Skip to content

Instantly share code, notes, and snippets.

@mapmeld

mapmeld/AutoKeras_image_regression.ipynb

Created April 28, 2020 21:22
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save mapmeld/98d1e9839f2d1f9c4ee197953661ed07 to your computer and use it in GitHub Desktop.
Save mapmeld/98d1e9839f2d1f9c4ee197953661ed07 to your computer and use it in GitHub Desktop.
Download ZIP
AutoKeras Image Regression
Display the source blob
Display the rendered blob
Raw
AutoKeras_image_regression.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "AutoKeras-ImageAge.ipynb",
"provenance": [],
"machine_shape": "hm"
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"accelerator": "GPU"
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "OngbNtFwK1sz",
"colab_type": "text"
},
"source": [
"# About this project\n",
"- This is a demo of AutoKeras's ImageRegressor\n",
"- Dataset of images and ages from https://data.vision.ee.ethz.ch/cvl/rrothe/imdb-wiki/\n",
"- Inspired by Abhik Jha's FastAI tutorial at https://medium.com/analytics-vidhya/68294d34f2ed"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "avOi1zJKMgwW",
"colab_type": "text"
},
"source": [
"# Import IMDB Celeb images and metadata"
]
},
{
"cell_type": "code",
"metadata": {
"id": "V5pxn5a_K4w0",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 196
},
"outputId": "c4c1afa2-5eeb-45fb-80d9-b72655b9facc"
},
"source": [
"! wget -O ./drive/My\\ Drive/mlin/celebs/imdb_0.tar https://data.vision.ee.ethz.ch/cvl/rrothe/imdb-wiki/static/imdb_0.tar"
],
"execution_count": 1,
"outputs": [
{
"output_type": "stream",
"text": [
"--2020-04-28 15:35:19-- https://data.vision.ee.ethz.ch/cvl/rrothe/imdb-wiki/static/imdb_0.tar\n",
"Resolving data.vision.ee.ethz.ch (data.vision.ee.ethz.ch)... 129.132.52.162\n",
"Connecting to data.vision.ee.ethz.ch (data.vision.ee.ethz.ch)|129.132.52.162|:443... connected.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 28708782080 (27G) [application/x-tar]\n",
"Saving to: ‘./drive/My Drive/mlin/celebs/imdb_0.tar’\n",
"\n",
"./drive/My Drive/ml 100%[===================>] 26.74G 11.6MB/s in 38m 44s \n",
"\n",
"2020-04-28 16:14:04 (11.8 MB/s) - ‘./drive/My Drive/mlin/celebs/imdb_0.tar’ saved [28708782080/28708782080]\n",
"\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "36cnwWWhagm0",
"colab_type": "code",
"colab": {}
},
"source": [
"! cd ./drive/My\\ Drive/mlin/celebs && tar -xf imdb_0.tar\n",
"! rm ./drive/My\\ Drive/mlin/celebs/imdb_0.tar"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "Wz1kFMxjrBw0",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 33
},
"outputId": "9ea7468a-c8a7-49fc-bf5f-55d5fa7889b9"
},
"source": [
"! ls ./drive/My\\ Drive/mlin/celebs/imdb/"
],
"execution_count": 5,
"outputs": [
{
"output_type": "stream",
"text": [
"00 01\t02 03\t04 05\t06 07\t08 09\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "kwgZp6iVmJPS",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 196
},
"outputId": "234e22da-45ad-4de3-b15e-c3b69d6aef62"
},
"source": [
"! wget https://data.vision.ee.ethz.ch/cvl/rrothe/imdb-wiki/static/imdb_meta.tar\n",
"! tar -xf imdb_meta.tar\n",
"! rm imdb_meta.tar"
],
"execution_count": 1,
"outputs": [
{
"output_type": "stream",
"text": [
"--2020-04-28 16:44:27-- https://data.vision.ee.ethz.ch/cvl/rrothe/imdb-wiki/static/imdb_meta.tar\n",
"Resolving data.vision.ee.ethz.ch (data.vision.ee.ethz.ch)... 129.132.52.162\n",
"Connecting to data.vision.ee.ethz.ch (data.vision.ee.ethz.ch)|129.132.52.162|:443... connected.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 22937600 (22M) [application/x-tar]\n",
"Saving to: ‘imdb_meta.tar’\n",
"\n",
"imdb_meta.tar 100%[===================>] 21.88M 10.1MB/s in 2.2s \n",
"\n",
"2020-04-28 16:44:30 (10.1 MB/s) - ‘imdb_meta.tar’ saved [22937600/22937600]\n",
"\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Iba_lkdFLDcL",
"colab_type": "text"
},
"source": [
"## Converting from MATLAB date to actual Date-of-Birth"
]
},
{
"cell_type": "code",
"metadata": {
"id": "9g3tQz6G9cce",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 33
},
"outputId": "20961e39-9de2-450d-bf68-41c8eacf7bf7"
},
"source": [
"from datetime import datetime, timedelta \n",
"def datenum_to_datetime(datenum):\n",
" \"\"\"\n",
" Convert Matlab datenum into Python datetime.\n",
" \"\"\"\n",
" days = datenum % 1\n",
" hours = days % 1 * 24\n",
" minutes = hours % 1 * 60\n",
" seconds = minutes % 1 * 60\n",
" try:\n",
" return datetime.fromordinal(int(datenum)) \\\n",
" + timedelta(days=int(days)) \\\n",
" + timedelta(hours=int(hours)) \\\n",
" + timedelta(minutes=int(minutes)) \\\n",
" + timedelta(seconds=round(seconds)) \\\n",
" - timedelta(days=366)\n",
" except:\n",
" return datenum_to_datetime(700000)\n",
"\n",
"print(datenum_to_datetime(734963))"
],
"execution_count": 2,
"outputs": [
{
"output_type": "stream",
"text": [
"2012-04-04 00:00:00\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "P0cjHr0QLFj7",
"colab_type": "text"
},
"source": [
"## Opening MatLab file to Pandas DataFrame"
]
},
{
"cell_type": "code",
"metadata": {
"id": "Jv5KBFRxwmKG",
"colab_type": "code",
"colab": {}
},
"source": [
"from scipy.io import loadmat\n",
"x = loadmat('imdb/imdb.mat')"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "udrLp4rJxiTn",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 147
},
"outputId": "9bc6cbd2-d94b-4b59-e8ae-c03bb62fe1c1"
},
"source": [
"import pandas as pd\n",
"import numpy as np \n",
"\n",
"mdata = x['imdb'] # variable in mat file\n",
"mdtype = mdata.dtype # dtypes of structures are \"unsized objects\"\n",
"ndata = {n: mdata[n][0, 0] for n in mdtype.names}\n",
"columns = [n for n, v in ndata.items()]\n",
"\n",
"rows = []\n",
"for col in range(0, 10):\n",
" values = list(ndata.items())[col]\n",
" for num, val in enumerate(values[1][0], start=0):\n",
" if col == 0:\n",
" rows.append([])\n",
" if num > 0:\n",
" if columns[col] == \"dob\":\n",
" rows[num].append(datenum_to_datetime(int(val)))\n",
" elif columns[col] == \"photo_taken\":\n",
" rows[num].append(datetime(year=int(val), month=6, day=30))\n",
" else:\n",
" rows[num].append(val)\n",
"\n",
"dt = map(lambda row: np.array(row), np.array(rows[1:]))\n",
"\n",
"df = pd.DataFrame(data=dt, index=range(0, len(rows) - 1), columns=columns)\n",
"print(df.head())"
],
"execution_count": 4,
"outputs": [
{
"output_type": "stream",
"text": [
" dob photo_taken ... celeb_names celeb_id\n",
"0 1899-05-10 1970-06-30 ... ['Weird Al' Yankovic] 6488.0\n",
"1 1899-05-10 1968-06-30 ... [2 Chainz] 6488.0\n",
"2 1899-05-10 1968-06-30 ... [50 Cent] 6488.0\n",
"3 1899-05-10 1968-06-30 ... [A Martinez] 6488.0\n",
"4 1924-09-16 1991-06-30 ... [A.D. Miles] 11516.0\n",
"\n",
"[5 rows x 10 columns]\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "OsKbxd0s_3tm",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 228
},
"outputId": "066b6feb-2a0a-49d9-ede9-fe4d812a3997"
},
"source": [
"print(columns)\n",
"print(df[\"full_path\"])"
],
"execution_count": 5,
"outputs": [
{
"output_type": "stream",
"text": [
"['dob', 'photo_taken', 'full_path', 'gender', 'name', 'face_location', 'face_score', 'second_face_score', 'celeb_names', 'celeb_id']\n",
"0 [01/nm0000001_rm3343756032_1899-5-10_1970.jpg]\n",
"1 [01/nm0000001_rm577153792_1899-5-10_1968.jpg]\n",
"2 [01/nm0000001_rm946909184_1899-5-10_1968.jpg]\n",
"3 [01/nm0000001_rm980463616_1899-5-10_1968.jpg]\n",
"4 [02/nm0000002_rm1075631616_1924-9-16_1991.jpg]\n",
" ... \n",
"460717 [08/nm3994408_rm761245696_1989-12-29_2011.jpg]\n",
"460718 [08/nm3994408_rm784182528_1989-12-29_2011.jpg]\n",
"460719 [08/nm3994408_rm926592512_1989-12-29_2011.jpg]\n",
"460720 [08/nm3994408_rm943369728_1989-12-29_2011.jpg]\n",
"460721 [08/nm3994408_rm976924160_1989-12-29_2011.jpg]\n",
"Name: full_path, Length: 460722, dtype: object\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "9Ecay5xbLOEh",
"colab_type": "text"
},
"source": [
"## Calculating age at time photo was taken"
]
},
{
"cell_type": "code",
"metadata": {
"id": "KvJ2PMT67eYP",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 212
},
"outputId": "a35a42ce-7697-4ece-d816-2a03d038a260"
},
"source": [
"df[\"age\"] = (df[\"photo_taken\"] - df[\"dob\"]).astype('int') / 31558102e9\n",
"print(df[\"age\"])"
],
"execution_count": 6,
"outputs": [
{
"output_type": "stream",
"text": [
"0 71.136445\n",
"1 69.137846\n",
"2 69.137846\n",
"3 69.137846\n",
"4 66.783332\n",
" ... \n",
"460717 21.500000\n",
"460718 21.500000\n",
"460719 21.500000\n",
"460720 21.500000\n",
"460721 21.500000\n",
"Name: age, Length: 460722, dtype: float64\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "OGpbZs9LLTP-",
"colab_type": "text"
},
"source": [
"# Creating dataset\n",
"- We sample 200 of the images which were included in this first download.\n",
"- Images are resized to 128x128 to standardize shape and conserve memory\n",
