\n",
"Epoch 46/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 2.0330e-06 - accuracy: 0.8250\n",
"Epoch 47/100\n",
"7/7 [==============================] - 0s 4ms/step - loss: 1.9972e-06 - accuracy: 0.8250\n",
"Epoch 48/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.9597e-06 - accuracy: 0.8250\n",
"Epoch 49/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.9256e-06 - accuracy: 0.8250\n",
"Epoch 50/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.8896e-06 - accuracy: 0.8250\n",
"Epoch 51/100\n",
"7/7 [==============================] - 0s 4ms/step - loss: 1.8567e-06 - accuracy: 0.8250\n",
"Epoch 52/100\n",
"7/7 [==============================] - 0s 4ms/step - loss: 1.8239e-06 - accuracy: 0.8250\n",
"Epoch 53/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.7905e-06 - accuracy: 0.8250\n",
"Epoch 54/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.7601e-06 - accuracy: 0.8250\n",
"Epoch 55/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.7315e-06 - accuracy: 0.8250\n",
"Epoch 56/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.7024e-06 - accuracy: 0.8250\n",
"Epoch 57/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.6755e-06 - accuracy: 0.8250\n",
"Epoch 58/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.6489e-06 - accuracy: 0.8250\n",
"Epoch 59/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.6224e-06 - accuracy: 0.8250\n",
"Epoch 60/100\n",
"7/7 [==============================] - 0s 4ms/step - loss: 1.5949e-06 - accuracy: 0.8250\n",
"Epoch 61/100\n",
"7/7 [==============================] - 0s 4ms/step - loss: 1.5679e-06 - accuracy: 0.8250\n",
"Epoch 62/100\n",
"7/7 [==============================] - 0s 4ms/step - loss: 1.5445e-06 - accuracy: 0.8250\n",
"Epoch 63/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.5195e-06 - accuracy: 0.8250\n",
"Epoch 64/100\n",
"7/7 [==============================] - 0s 4ms/step - loss: 1.4952e-06 - accuracy: 0.8250\n",
"Epoch 65/100\n",
"7/7 [==============================] - 0s 4ms/step - loss: 1.4706e-06 - accuracy: 0.8250\n",
"Epoch 66/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.4473e-06 - accuracy: 0.8250\n",
"Epoch 67/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.4259e-06 - accuracy: 0.8250\n",
"Epoch 68/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.4045e-06 - accuracy: 0.8250\n",
"Epoch 69/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.3827e-06 - accuracy: 0.8250\n",
"Epoch 70/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.3623e-06 - accuracy: 0.8250\n",
"Epoch 71/100\n",
"7/7 [==============================] - 0s 4ms/step - loss: 1.3426e-06 - accuracy: 0.8250\n",
"Epoch 72/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.3231e-06 - accuracy: 0.8250\n",
"Epoch 73/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.3031e-06 - accuracy: 0.8250\n",
"Epoch 74/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.2849e-06 - accuracy: 0.8250\n",
"Epoch 75/100\n",
"7/7 [==============================] - 0s 4ms/step - loss: 1.2658e-06 - accuracy: 0.8250\n",
"Epoch 76/100\n",
"7/7 [==============================] - 0s 4ms/step - loss: 1.2470e-06 - accuracy: 0.8250\n",
"Epoch 77/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.2294e-06 - accuracy: 0.8250\n",
"Epoch 78/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.2125e-06 - accuracy: 0.8250\n",
"Epoch 79/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.1931e-06 - accuracy: 0.8250\n",
"Epoch 80/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.1757e-06 - accuracy: 0.8250\n",
"Epoch 81/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.1594e-06 - accuracy: 0.8250\n",
"Epoch 82/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.1429e-06 - accuracy: 0.8250\n",
"Epoch 83/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.1280e-06 - accuracy: 0.8250\n",
"Epoch 84/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.1121e-06 - accuracy: 0.8250\n",
"Epoch 85/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.0962e-06 - accuracy: 0.8250\n",
"Epoch 86/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.0802e-06 - accuracy: 0.8250\n",
"Epoch 87/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.0662e-06 - accuracy: 0.8250\n",
"Epoch 88/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.0531e-06 - accuracy: 0.8250\n",
"Epoch 89/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.0387e-06 - accuracy: 0.8250\n",
"Epoch 90/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.0251e-06 - accuracy: 0.8250\n",
"Epoch 91/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.0117e-06 - accuracy: 0.8250\n",
"Epoch 92/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 1.0002e-06 - accuracy: 0.8250\n",
"Epoch 93/100\n",
"7/7 [==============================] - 0s 4ms/step - loss: 9.8552e-07 - accuracy: 0.8250\n",
"Epoch 94/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 9.7282e-07 - accuracy: 0.8250\n",
"Epoch 95/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 9.5606e-07 - accuracy: 0.8250\n",
"Epoch 96/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 9.4239e-07 - accuracy: 0.8250\n",
"Epoch 97/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 9.2867e-07 - accuracy: 0.8250\n",
"Epoch 98/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 9.1712e-07 - accuracy: 0.8250\n",
"Epoch 99/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 9.0452e-07 - accuracy: 0.8250\n",
"Epoch 100/100\n",
"7/7 [==============================] - 0s 3ms/step - loss: 8.9307e-07 - accuracy: 0.8250\n",
"[0.3704453408718109, 0.6295546293258667, 0.7874494194984436, 0.840080976486206, 0.840080976486206, 0.829959511756897, 0.8279352188110352, 0.8279352188110352, 0.8279352188110352, 0.8279352188110352, 0.8279352188110352, 0.8279352188110352, 0.8279352188110352, 0.8279352188110352, 0.8279352188110352, 0.8279352188110352, 0.8279352188110352, 0.8279352188110352, 0.8259109258651733, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115, 0.8238866329193115]\n",
"[0.26510804891586304, 0.1713247299194336, 0.09705796092748642, 0.04737413674592972, 0.020477909594774246, 0.00846175942569971, 0.0038459363859146833, 0.0019572663586586714, 0.0011695781722664833, 0.0007879302138462663, 0.0005816396442241967, 0.0004613046767190099, 0.0003824884770438075, 0.00032161048147827387, 0.00028471878613345325, 0.00025238521629944444, 0.00022637817892245948, 0.0002043702406808734, 0.00018487342458683997, 0.00017045895219780505, 0.00015532721590716392, 0.00014332932187244296, 0.00013178630615584552, 0.0001212421921081841, 0.00011223170440644026, 0.00010407018999103457, 9.681445226306096e-05, 8.996229007607326e-05, 8.390725270146504e-05, 7.822852057870477e-05, 7.302047742996365e-05, 6.855121318949386e-05, 6.382728315657005e-05, 6.019971988280304e-05, 5.676442015101202e-05, 5.3250656492309645e-05, 5.019962918595411e-05, 4.752955646836199e-05, 