"- RGB images are converted to grayscale to standardize shape\n",
"- Ages are converted to ints"
]
},
{
"cell_type": "code",
"metadata": {
"id": "h-uBjUTx_a3z",
"colab_type": "code",
"colab": {}
},
"source": [
"import os\n",
"train_set = df[df[\"full_path\"] < '02'].sample(200)\n",
"\n",
"from PIL import Image\n",
"images = []\n",
"for img_path in train_set[\"full_path\"]:\n",
" img = Image.open(\"./drive/My Drive/mlin/celebs/imdb/\" + img_path[0]).resize((128, 128)).convert('L')\n",
" images.append(\n",
" np.asarray(img, dtype=\"int32\")\n",
" )\n",
"\n",
"image_inputs = np.array(images)\n",
"\n",
"ages = train_set[\"age\"].astype('int').to_numpy()"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "iQxbO1-eLskA",
"colab_type": "text"
},
"source": [
"# Working with AutoKeras"
]
},
{
"cell_type": "code",
"metadata": {
"id": "CszJu9465teA",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 655
},
"outputId": "0c909f09-b46a-4699-db2f-31df54aef006"
},
"source": [
"! pip install autokeras"
],
"execution_count": 11,
"outputs": [
{
"output_type": "stream",
"text": [
"Collecting autokeras\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/a8/74/6588d79b8618c0f45ea2b3ace4959db2697029c8175bf1a0d2ed07c14761/autokeras-1.0.2-py3-none-any.whl (67kB)\n",
"\r\u001b[K |████▉ | 10kB 23.7MB/s eta 0:00:01\r\u001b[K |█████████▊ | 20kB 3.2MB/s eta 0:00:01\r\u001b[K |██████████████▋ | 30kB 4.6MB/s eta 0:00:01\r\u001b[K |███████████████████▍ | 40kB 3.0MB/s eta 0:00:01\r\u001b[K |████████████████████████▎ | 51kB 3.7MB/s eta 0:00:01\r\u001b[K |█████████████████████████████▏ | 61kB 4.4MB/s eta 0:00:01\r\u001b[K |████████████████████████████████| 71kB 3.5MB/s \n",
"\u001b[?25hRequirement already satisfied: packaging in /usr/local/lib/python3.6/dist-packages (from autokeras) (20.3)\n",
"Requirement already satisfied: scikit-learn in /usr/local/lib/python3.6/dist-packages (from autokeras) (0.22.2.post1)\n",
"Requirement already satisfied: pandas in /usr/local/lib/python3.6/dist-packages (from autokeras) (1.0.3)\n",
"Requirement already satisfied: numpy in /usr/local/lib/python3.6/dist-packages (from autokeras) (1.18.3)\n",
"Collecting keras-tuner>=1.0.1\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/a7/f7/4b41b6832abf4c9bef71a664dc563adb25afc5812831667c6db572b1a261/keras-tuner-1.0.1.tar.gz (54kB)\n",
"\u001b[K |████████████████████████████████| 61kB 4.8MB/s \n",
"\u001b[?25hRequirement already satisfied: six in /usr/local/lib/python3.6/dist-packages (from packaging->autokeras) (1.12.0)\n",
"Requirement already satisfied: pyparsing>=2.0.2 in /usr/local/lib/python3.6/dist-packages (from packaging->autokeras) (2.4.7)\n",
"Requirement already satisfied: scipy>=0.17.0 in /usr/local/lib/python3.6/dist-packages (from scikit-learn->autokeras) (1.4.1)\n",
"Requirement already satisfied: joblib>=0.11 in /usr/local/lib/python3.6/dist-packages (from scikit-learn->autokeras) (0.14.1)\n",
"Requirement already satisfied: python-dateutil>=2.6.1 in /usr/local/lib/python3.6/dist-packages (from pandas->autokeras) (2.8.1)\n",
"Requirement already satisfied: pytz>=2017.2 in /usr/local/lib/python3.6/dist-packages (from pandas->autokeras) (2018.9)\n",
"Requirement already satisfied: future in /usr/local/lib/python3.6/dist-packages (from keras-tuner>=1.0.1->autokeras) (0.16.0)\n",
"Requirement already satisfied: tabulate in /usr/local/lib/python3.6/dist-packages (from keras-tuner>=1.0.1->autokeras) (0.8.7)\n",
"Collecting terminaltables\n",
" Downloading https://files.pythonhosted.org/packages/9b/c4/4a21174f32f8a7e1104798c445dacdc1d4df86f2f26722767034e4de4bff/terminaltables-3.1.0.tar.gz\n",
"Collecting colorama\n",
" Downloading https://files.pythonhosted.org/packages/c9/dc/45cdef1b4d119eb96316b3117e6d5708a08029992b2fee2c143c7a0a5cc5/colorama-0.4.3-py2.py3-none-any.whl\n",
"Requirement already satisfied: tqdm in /usr/local/lib/python3.6/dist-packages (from keras-tuner>=1.0.1->autokeras) (4.38.0)\n",
"Requirement already satisfied: requests in /usr/local/lib/python3.6/dist-packages (from keras-tuner>=1.0.1->autokeras) (2.21.0)\n",
"Requirement already satisfied: urllib3<1.25,>=1.21.1 in /usr/local/lib/python3.6/dist-packages (from requests->keras-tuner>=1.0.1->autokeras) (1.24.3)\n",
"Requirement already satisfied: chardet<3.1.0,>=3.0.2 in /usr/local/lib/python3.6/dist-packages (from requests->keras-tuner>=1.0.1->autokeras) (3.0.4)\n",
"Requirement already satisfied: idna<2.9,>=2.5 in /usr/local/lib/python3.6/dist-packages (from requests->keras-tuner>=1.0.1->autokeras) (2.8)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.6/dist-packages (from requests->keras-tuner>=1.0.1->autokeras) (2020.4.5.1)\n",
"Building wheels for collected packages: keras-tuner, terminaltables\n",
" Building wheel for keras-tuner (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for keras-tuner: filename=keras_tuner-1.0.1-cp36-none-any.whl size=73200 sha256=2106ec06261241196be50589971a9d96e3f2640678a44556725b2999ac1c0f1a\n",
" Stored in directory: /root/.cache/pip/wheels/b9/cc/62/52716b70dd90f3db12519233c3a93a5360bc672da1a10ded43\n",
" Building wheel for terminaltables (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for terminaltables: filename=terminaltables-3.1.0-cp36-none-any.whl size=15356 sha256=d52229c9e913ebfc32a662ba22dd7aa50bd5b994182d6fc091ec7e4134bfa9bb\n",
" Stored in directory: /root/.cache/pip/wheels/30/6b/50/6c75775b681fb36cdfac7f19799888ef9d8813aff9e379663e\n",
"Successfully built keras-tuner terminaltables\n",
"Installing collected packages: terminaltables, colorama, keras-tuner, autokeras\n",
"Successfully installed autokeras-1.0.2 colorama-0.4.3 keras-tuner-1.0.1 terminaltables-3.1.0\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "o4CVtTsO5sOz",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"outputId": "7774348c-03a5-409b-dde8-c3640fb09390"
},
"source": [
"import autokeras as ak\n",
"\n",
"regressor = ak.ImageRegressor(max_trials=20)\n",
"regressor.fit(x=image_inputs, y=ages)"
],
"execution_count": 0,
"outputs": [
{
"output_type": "stream",
"text": [
"5/5 [==============================] - 8s 2s/step - loss: 1303.9402 - mean_squared_error: 1303.9402 - val_loss: 1685.1797 - val_mean_squared_error: 1618.4495\n",
"Epoch 451/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1303.6483 - mean_squared_error: 1303.6483 - val_loss: 1684.8372 - val_mean_squared_error: 1618.1165\n",
"Epoch 452/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1303.3562 - mean_squared_error: 1303.3562 - val_loss: 1684.4946 - val_mean_squared_error: 1617.7834\n",
"Epoch 453/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1303.0642 - mean_squared_error: 1303.0642 - val_loss: 1684.1520 - val_mean_squared_error: 1617.4502\n",
"Epoch 454/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1302.7719 - mean_squared_error: 1302.7719 - val_loss: 1683.8092 - val_mean_squared_error: 1617.1168\n",
"Epoch 455/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1302.4794 - mean_squared_error: 1302.4794 - val_loss: 1683.4662 - val_mean_squared_error: 1616.7834\n",
"Epoch 456/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1302.1869 - mean_squared_error: 1302.1869 - val_loss: 1683.1230 - val_mean_squared_error: 1616.4496\n",
"Epoch 457/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1301.8943 - mean_squared_error: 1301.8943 - val_loss: 1682.7799 - val_mean_squared_error: 1616.1160\n",
"Epoch 458/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1301.6018 - mean_squared_error: 1301.6018 - val_loss: 1682.4365 - val_mean_squared_error: 1615.7820\n",
"Epoch 459/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1301.3090 - mean_squared_error: 1301.3090 - val_loss: 1682.0930 - val_mean_squared_error: 1615.4480\n",
"Epoch 460/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1301.0160 - mean_squared_error: 1301.0160 - val_loss: 1681.7494 - val_mean_squared_error: 1615.1139\n",
"Epoch 461/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1300.7230 - mean_squared_error: 1300.7230 - val_loss: 1681.4055 - val_mean_squared_error: 1614.7795\n",
"Epoch 462/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1300.4299 - mean_squared_error: 1300.4299 - val_loss: 1681.0618 - val_mean_squared_error: 1614.4451\n",
"Epoch 463/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1300.1367 - mean_squared_error: 1300.1367 - val_loss: 1680.7175 - val_mean_squared_error: 1614.1106\n",
"Epoch 464/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1299.8434 - mean_squared_error: 1299.8434 - val_loss: 1680.3734 - val_mean_squared_error: 1613.7758\n",
"Epoch 465/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1299.5499 - mean_squared_error: 1299.5499 - val_loss: 1680.0293 - val_mean_squared_error: 1613.4412\n",
"Epoch 466/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1299.2563 - mean_squared_error: 1299.2563 - val_loss: 1679.6847 - val_mean_squared_error: 1613.1062\n",