4.484423698158935e-05, 4.2345978727098554e-05, 4.026213719043881e-05, 3.7958856410114095e-05, 3.623523662099615e-05, 3.4433131077094004e-05, 3.2737560104578733e-05, 3.119474058621563e-05, 2.961535756185185e-05, 2.839771332219243e-05, 2.710553781071212e-05, 2.5957033358281478e-05, 2.4760673113632947e-05, 2.3705211788183078e-05, 2.27360305871116e-05, 2.1785139324492775e-05, 2.09777062991634e-05, 2.015419704548549e-05, 1.9336837794980966e-05, 1.860437805589754e-05, 1.7938595192390494e-05, 1.724003959679976e-05, 1.6614212654531002e-05, 1.6050720660132356e-05, 1.5482861272175796e-05, 1.4936449588276446e-05, 1.442048142052954e-05, 1.3958482668385841e-05, 1.3462928109220229e-05, 1.3060066521575209e-05, 1.2627419891941827e-05, 1.2241029253345914e-05, 1.1855577213282231e-05, 1.148512092186138e-05, 1.1117897884105332e-05, 1.0834173735929653e-05, 1.048294870997779e-05, 1.0188908163399901e-05, 9.887841770250816e-06, 9.611836503609084e-06, 9.35175376071129e-06, 9.094696906686295e-06, 8.82464610185707e-06, 8.596624866186175e-06, 8.379810424230527e-06, 8.156369403877761e-06, 7.947160156618338e-06, 7.750390977889765e-06, 7.550789632659871e-06, 7.364276825683191e-06, 7.169613127189223e-06, 6.995529020059621e-06, 6.8251329139457084e-06, 6.678331828879891e-06, 6.512816071335692e-06, 6.358654900395777e-06, 6.213774668140104e-06, 6.075845249142731e-06, 5.938092726864852e-06, 5.807462912343908e-06, 5.670374321198324e-06, 5.549996330955764e-06]\n",
"[0.2147301286458969, 0.13029871881008148, 0.06731414794921875, 0.029764795675873756, 0.012174710631370544, 0.0052451686933636665, 0.002568677766248584, 0.0014680600725114346, 0.0009587483364157379, 0.0006918762228451669, 0.0005376273184083402, 0.00044003146467730403, 0.00037345648161135614, 0.0003263847029302269, 0.0002897039521485567, 0.00026051170425489545, 0.0002364225365454331, 0.00021600833861157298, 0.00019860424799844623, 0.00018272917077410966, 0.00016890591359697282, 0.00015634125156793743, 0.00014507224841509014, 0.0001350250095129013, 0.0001259254349861294, 0.0001175885772681795, 0.00010991400631610304, 0.00010292865772498772, 9.650499123381451e-05, 9.06694185687229e-05, 8.535535744158551e-05, 8.039730892051011e-05, 7.601814286317676e-05, 7.18704832252115e-05, 6.794971704948694e-05, 6.439867138396949e-05, 6.111325637903064e-05, 5.8024830650538206e-05, 5.520101694855839e-05, 5.258751843939535e-05, 5.0088518037227914e-05, 4.7858458856353536e-05, 4.568129588733427e-05, 4.365401764516719e-05, 4.178556628176011e-05, 4.001970955869183e-05, 3.842431397060864e-05, 3.686166019178927e-05, 3.540303441695869e-05, 3.4007462090812624e-05, 3.273432230344042e-05, 3.153004581690766e-05, 3.038638533325866e-05, 2.931473500211723e-05, 2.8271701012272388e-05, 2.7277154003968462e-05, 2.6356554371886887e-05, 2.547546500863973e-05, 2.4629291146993637e-05, 2.384203253313899e-05, 2.3094038624549285e-05, 2.2364474716596305e-05, 2.167394086427521e-05, 2.1022193323005922e-05, 2.0400748326210305e-05, 1.979700209631119e-05, 1.9238095774198882e-05, 1.8684528185985982e-05, 1.8161739717470482e-05, 1.765592605806887e-05, 1.7173864762298763e-05, 1.671531754254829e-05, 1.62894884851994e-05, 1.58532420755364e-05, 1.5446808902197517e-05, 1.5059037650644314e-05, 1.4686536815133877e-05, 1.4326883501780685e-05, 1.3976925401948392e-05, 1.3641026271216106e-05, 1.3328393833944574e-05, 1.3020609003433492e-05, 1.271815926884301e-05, 1.2429521120793652e-05, 1.2151307601016015e-05, 1.1874308256665245e-05, 1.1612332855293062e-05, 1.1359809832356405e-05, 1.1120376257167663e-05, 1.0891603778873105e-05, 1.0669618859537877e-05, 1.044448436005041e-05, 1.0231467967969365e-05, 1.00274182841531e-05, 9.827247595239896e-06, 9.631437933421694e-06, 9.44241492106812e-06, 9.258967111236416e-06, 9.085210876946803e-06, 8.91509171196958e-06]\n",
"[0.6016260385513306, 0.8211382031440735, 0.8780487775802612, 0.8455284833908081, 0.8536585569381714, 0.8373983502388, 0.8373983502388, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368, 0.8292682766914368]\n"
]
},
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"1/1 [==============================] - 0s 113ms/step\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/tmp/ipykernel_21/30731265.py:109: FutureWarning: The default value of numeric_only in DataFrame.mean is deprecated. In a future version, it will default to False. In addition, specifying 'numeric_only=None' is deprecated. Select only valid columns or specify the value of numeric_only to silence this warning.\n",
" test_df.fillna(df.mean(), inplace=True)\n"
]
}
],
"source": [
"from sklearn.model_selection import train_test_split, KFold\n",
"from sklearn.preprocessing import StandardScaler\n",
"from keras.models import Sequential\n",
"from keras.layers import Dense\n",
"from keras.callbacks import EarlyStopping\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"from sklearn.metrics import confusion_matrix\n",
"from keras.utils import to_categorical\n",
"import keras.backend as K\n",
"\n",
"# Read the CSV file into a DataFrame\n",
"df = pd.read_csv(\"/kaggle/input/icr-identify-age-related-conditions/train.csv\")\n",
"\n",
"# Fill missing values with the mean\n",
"df.fillna(df.mean(), inplace=True)\n",
"\n",
"# Split the data into input features (x) and labels (y)\n",
"# and drop non-numeric values\n",
"x = df.drop(['Id', 'Class', 'EJ'], axis=1)\n",
"y = df['Class']\n",
"\n",
"# Convert labels to one-hot encoded vectors\n",
"y_one_hot = to_categorical(y, num_classes=2)\n",
"\n",
"# Scale the data using StandardScaler\n",
"scaler = StandardScaler()\n",
"x_scaled = scaler.fit_transform(x)\n",
"\n",
"# Define the model architecture\n",
"model = Sequential()\n",
"model.add(Dense(128, activation='relu', input_dim=len(x.columns)))\n",
"model.add(Dense(64, activation='relu'))\n",
"model.add(Dense(32, activation='relu'))\n",
"model.add(Dense(2, activation='sigmoid')) # Change the number of units to 2\n",
"\n",
"# Define the custom loss function\n",
"def balanced_log_loss(y_true, y_pred):\n",
" y_pred = K.clip(y_pred, K.epsilon(), 1 - K.epsilon())\n",
" class_0_loss = -K.mean(y_true[:, 0] * K.log(y_pred[:, 0]))\n",
" class_1_loss = -K.mean(y_true[:, 1] * K.log(y_pred[:, 1]))\n",
" return (class_0_loss + class_1_loss) / 2\n",
"\n",
"# Compile the model with the balanced logarithmic loss\n",
"model.compile(loss=balanced_log_loss, optimizer='adam', metrics=['accuracy'])\n",
"model.summary()\n",
"\n",
"# Perform KFold cross-validation\n",
"kf = KFold(n_splits=5, random_state=0, shuffle=True)\n",
"\n",
"best_val_loss = float('inf')\n",
"best_epoch = 0\n",
"\n",
"for train_index, val_index in kf.split(x_scaled):\n",
" x_train, x_val = x_scaled[train_index], x_scaled[val_index]\n",
" y_train, y_val = y_one_hot[train_index], y_one_hot[val_index]\n",
"\n",
" # Define the model architecture\n",
" model = Sequential()\n",