"Epoch 467/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1298.9626 - mean_squared_error: 1298.9626 - val_loss: 1679.3403 - val_mean_squared_error: 1612.7712\n",
"Epoch 468/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1298.6689 - mean_squared_error: 1298.6689 - val_loss: 1678.9954 - val_mean_squared_error: 1612.4359\n",
"Epoch 469/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1298.3750 - mean_squared_error: 1298.3750 - val_loss: 1678.6506 - val_mean_squared_error: 1612.1006\n",
"Epoch 470/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1298.0811 - mean_squared_error: 1298.0811 - val_loss: 1678.3057 - val_mean_squared_error: 1611.7651\n",
"Epoch 471/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1297.7870 - mean_squared_error: 1297.7870 - val_loss: 1677.9607 - val_mean_squared_error: 1611.4297\n",
"Epoch 472/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1297.4928 - mean_squared_error: 1297.4928 - val_loss: 1677.6155 - val_mean_squared_error: 1611.0940\n",
"Epoch 473/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1297.1985 - mean_squared_error: 1297.1985 - val_loss: 1677.2701 - val_mean_squared_error: 1610.7582\n",
"Epoch 474/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1296.9042 - mean_squared_error: 1296.9042 - val_loss: 1676.9248 - val_mean_squared_error: 1610.4224\n",
"Epoch 475/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1296.6099 - mean_squared_error: 1296.6099 - val_loss: 1676.5793 - val_mean_squared_error: 1610.0864\n",
"Epoch 476/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1296.3153 - mean_squared_error: 1296.3153 - val_loss: 1676.2335 - val_mean_squared_error: 1609.7502\n",
"Epoch 477/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1296.0205 - mean_squared_error: 1296.0205 - val_loss: 1675.8878 - val_mean_squared_error: 1609.4141\n",
"Epoch 478/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1295.7260 - mean_squared_error: 1295.7260 - val_loss: 1675.5420 - val_mean_squared_error: 1609.0778\n",
"Epoch 479/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1295.4310 - mean_squared_error: 1295.4310 - val_loss: 1675.1958 - val_mean_squared_error: 1608.7412\n",
"Epoch 480/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1295.1361 - mean_squared_error: 1295.1361 - val_loss: 1674.8499 - val_mean_squared_error: 1608.4047\n",
"Epoch 481/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1294.8411 - mean_squared_error: 1294.8411 - val_loss: 1674.5035 - val_mean_squared_error: 1608.0680\n",
"Epoch 482/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1294.5460 - mean_squared_error: 1294.5460 - val_loss: 1674.1572 - val_mean_squared_error: 1607.7312\n",
"Epoch 483/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1294.2507 - mean_squared_error: 1294.2507 - val_loss: 1673.8108 - val_mean_squared_error: 1607.3943\n",
"Epoch 484/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1293.9554 - mean_squared_error: 1293.9554 - val_loss: 1673.4641 - val_mean_squared_error: 1607.0574\n",
"Epoch 485/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1293.6602 - mean_squared_error: 1293.6602 - val_loss: 1673.1173 - val_mean_squared_error: 1606.7201\n",
"Epoch 486/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1293.3646 - mean_squared_error: 1293.3646 - val_loss: 1672.7705 - val_mean_squared_error: 1606.3829\n",
"Epoch 487/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1293.0690 - mean_squared_error: 1293.0690 - val_loss: 1672.4237 - val_mean_squared_error: 1606.0457\n",
"Epoch 488/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1292.7734 - mean_squared_error: 1292.7734 - val_loss: 1672.0767 - val_mean_squared_error: 1605.7083\n",
"Epoch 489/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1292.4775 - mean_squared_error: 1292.4775 - val_loss: 1671.7296 - val_mean_squared_error: 1605.3708\n",
"Epoch 490/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1292.1819 - mean_squared_error: 1292.1819 - val_loss: 1671.3823 - val_mean_squared_error: 1605.0331\n",
"Epoch 491/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1291.8859 - mean_squared_error: 1291.8859 - val_loss: 1671.0347 - val_mean_squared_error: 1604.6951\n",
"Epoch 492/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1291.5898 - mean_squared_error: 1291.5898 - val_loss: 1670.6874 - val_mean_squared_error: 1604.3574\n",
"Epoch 493/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1291.2938 - mean_squared_error: 1291.2938 - val_loss: 1670.3397 - val_mean_squared_error: 1604.0193\n",
"Epoch 494/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1290.9976 - mean_squared_error: 1290.9976 - val_loss: 1669.9919 - val_mean_squared_error: 1603.6813\n",
"Epoch 495/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1290.7014 - mean_squared_error: 1290.7014 - val_loss: 1669.6442 - val_mean_squared_error: 1603.3430\n",
"Epoch 496/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1290.4050 - mean_squared_error: 1290.4050 - val_loss: 1669.2963 - val_mean_squared_error: 1603.0048\n",
"Epoch 497/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1290.1086 - mean_squared_error: 1290.1086 - val_loss: 1668.9485 - val_mean_squared_error: 1602.6666\n",
"Epoch 498/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1289.8120 - mean_squared_error: 1289.8120 - val_loss: 1668.6002 - val_mean_squared_error: 1602.3279\n",
"Epoch 499/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1289.5154 - mean_squared_error: 1289.5154 - val_loss: 1668.2521 - val_mean_squared_error: 1601.9895\n",
"Epoch 500/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1289.2188 - mean_squared_error: 1289.2188 - val_loss: 1667.9038 - val_mean_squared_error: 1601.6508\n",
"Epoch 501/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1288.9220 - mean_squared_error: 1288.9220 - val_loss: 1667.5554 - val_mean_squared_error: 1601.3121\n",
"Epoch 502/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1288.6252 - mean_squared_error: 1288.6252 - val_loss: 1667.2068 - val_mean_squared_error: 1600.9731\n",
"Epoch 503/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1288.3282 - mean_squared_error: 1288.3282 - val_loss: 1666.8583 - val_mean_squared_error: 1600.6344\n",
"Epoch 504/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1288.0314 - mean_squared_error: 1288.0314 - val_loss: 1666.5095 - val_mean_squared_error: 1600.2952\n",
"Epoch 505/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1287.7343 - mean_squared_error: 1287.7343 - val_loss: 1666.1606 - val_mean_squared_error: 1599.9561\n",
"Epoch 506/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1287.4371 - mean_squared_error: 1287.4371 - val_loss: 1665.8118 - val_mean_squared_error: 1599.6168\n",
"Epoch 507/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1287.1398 - mean_squared_error: 1287.1398 - val_loss: 1665.4629 - val_mean_squared_error: 1599.2776\n",
"Epoch 508/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1286.8425 - mean_squared_error: 1286.8425 - val_loss: 1665.1138 - val_mean_squared_error: 1598.9381\n",
"Epoch 509/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1286.5453 - mean_squared_error: 1286.5453 - val_loss: 1664.7645 - val_mean_squared_error: 1598.5986\n",
"Epoch 510/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1286.2477 - mean_squared_error: 1286.2477 - val_loss: 1664.4152 - val_mean_squared_error: 1598.2590\n",
"Epoch 511/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1285.9501 - mean_squared_error: 1285.9501 - val_loss: 1664.0658 - val_mean_squared_error: 1597.9192\n",
"Epoch 512/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1285.6526 - mean_squared_error: 1285.6526 - val_loss: 1663.7163 - val_mean_squared_error: 1597.5793\n",
"Epoch 513/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1285.3550 - mean_squared_error: 1285.3550 - val_loss: 1663.3667 - val_mean_squared_error: 1597.2395\n",
"Epoch 514/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1285.0571 - mean_squared_error: 1285.0571 - val_loss: 1663.0170 - val_mean_squared_error: 1596.8994\n",
"Epoch 515/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1284.7592 - mean_squared_error: 1284.7592 - val_loss: 1662.6672 - val_mean_squared_error: 1596.5593\n",
"Epoch 516/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1284.4613 - mean_squared_error: 1284.4613 - val_loss: 1662.3174 - val_mean_squared_error: 1596.2195\n",
"Epoch 517/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1284.1636 - mean_squared_error: 1284.1636 - val_loss: 1661.9675 - val_mean_squared_error: 1595.8792\n",
"Epoch 518/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1283.8655 - mean_squared_error: 1283.8655 - val_loss: 1661.6176 - val_mean_squared_error: 1595.5388\n",
"Epoch 519/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1283.5674 - mean_squared_error: 1283.5674 - val_loss: 1661.2673 - val_mean_squared_error: 1595.1985\n",
"Epoch 520/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1283.2693 - mean_squared_error: 1283.2693 - val_loss: 1660.9172 - val_mean_squared_error: 1594.8580\n",
"Epoch 521/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1282.9709 - mean_squared_error: 1282.9709 - val_loss: 1660.5669 - val_mean_squared_error: 1594.5173\n",
"Epoch 522/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1282.6726 - mean_squared_error: 1282.6726 - val_loss: 1660.2163 - val_mean_squared_error: 1594.1766\n",
"Epoch 523/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1282.3743 - mean_squared_error: 1282.3743 - val_loss: 1659.8660 - val_mean_squared_error: 1593.8359\n",
"Epoch 524/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1282.0758 - mean_squared_error: 1282.0758 - val_loss: 1659.5156 - val_mean_squared_error: 1593.4954\n",
"Epoch 525/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1281.7772 - mean_squared_error: 1281.7772 - val_loss: 1659.1650 - val_mean_squared_error: 1593.1545\n",
"Epoch 526/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1281.4788 - mean_squared_error: 1281.4788 - val_loss: 1658.8142 - val_mean_squared_error: 1592.8134\n",
"Epoch 527/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1281.1801 - mean_squared_error: 1281.1801 - val_loss: 1658.4633 - val_mean_squared_error: 1592.4723\n",
"Epoch 528/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1280.8815 - mean_squared_error: 1280.8815 - val_loss: 1658.1125 - val_mean_squared_error: 1592.1313\n",
"Epoch 529/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1280.5826 - mean_squared_error: 1280.5826 - val_loss: 1657.7615 - val_mean_squared_error: 1591.7898\n",
"Epoch 530/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1280.2838 - mean_squared_error: 1280.2838 - val_loss: 1657.4104 - val_mean_squared_error: 1591.4486\n",
"Epoch 531/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1279.9849 - mean_squared_error: 1279.9849 - val_loss: 1657.0593 - val_mean_squared_error: 1591.1074\n",
"Epoch 532/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1279.6859 - mean_squared_error: 1279.6859 - val_loss: 1656.7083 - val_mean_squared_error: 1590.7660\n",
"Epoch 533/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1279.3868 - mean_squared_error: 1279.3868 - val_loss: 1656.3569 - val_mean_squared_error: 1590.4244\n",
"Epoch 534/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1279.0878 - mean_squared_error: 1279.0878 - val_loss: 1656.0055 - val_mean_squared_error: 1590.0828\n",
"Epoch 535/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1278.7886 - mean_squared_error: 1278.7886 - val_loss: 1655.6541 - val_mean_squared_error: 1589.7410\n",
"Epoch 536/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1278.4895 - mean_squared_error: 1278.4895 - val_loss: 1655.3025 - val_mean_squared_error: 1589.3993\n",
"Epoch 537/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1278.1902 - mean_squared_error: 1278.1902 - val_loss: 1654.9509 - val_mean_squared_error: 1589.0576\n",
"Epoch 538/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1277.8909 - mean_squared_error: 1277.8909 - val_loss: 1654.5992 - val_mean_squared_error: 1588.7156\n",
"Epoch 539/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1277.5916 - mean_squared_error: 1277.5916 - val_loss: 1654.2476 - val_mean_squared_error: 1588.3737\n",
"Epoch 540/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1277.2920 - mean_squared_error: 1277.2920 - val_loss: 1653.8956 - val_mean_squared_error: 1588.0316\n",
"Epoch 541/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1276.9926 - mean_squared_error: 1276.9926 - val_loss: 1653.5439 - val_mean_squared_error: 1587.6897\n",
"Epoch 542/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1276.6930 - mean_squared_error: 1276.6930 - val_loss: 1653.1919 - val_mean_squared_error: 1587.3474\n",
"Epoch 543/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1276.3933 - mean_squared_error: 1276.3933 - val_loss: 1652.8397 - val_mean_squared_error: 1587.0051\n",
"Epoch 544/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1276.0936 - mean_squared_error: 1276.0936 - val_loss: 1652.4877 - val_mean_squared_error: 1586.6628\n",
"Epoch 545/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1275.7941 - mean_squared_error: 1275.7941 - val_loss: 1652.1355 - val_mean_squared_error: 1586.3206\n",
"Epoch 546/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1275.4941 - mean_squared_error: 1275.4941 - val_loss: 1651.7832 - val_mean_squared_error: 1585.9779\n",
"Epoch 547/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1275.1943 - mean_squared_error: 1275.1943 - val_loss: 1651.4308 - val_mean_squared_error: 1585.6354\n",
"Epoch 548/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1274.8945 - mean_squared_error: 1274.8945 - val_loss: 1651.0785 - val_mean_squared_error: 1585.2928\n",
"Epoch 549/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1274.5945 - mean_squared_error: 1274.5945 - val_loss: 1650.7258 - val_mean_squared_error: 1584.9500\n",
"Epoch 550/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1274.2944 - mean_squared_error: 1274.2944 - val_loss: 1650.3733 - val_mean_squared_error: 1584.6073\n",
"Epoch 551/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1273.9944 - mean_squared_error: 1273.9944 - val_loss: 1650.0208 - val_mean_squared_error: 1584.2646\n",
"Epoch 552/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1273.6943 - mean_squared_error: 1273.6943 - val_loss: 1649.6680 - val_mean_squared_error: 1583.9216\n",
"Epoch 553/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1273.3942 - mean_squared_error: 1273.3942 - val_loss: 1649.3152 - val_mean_squared_error: 1583.5787\n",
"Epoch 554/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1273.0940 - mean_squared_error: 1273.0940 - val_loss: 1648.9626 - val_mean_squared_error: 1583.2360\n",
"Epoch 555/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1272.7937 - mean_squared_error: 1272.7937 - val_loss: 1648.6096 - val_mean_squared_error: 1582.8928\n",
"Epoch 556/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1272.4935 - mean_squared_error: 1272.4935 - val_loss: 1648.2566 - val_mean_squared_error: 1582.5496\n",
"Epoch 557/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1272.1931 - mean_squared_error: 1272.1931 - val_loss: 1647.9036 - val_mean_squared_error: 1582.2064\n",
"Epoch 558/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1271.8927 - mean_squared_error: 1271.8927 - val_loss: 1647.5505 - val_mean_squared_error: 1581.8633\n",
"Epoch 559/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1271.5923 - mean_squared_error: 1271.5923 - val_loss: 1647.1974 - val_mean_squared_error: 1581.5199\n",
"Epoch 560/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1271.2917 - mean_squared_error: 1271.2917 - val_loss: 1646.8441 - val_mean_squared_error: 1581.1765\n",
"Epoch 561/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1270.9912 - mean_squared_error: 1270.9912 - val_loss: 1646.4908 - val_mean_squared_error: 1580.8331\n",
"Epoch 562/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1270.6906 - mean_squared_error: 1270.6906 - val_loss: 1646.1375 - val_mean_squared_error: 1580.4896\n",
"Epoch 563/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1270.3899 - mean_squared_error: 1270.3899 - val_loss: 1645.7842 - val_mean_squared_error: 1580.1461\n",
"Epoch 564/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1270.0892 - mean_squared_error: 1270.0892 - val_loss: 1645.4307 - val_mean_squared_error: 1579.8025\n",
"Epoch 565/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1269.7885 - mean_squared_error: 1269.7885 - val_loss: 1645.0771 - val_mean_squared_error: 1579.4589\n",
"Epoch 566/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1269.4877 - mean_squared_error: 1269.4877 - val_loss: 1644.7234 - val_mean_squared_error: 1579.1150\n",
"Epoch 567/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1269.1869 - mean_squared_error: 1269.1869 - val_loss: 1644.3699 - val_mean_squared_error: 1578.7712\n",
"Epoch 568/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1268.8860 - mean_squared_error: 1268.8860 - val_loss: 1644.0162 - val_mean_squared_error: 1578.4275\n",
"Epoch 569/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1268.5851 - mean_squared_error: 1268.5851 - val_loss: 1643.6625 - val_mean_squared_error: 1578.0837\n",
"Epoch 570/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1268.2841 - mean_squared_error: 1268.2841 - val_loss: 1643.3088 - val_mean_squared_error: 1577.7399\n",
"Epoch 571/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1267.9830 - mean_squared_error: 1267.9830 - val_loss: 1642.9546 - val_mean_squared_error: 1577.3955\n",