" model.add(Dense(128, activation='relu', input_dim=len(x.columns)))\n",
" model.add(Dense(64, activation='relu'))\n",
" model.add(Dense(32, activation='relu'))\n",
" model.add(Dense(2, activation='sigmoid')) # Change the number of units to 2\n",
" model.compile(loss=balanced_log_loss, optimizer='adam', metrics=['accuracy'])\n",
" \n",
" # Define early stopping callback\n",
" early_stopping = EarlyStopping(monitor='val_loss', patience=10, mode='min', restore_best_weights=True)\n",
"\n",
" # Train the model\n",
" hist = model.fit(x_train, y_train, validation_data=(x_val, y_val), epochs=100, batch_size=100, callbacks=[early_stopping])\n",
" \n",
" # Track the best epoch based on validation loss\n",
" if np.min(hist.history['val_loss']) < best_val_loss:\n",
" best_val_loss = np.min(hist.history['val_loss'])\n",
" best_epoch = np.argmin(hist.history['val_loss']) + 1\n",
"\n",
"# Train the final model with the best epoch\n",
"model.fit(x_scaled, y_one_hot, epochs=best_epoch, batch_size=100)\n",
"\n",
"# Print training accuracy\n",
"print(hist.history['accuracy'])\n",
"\n",
"# Print training loss\n",
"print(hist.history['loss'])\n",
"\n",
"# Print validation loss\n",
"print(hist.history['val_loss'])\n",
"\n",
"# Print validation accuracy\n",
"print(hist.history['val_accuracy'])\n",
"\n",
"# Plot training and validation accuracy\n",
"sns.set()\n",
"acc = hist.history['accuracy']\n",
"val = hist.history['val_accuracy']\n",
"epochs = range(1, len(acc) + 1)\n",
"plt.plot(epochs, acc, '-', label='Training accuracy')\n",
"plt.plot(epochs, val, ':', label='Validation accuracy')\n",
"plt.title('Training and Validation Accuracy')\n",
"plt.xlabel('Epoch')\n",
"plt.ylabel('Accuracy')\n",
"plt.legend(loc='lower right')\n",
"plt.show()\n",
"\n",
"# Load the test data\n",
"test_df = pd.read_csv(\"/kaggle/input/icr-identify-age-related-conditions/test.csv\")\n",
"\n",
"# Fill missing values with the mean\n",
"test_df.fillna(df.mean(), inplace=True)\n",
"\n",
"# Scale the test data using StandardScaler\n",
"test_x_scaled = scaler.transform(test_df.drop(['Id', 'EJ'], axis=1))\n",
"\n",
"# Predict the probabilities for the test data using the trained model\n",
"probabilities = model.predict(test_x_scaled)\n",
"\n",
"# Clip the predicted probabilities\n",
"probabilities = np.clip(probabilities, 1e-15, 1 - 1e-15)\n",
"\n",
"# Rescale the probabilities\n",
"probabilities /= probabilities.sum(axis=1, keepdims=True)\n",
"\n",
"# Create a DataFrame for the predictions\n",
"sample = pd.read_csv('/kaggle/input/icr-identify-age-related-conditions/sample_submission.csv')\n",
"sample['class_1'] = probabilities[:, 1] # Probability for class 1\n",
"sample['class_0'] = probabilities[:, 0] # Probability for class 0\n",
"sample.to_csv('submission.csv', index=False)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ea5cf023",
"metadata": {
"papermill": {
"duration": 0.170151,
"end_time": "2023-08-10T14:35:06.324411",
"exception": false,
"start_time": "2023-08-10T14:35:06.154260",
"status": "completed"
},
"tags": []
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.10.12"
},
"papermill": {
"default_parameters": {},
"duration": 74.85881,
"end_time": "2023-08-10T14:35:08.931637",
"environment_variables": {},
"exception": null,
"input_path": "__notebook__.ipynb",
"output_path": "__notebook__.ipynb",
"parameters": {},
"start_time": "2023-08-10T14:33:54.072827",
"version": "2.4.0"
}
},
"nbformat": 4,
"nbformat_minor": 5
}