"Epoch 572/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1267.6819 - mean_squared_error: 1267.6819 - val_loss: 1642.6006 - val_mean_squared_error: 1577.0515\n",
"Epoch 573/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1267.3809 - mean_squared_error: 1267.3809 - val_loss: 1642.2468 - val_mean_squared_error: 1576.7075\n",
"Epoch 574/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1267.0798 - mean_squared_error: 1267.0798 - val_loss: 1641.8926 - val_mean_squared_error: 1576.3633\n",
"Epoch 575/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1266.7786 - mean_squared_error: 1266.7786 - val_loss: 1641.5386 - val_mean_squared_error: 1576.0192\n",
"Epoch 576/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1266.4773 - mean_squared_error: 1266.4773 - val_loss: 1641.1846 - val_mean_squared_error: 1575.6750\n",
"Epoch 577/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1266.1761 - mean_squared_error: 1266.1761 - val_loss: 1640.8301 - val_mean_squared_error: 1575.3304\n",
"Epoch 578/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1265.8748 - mean_squared_error: 1265.8748 - val_loss: 1640.4761 - val_mean_squared_error: 1574.9863\n",
"Epoch 579/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1265.5736 - mean_squared_error: 1265.5736 - val_loss: 1640.1217 - val_mean_squared_error: 1574.6418\n",
"Epoch 580/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1265.2722 - mean_squared_error: 1265.2722 - val_loss: 1639.7673 - val_mean_squared_error: 1574.2972\n",
"Epoch 581/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1264.9707 - mean_squared_error: 1264.9707 - val_loss: 1639.4128 - val_mean_squared_error: 1573.9529\n",
"Epoch 582/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1264.6693 - mean_squared_error: 1264.6693 - val_loss: 1639.0585 - val_mean_squared_error: 1573.6083\n",
"Epoch 583/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1264.3679 - mean_squared_error: 1264.3679 - val_loss: 1638.7039 - val_mean_squared_error: 1573.2635\n",
"Epoch 584/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1264.0663 - mean_squared_error: 1264.0663 - val_loss: 1638.3494 - val_mean_squared_error: 1572.9191\n",
"Epoch 585/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1263.7649 - mean_squared_error: 1263.7649 - val_loss: 1637.9949 - val_mean_squared_error: 1572.5745\n",
"Epoch 586/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1263.4633 - mean_squared_error: 1263.4633 - val_loss: 1637.6400 - val_mean_squared_error: 1572.2295\n",
"Epoch 587/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1263.1615 - mean_squared_error: 1263.1615 - val_loss: 1637.2852 - val_mean_squared_error: 1571.8845\n",
"Epoch 588/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1262.8597 - mean_squared_error: 1262.8597 - val_loss: 1636.9304 - val_mean_squared_error: 1571.5398\n",
"Epoch 589/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1262.5582 - mean_squared_error: 1262.5582 - val_loss: 1636.5756 - val_mean_squared_error: 1571.1948\n",
"Epoch 590/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1262.2562 - mean_squared_error: 1262.2562 - val_loss: 1636.2205 - val_mean_squared_error: 1570.8499\n",
"Epoch 591/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1261.9545 - mean_squared_error: 1261.9545 - val_loss: 1635.8658 - val_mean_squared_error: 1570.5051\n",
"Epoch 592/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1261.6527 - mean_squared_error: 1261.6527 - val_loss: 1635.5107 - val_mean_squared_error: 1570.1598\n",
"Epoch 593/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1261.3510 - mean_squared_error: 1261.3510 - val_loss: 1635.1558 - val_mean_squared_error: 1569.8148\n",
"Epoch 594/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1261.0491 - mean_squared_error: 1261.0491 - val_loss: 1634.8008 - val_mean_squared_error: 1569.4697\n",
"Epoch 595/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1260.7472 - mean_squared_error: 1260.7472 - val_loss: 1634.4457 - val_mean_squared_error: 1569.1246\n",
"Epoch 596/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1260.4453 - mean_squared_error: 1260.4453 - val_loss: 1634.0906 - val_mean_squared_error: 1568.7794\n",
"Epoch 597/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1260.1433 - mean_squared_error: 1260.1433 - val_loss: 1633.7354 - val_mean_squared_error: 1568.4342\n",
"Epoch 598/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1259.8413 - mean_squared_error: 1259.8413 - val_loss: 1633.3800 - val_mean_squared_error: 1568.0887\n",
"Epoch 599/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1259.5393 - mean_squared_error: 1259.5393 - val_loss: 1633.0247 - val_mean_squared_error: 1567.7434\n",
"Epoch 600/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1259.2373 - mean_squared_error: 1259.2373 - val_loss: 1632.6694 - val_mean_squared_error: 1567.3981\n",
"Epoch 601/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1258.9352 - mean_squared_error: 1258.9352 - val_loss: 1632.3141 - val_mean_squared_error: 1567.0527\n",
"Epoch 602/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1258.6331 - mean_squared_error: 1258.6331 - val_loss: 1631.9586 - val_mean_squared_error: 1566.7073\n",
"Epoch 603/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1258.3308 - mean_squared_error: 1258.3308 - val_loss: 1631.6030 - val_mean_squared_error: 1566.3617\n",
"Epoch 604/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1258.0286 - mean_squared_error: 1258.0286 - val_loss: 1631.2476 - val_mean_squared_error: 1566.0162\n",
"Epoch 605/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1257.7263 - mean_squared_error: 1257.7263 - val_loss: 1630.8918 - val_mean_squared_error: 1565.6703\n",
"Epoch 606/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1257.4241 - mean_squared_error: 1257.4241 - val_loss: 1630.5364 - val_mean_squared_error: 1565.3248\n",
"Epoch 607/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1257.1217 - mean_squared_error: 1257.1217 - val_loss: 1630.1807 - val_mean_squared_error: 1564.9791\n",
"Epoch 608/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1256.8196 - mean_squared_error: 1256.8196 - val_loss: 1629.8250 - val_mean_squared_error: 1564.6334\n",
"Epoch 609/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1256.5171 - mean_squared_error: 1256.5171 - val_loss: 1629.4692 - val_mean_squared_error: 1564.2877\n",
"Epoch 610/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1256.2147 - mean_squared_error: 1256.2147 - val_loss: 1629.1135 - val_mean_squared_error: 1563.9420\n",
"Epoch 611/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1255.9125 - mean_squared_error: 1255.9125 - val_loss: 1628.7577 - val_mean_squared_error: 1563.5961\n",
"Epoch 612/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1255.6100 - mean_squared_error: 1255.6100 - val_loss: 1628.4020 - val_mean_squared_error: 1563.2504\n",
"Epoch 613/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1255.3074 - mean_squared_error: 1255.3074 - val_loss: 1628.0461 - val_mean_squared_error: 1562.9045\n",
"Epoch 614/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1255.0049 - mean_squared_error: 1255.0049 - val_loss: 1627.6899 - val_mean_squared_error: 1562.5583\n",
"Epoch 615/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1254.7024 - mean_squared_error: 1254.7024 - val_loss: 1627.3342 - val_mean_squared_error: 1562.2125\n",
"Epoch 616/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1254.4000 - mean_squared_error: 1254.4000 - val_loss: 1626.9781 - val_mean_squared_error: 1561.8665\n",
"Epoch 617/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1254.0973 - mean_squared_error: 1254.0973 - val_loss: 1626.6221 - val_mean_squared_error: 1561.5203\n",
"Epoch 618/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1253.7948 - mean_squared_error: 1253.7948 - val_loss: 1626.2661 - val_mean_squared_error: 1561.1744\n",
"Epoch 619/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1253.4923 - mean_squared_error: 1253.4923 - val_loss: 1625.9099 - val_mean_squared_error: 1560.8284\n",
"Epoch 620/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1253.1897 - mean_squared_error: 1253.1897 - val_loss: 1625.5538 - val_mean_squared_error: 1560.4822\n",
"Epoch 621/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1252.8870 - mean_squared_error: 1252.8870 - val_loss: 1625.1975 - val_mean_squared_error: 1560.1360\n",
"Epoch 622/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1252.5842 - mean_squared_error: 1252.5842 - val_loss: 1624.8413 - val_mean_squared_error: 1559.7898\n",
"Epoch 623/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1252.2815 - mean_squared_error: 1252.2815 - val_loss: 1624.4851 - val_mean_squared_error: 1559.4436\n",
"Epoch 624/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1251.9789 - mean_squared_error: 1251.9789 - val_loss: 1624.1289 - val_mean_squared_error: 1559.0974\n",
"Epoch 625/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1251.6761 - mean_squared_error: 1251.6761 - val_loss: 1623.7725 - val_mean_squared_error: 1558.7510\n",
"Epoch 626/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1251.3734 - mean_squared_error: 1251.3734 - val_loss: 1623.4163 - val_mean_squared_error: 1558.4047\n",
"Epoch 627/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1251.0706 - mean_squared_error: 1251.0706 - val_loss: 1623.0598 - val_mean_squared_error: 1558.0582\n",
"Epoch 628/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1250.7678 - mean_squared_error: 1250.7678 - val_loss: 1622.7034 - val_mean_squared_error: 1557.7119\n",
"Epoch 629/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1250.4650 - mean_squared_error: 1250.4650 - val_loss: 1622.3470 - val_mean_squared_error: 1557.3655\n",
"Epoch 630/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1250.1621 - mean_squared_error: 1250.1621 - val_loss: 1621.9906 - val_mean_squared_error: 1557.0192\n",
"Epoch 631/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1249.8594 - mean_squared_error: 1249.8594 - val_loss: 1621.6340 - val_mean_squared_error: 1556.6726\n",
"Epoch 632/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1249.5564 - mean_squared_error: 1249.5564 - val_loss: 1621.2773 - val_mean_squared_error: 1556.3259\n",
"Epoch 633/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1249.2535 - mean_squared_error: 1249.2535 - val_loss: 1620.9210 - val_mean_squared_error: 1555.9796\n",
"Epoch 634/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1248.9506 - mean_squared_error: 1248.9506 - val_loss: 1620.5645 - val_mean_squared_error: 1555.6331\n",
"Epoch 635/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1248.6477 - mean_squared_error: 1248.6477 - val_loss: 1620.2078 - val_mean_squared_error: 1555.2865\n",
"Epoch 636/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1248.3447 - mean_squared_error: 1248.3447 - val_loss: 1619.8511 - val_mean_squared_error: 1554.9398\n",
"Epoch 637/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1248.0417 - mean_squared_error: 1248.0417 - val_loss: 1619.4945 - val_mean_squared_error: 1554.5931\n",
"Epoch 638/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1247.7388 - mean_squared_error: 1247.7388 - val_loss: 1619.1378 - val_mean_squared_error: 1554.2467\n",
"Epoch 639/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1247.4358 - mean_squared_error: 1247.4358 - val_loss: 1618.7810 - val_mean_squared_error: 1553.8998\n",
"Epoch 640/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1247.1326 - mean_squared_error: 1247.1326 - val_loss: 1618.4243 - val_mean_squared_error: 1553.5532\n",
"Epoch 641/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1246.8298 - mean_squared_error: 1246.8298 - val_loss: 1618.0675 - val_mean_squared_error: 1553.2063\n",
"Epoch 642/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1246.5266 - mean_squared_error: 1246.5266 - val_loss: 1617.7107 - val_mean_squared_error: 1552.8596\n",
"Epoch 643/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1246.2235 - mean_squared_error: 1246.2235 - val_loss: 1617.3538 - val_mean_squared_error: 1552.5129\n",
"Epoch 644/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1245.9205 - mean_squared_error: 1245.9205 - val_loss: 1616.9968 - val_mean_squared_error: 1552.1659\n",
"Epoch 645/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1245.6174 - mean_squared_error: 1245.6174 - val_loss: 1616.6400 - val_mean_squared_error: 1551.8191\n",
"Epoch 646/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1245.3142 - mean_squared_error: 1245.3142 - val_loss: 1616.2832 - val_mean_squared_error: 1551.4724\n",
"Epoch 647/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1245.0111 - mean_squared_error: 1245.0111 - val_loss: 1615.9263 - val_mean_squared_error: 1551.1256\n",
"Epoch 648/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1244.7080 - mean_squared_error: 1244.7080 - val_loss: 1615.5695 - val_mean_squared_error: 1550.7787\n",
"Epoch 649/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1244.4048 - mean_squared_error: 1244.4048 - val_loss: 1615.2123 - val_mean_squared_error: 1550.4316\n",
"Epoch 650/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1244.1016 - mean_squared_error: 1244.1016 - val_loss: 1614.8552 - val_mean_squared_error: 1550.0847\n",
"Epoch 651/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1243.7985 - mean_squared_error: 1243.7985 - val_loss: 1614.4980 - val_mean_squared_error: 1549.7375\n",
"Epoch 652/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1243.4954 - mean_squared_error: 1243.4954 - val_loss: 1614.1411 - val_mean_squared_error: 1549.3907\n",
"Epoch 653/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1243.1921 - mean_squared_error: 1243.1921 - val_loss: 1613.7842 - val_mean_squared_error: 1549.0437\n",
"Epoch 654/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1242.8889 - mean_squared_error: 1242.8889 - val_loss: 1613.4270 - val_mean_squared_error: 1548.6967\n",
"Epoch 655/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1242.5856 - mean_squared_error: 1242.5856 - val_loss: 1613.0698 - val_mean_squared_error: 1548.3497\n",
"Epoch 656/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1242.2823 - mean_squared_error: 1242.2823 - val_loss: 1612.7128 - val_mean_squared_error: 1548.0027\n",
"Epoch 657/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1241.9791 - mean_squared_error: 1241.9791 - val_loss: 1612.3555 - val_mean_squared_error: 1547.6554\n",
"Epoch 658/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1241.6758 - mean_squared_error: 1241.6758 - val_loss: 1611.9985 - val_mean_squared_error: 1547.3085\n",
"Epoch 659/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1241.3724 - mean_squared_error: 1241.3724 - val_loss: 1611.6411 - val_mean_squared_error: 1546.9612\n",
"Epoch 660/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1241.0691 - mean_squared_error: 1241.0691 - val_loss: 1611.2839 - val_mean_squared_error: 1546.6141\n",
"Epoch 661/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1240.7659 - mean_squared_error: 1240.7659 - val_loss: 1610.9268 - val_mean_squared_error: 1546.2670\n",
"Epoch 662/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1240.4625 - mean_squared_error: 1240.4625 - val_loss: 1610.5693 - val_mean_squared_error: 1545.9197\n",
"Epoch 663/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1240.1592 - mean_squared_error: 1240.1592 - val_loss: 1610.2120 - val_mean_squared_error: 1545.5725\n",
"Epoch 664/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1239.8558 - mean_squared_error: 1239.8558 - val_loss: 1609.8547 - val_mean_squared_error: 1545.2252\n",
"Epoch 665/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1239.5525 - mean_squared_error: 1239.5525 - val_loss: 1609.4973 - val_mean_squared_error: 1544.8781\n",
"Epoch 666/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1239.2490 - mean_squared_error: 1239.2490 - val_loss: 1609.1401 - val_mean_squared_error: 1544.5309\n",
"Epoch 667/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1238.9457 - mean_squared_error: 1238.9457 - val_loss: 1608.7827 - val_mean_squared_error: 1544.1836\n",
"Epoch 668/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1238.6423 - mean_squared_error: 1238.6423 - val_loss: 1608.4253 - val_mean_squared_error: 1543.8362\n",
"Epoch 669/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1238.3389 - mean_squared_error: 1238.3389 - val_loss: 1608.0679 - val_mean_squared_error: 1543.4890\n",
"Epoch 670/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1238.0356 - mean_squared_error: 1238.0356 - val_loss: 1607.7104 - val_mean_squared_error: 1543.1416\n",
"Epoch 671/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1237.7322 - mean_squared_error: 1237.7322 - val_loss: 1607.3531 - val_mean_squared_error: 1542.7943\n",
"Epoch 672/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1237.4288 - mean_squared_error: 1237.4288 - val_loss: 1606.9956 - val_mean_squared_error: 1542.4470\n",
"Epoch 673/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1237.1254 - mean_squared_error: 1237.1254 - val_loss: 1606.6382 - val_mean_squared_error: 1542.0996\n",
"Epoch 674/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1236.8220 - mean_squared_error: 1236.8220 - val_loss: 1606.2808 - val_mean_squared_error: 1541.7523\n",
"Epoch 675/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1236.5186 - mean_squared_error: 1236.5186 - val_loss: 1605.9232 - val_mean_squared_error: 1541.4049\n",
"Epoch 676/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1236.2151 - mean_squared_error: 1236.2151 - val_loss: 1605.5657 - val_mean_squared_error: 1541.0574\n",
"Epoch 677/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1235.9116 - mean_squared_error: 1235.9116 - val_loss: 1605.2083 - val_mean_squared_error: 1540.7101\n",
"Epoch 678/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1235.6082 - mean_squared_error: 1235.6082 - val_loss: 1604.8506 - val_mean_squared_error: 1540.3625\n",
"Epoch 679/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1235.3047 - mean_squared_error: 1235.3047 - val_loss: 1604.4929 - val_mean_squared_error: 1540.0151\n",
"Epoch 680/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1235.0013 - mean_squared_error: 1235.0013 - val_loss: 1604.1355 - val_mean_squared_error: 1539.6677\n",
"Epoch 681/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1234.6979 - mean_squared_error: 1234.6979 - val_loss: 1603.7781 - val_mean_squared_error: 1539.3204\n",
"Epoch 682/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1234.3944 - mean_squared_error: 1234.3944 - val_loss: 1603.4203 - val_mean_squared_error: 1538.9729\n",
"Epoch 683/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1234.0909 - mean_squared_error: 1234.0909 - val_loss: 1603.0627 - val_mean_squared_error: 1538.6252\n",
"Epoch 684/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1233.7875 - mean_squared_error: 1233.7875 - val_loss: 1602.7052 - val_mean_squared_error: 1538.2780\n",
"Epoch 685/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1233.4840 - mean_squared_error: 1233.4840 - val_loss: 1602.3475 - val_mean_squared_error: 1537.9304\n",
"Epoch 686/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1233.1804 - mean_squared_error: 1233.1804 - val_loss: 1601.9900 - val_mean_squared_error: 1537.5830\n",
"Epoch 687/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1232.8771 - mean_squared_error: 1232.8771 - val_loss: 1601.6322 - val_mean_squared_error: 1537.2354\n",
"Epoch 688/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1232.5735 - mean_squared_error: 1232.5735 - val_loss: 1601.2744 - val_mean_squared_error: 1536.8877\n",
"Epoch 689/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1232.2701 - mean_squared_error: 1232.2701 - val_loss: 1600.9169 - val_mean_squared_error: 1536.5403\n",
"Epoch 690/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1231.9667 - mean_squared_error: 1231.9667 - val_loss: 1600.5590 - val_mean_squared_error: 1536.1925\n",
"Epoch 691/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1231.6631 - mean_squared_error: 1231.6631 - val_loss: 1600.2014 - val_mean_squared_error: 1535.8450\n",
"Epoch 692/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1231.3596 - mean_squared_error: 1231.3596 - val_loss: 1599.8438 - val_mean_squared_error: 1535.4976\n",
"Epoch 693/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1231.0562 - mean_squared_error: 1231.0562 - val_loss: 1599.4861 - val_mean_squared_error: 1535.1500\n",
"Epoch 694/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1230.7526 - mean_squared_error: 1230.7526 - val_loss: 1599.1284 - val_mean_squared_error: 1534.8025\n",
"Epoch 695/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1230.4490 - mean_squared_error: 1230.4490 - val_loss: 1598.7706 - val_mean_squared_error: 1534.4548\n",
"Epoch 696/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1230.1455 - mean_squared_error: 1230.1455 - val_loss: 1598.4128 - val_mean_squared_error: 1534.1072\n",
"Epoch 697/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1229.8422 - mean_squared_error: 1229.8422 - val_loss: 1598.0552 - val_mean_squared_error: 1533.7596\n",
"Epoch 698/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1229.5387 - mean_squared_error: 1229.5387 - val_loss: 1597.6975 - val_mean_squared_error: 1533.4121\n",
"Epoch 699/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1229.2351 - mean_squared_error: 1229.2351 - val_loss: 1597.3396 - val_mean_squared_error: 1533.0643\n",
"Epoch 700/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1228.9315 - mean_squared_error: 1228.9315 - val_loss: 1596.9817 - val_mean_squared_error: 1532.7167\n",
"Epoch 701/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1228.6282 - mean_squared_error: 1228.6282 - val_loss: 1596.6240 - val_mean_squared_error: 1532.3691\n",
"Epoch 702/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1228.3246 - mean_squared_error: 1228.3246 - val_loss: 1596.2661 - val_mean_squared_error: 1532.0215\n",
"Epoch 703/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1228.0211 - mean_squared_error: 1228.0211 - val_loss: 1595.9084 - val_mean_squared_error: 1531.6740\n",
"Epoch 704/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1227.7175 - mean_squared_error: 1227.7175 - val_loss: 1595.5505 - val_mean_squared_error: 1531.3262\n",
"Epoch 705/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1227.4141 - mean_squared_error: 1227.4141 - val_loss: 1595.1929 - val_mean_squared_error: 1530.9785\n",
"Epoch 706/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1227.1106 - mean_squared_error: 1227.1106 - val_loss: 1594.8350 - val_mean_squared_error: 1530.6307\n",
"Epoch 707/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1226.8073 - mean_squared_error: 1226.8073 - val_loss: 1594.4771 - val_mean_squared_error: 1530.2830\n",
"Epoch 708/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1226.5037 - mean_squared_error: 1226.5037 - val_loss: 1594.1193 - val_mean_squared_error: 1529.9354\n",
"Epoch 709/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1226.2002 - mean_squared_error: 1226.2002 - val_loss: 1593.7617 - val_mean_squared_error: 1529.5880\n",
"Epoch 710/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1225.8967 - mean_squared_error: 1225.8967 - val_loss: 1593.4037 - val_mean_squared_error: 1529.2402\n",
"Epoch 711/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1225.5931 - mean_squared_error: 1225.5931 - val_loss: 1593.0459 - val_mean_squared_error: 1528.8926\n",
"Epoch 712/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1225.2897 - mean_squared_error: 1225.2897 - val_loss: 1592.6880 - val_mean_squared_error: 1528.5448\n",
"Epoch 713/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1224.9861 - mean_squared_error: 1224.9861 - val_loss: 1592.3301 - val_mean_squared_error: 1528.1970\n",
"Epoch 714/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1224.6827 - mean_squared_error: 1224.6827 - val_loss: 1591.9723 - val_mean_squared_error: 1527.8494\n",
"Epoch 715/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1224.3793 - mean_squared_error: 1224.3793 - val_loss: 1591.6144 - val_mean_squared_error: 1527.5017\n",
"Epoch 716/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1224.0758 - mean_squared_error: 1224.0758 - val_loss: 1591.2566 - val_mean_squared_error: 1527.1541\n",
"Epoch 717/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1223.7723 - mean_squared_error: 1223.7723 - val_loss: 1590.8987 - val_mean_squared_error: 1526.8064\n",
"Epoch 718/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1223.4688 - mean_squared_error: 1223.4688 - val_loss: 1590.5409 - val_mean_squared_error: 1526.4587\n",
"Epoch 719/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1223.1654 - mean_squared_error: 1223.1654 - val_loss: 1590.1829 - val_mean_squared_error: 1526.1110\n",
"Epoch 720/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1222.8619 - mean_squared_error: 1222.8619 - val_loss: 1589.8252 - val_mean_squared_error: 1525.7634\n",
"Epoch 721/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1222.5586 - mean_squared_error: 1222.5586 - val_loss: 1589.4672 - val_mean_squared_error: 1525.4155\n",
"Epoch 722/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1222.2551 - mean_squared_error: 1222.2551 - val_loss: 1589.1095 - val_mean_squared_error: 1525.0681\n",
"Epoch 723/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1221.9518 - mean_squared_error: 1221.9518 - val_loss: 1588.7515 - val_mean_squared_error: 1524.7202\n",
"Epoch 724/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1221.6483 - mean_squared_error: 1221.6483 - val_loss: 1588.3936 - val_mean_squared_error: 1524.3724\n",
"Epoch 725/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1221.3448 - mean_squared_error: 1221.3448 - val_loss: 1588.0356 - val_mean_squared_error: 1524.0248\n",
"Epoch 726/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1221.0414 - mean_squared_error: 1221.0414 - val_loss: 1587.6779 - val_mean_squared_error: 1523.6771\n",
"Epoch 727/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1220.7380 - mean_squared_error: 1220.7380 - val_loss: 1587.3201 - val_mean_squared_error: 1523.3295\n",
"Epoch 728/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1220.4347 - mean_squared_error: 1220.4347 - val_loss: 1586.9622 - val_mean_squared_error: 1522.9818\n",
"Epoch 729/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1220.1313 - mean_squared_error: 1220.1313 - val_loss: 1586.6042 - val_mean_squared_error: 1522.6342\n",
"Epoch 730/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1219.8279 - mean_squared_error: 1219.8279 - val_loss: 1586.2466 - val_mean_squared_error: 1522.2865\n",
"Epoch 731/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1219.5245 - mean_squared_error: 1219.5245 - val_loss: 1585.8884 - val_mean_squared_error: 1521.9387\n",
"Epoch 732/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1219.2212 - mean_squared_error: 1219.2212 - val_loss: 1585.5308 - val_mean_squared_error: 1521.5912\n",
"Epoch 733/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1218.9178 - mean_squared_error: 1218.9178 - val_loss: 1585.1727 - val_mean_squared_error: 1521.2434\n",
"Epoch 734/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1218.6144 - mean_squared_error: 1218.6144 - val_loss: 1584.8149 - val_mean_squared_error: 1520.8958\n",
"Epoch 735/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1218.3112 - mean_squared_error: 1218.3112 - val_loss: 1584.4570 - val_mean_squared_error: 1520.5481\n",
"Epoch 736/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1218.0077 - mean_squared_error: 1218.0077 - val_loss: 1584.0992 - val_mean_squared_error: 1520.2004\n",
"Epoch 737/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1217.7043 - mean_squared_error: 1217.7043 - val_loss: 1583.7413 - val_mean_squared_error: 1519.8528\n",
"Epoch 738/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1217.4011 - mean_squared_error: 1217.4011 - val_loss: 1583.3835 - val_mean_squared_error: 1519.5051\n",
"Epoch 739/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1217.0977 - mean_squared_error: 1217.0977 - val_loss: 1583.0256 - val_mean_squared_error: 1519.1575\n",
"Epoch 740/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1216.7944 - mean_squared_error: 1216.7944 - val_loss: 1582.6677 - val_mean_squared_error: 1518.8097\n",
"Epoch 741/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1216.4910 - mean_squared_error: 1216.4910 - val_loss: 1582.3099 - val_mean_squared_error: 1518.4622\n",
"Epoch 742/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1216.1879 - mean_squared_error: 1216.1879 - val_loss: 1581.9519 - val_mean_squared_error: 1518.1145\n",
"Epoch 743/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1215.8845 - mean_squared_error: 1215.8845 - val_loss: 1581.5940 - val_mean_squared_error: 1517.7667\n",
"Epoch 744/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1215.5813 - mean_squared_error: 1215.5813 - val_loss: 1581.2362 - val_mean_squared_error: 1517.4191\n",
"Epoch 745/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1215.2780 - mean_squared_error: 1215.2780 - val_loss: 1580.8784 - val_mean_squared_error: 1517.0714\n",
"Epoch 746/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1214.9749 - mean_squared_error: 1214.9749 - val_loss: 1580.5205 - val_mean_squared_error: 1516.7239\n",
"Epoch 747/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1214.6715 - mean_squared_error: 1214.6715 - val_loss: 1580.1627 - val_mean_squared_error: 1516.3762\n",
"Epoch 748/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1214.3682 - mean_squared_error: 1214.3682 - val_loss: 1579.8049 - val_mean_squared_error: 1516.0286\n",
"Epoch 749/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1214.0651 - mean_squared_error: 1214.0651 - val_loss: 1579.4470 - val_mean_squared_error: 1515.6809\n",
"Epoch 750/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1213.7618 - mean_squared_error: 1213.7618 - val_loss: 1579.0894 - val_mean_squared_error: 1515.3334\n",
"Epoch 751/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1213.4586 - mean_squared_error: 1213.4586 - val_loss: 1578.7313 - val_mean_squared_error: 1514.9856\n",
"Epoch 752/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1213.1555 - mean_squared_error: 1213.1555 - val_loss: 1578.3735 - val_mean_squared_error: 1514.6381\n",
"Epoch 753/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1212.8523 - mean_squared_error: 1212.8523 - val_loss: 1578.0159 - val_mean_squared_error: 1514.2906\n",
"Epoch 754/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1212.5491 - mean_squared_error: 1212.5491 - val_loss: 1577.6580 - val_mean_squared_error: 1513.9430\n",
"Epoch 755/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1212.2460 - mean_squared_error: 1212.2460 - val_loss: 1577.3002 - val_mean_squared_error: 1513.5953\n",
"Epoch 756/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1211.9426 - mean_squared_error: 1211.9426 - val_loss: 1576.9424 - val_mean_squared_error: 1513.2478\n",
"Epoch 757/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1211.6396 - mean_squared_error: 1211.6396 - val_loss: 1576.5847 - val_mean_squared_error: 1512.9003\n",
"Epoch 758/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1211.3365 - mean_squared_error: 1211.3365 - val_loss: 1576.2268 - val_mean_squared_error: 1512.5527\n",
"Epoch 759/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1211.0334 - mean_squared_error: 1211.0334 - val_loss: 1575.8690 - val_mean_squared_error: 1512.2051\n",
"Epoch 760/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1210.7303 - mean_squared_error: 1210.7303 - val_loss: 1575.5111 - val_mean_squared_error: 1511.8574\n",
"Epoch 761/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1210.4272 - mean_squared_error: 1210.4272 - val_loss: 1575.1536 - val_mean_squared_error: 1511.5100\n",
"Epoch 762/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1210.1243 - mean_squared_error: 1210.1243 - val_loss: 1574.7957 - val_mean_squared_error: 1511.1624\n",
"Epoch 763/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1209.8210 - mean_squared_error: 1209.8210 - val_loss: 1574.4380 - val_mean_squared_error: 1510.8151\n",
"Epoch 764/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1209.5181 - mean_squared_error: 1209.5181 - val_loss: 1574.0802 - val_mean_squared_error: 1510.4674\n",
"Epoch 765/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1209.2151 - mean_squared_error: 1209.2151 - val_loss: 1573.7224 - val_mean_squared_error: 1510.1199\n",
"Epoch 766/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1208.9119 - mean_squared_error: 1208.9119 - val_loss: 1573.3647 - val_mean_squared_error: 1509.7725\n",
"Epoch 767/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1208.6090 - mean_squared_error: 1208.6090 - val_loss: 1573.0070 - val_mean_squared_error: 1509.4249\n",
"Epoch 768/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1208.3059 - mean_squared_error: 1208.3059 - val_loss: 1572.6493 - val_mean_squared_error: 1509.0775\n",
"Epoch 769/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1208.0031 - mean_squared_error: 1208.0031 - val_loss: 1572.2915 - val_mean_squared_error: 1508.7300\n",
"Epoch 770/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1207.7000 - mean_squared_error: 1207.7000 - val_loss: 1571.9338 - val_mean_squared_error: 1508.3824\n",
"Epoch 771/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1207.3970 - mean_squared_error: 1207.3970 - val_loss: 1571.5762 - val_mean_squared_error: 1508.0350\n",
"Epoch 772/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1207.0941 - mean_squared_error: 1207.0941 - val_loss: 1571.2185 - val_mean_squared_error: 1507.6877\n",
"Epoch 773/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1206.7913 - mean_squared_error: 1206.7913 - val_loss: 1570.8610 - val_mean_squared_error: 1507.3402\n",
"Epoch 774/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1206.4884 - mean_squared_error: 1206.4884 - val_loss: 1570.5033 - val_mean_squared_error: 1506.9929\n",
"Epoch 775/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1206.1854 - mean_squared_error: 1206.1854 - val_loss: 1570.1456 - val_mean_squared_error: 1506.6455\n",
"Epoch 776/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1205.8826 - mean_squared_error: 1205.8826 - val_loss: 1569.7881 - val_mean_squared_error: 1506.2982\n",
"Epoch 777/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1205.5798 - mean_squared_error: 1205.5798 - val_loss: 1569.4303 - val_mean_squared_error: 1505.9506\n",
"Epoch 778/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1205.2770 - mean_squared_error: 1205.2770 - val_loss: 1569.0728 - val_mean_squared_error: 1505.6033\n",
"Epoch 779/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1204.9741 - mean_squared_error: 1204.9741 - val_loss: 1568.7151 - val_mean_squared_error: 1505.2559\n",
"Epoch 780/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1204.6713 - mean_squared_error: 1204.6713 - val_loss: 1568.3577 - val_mean_squared_error: 1504.9087\n",
"Epoch 781/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1204.3684 - mean_squared_error: 1204.3684 - val_loss: 1568.0000 - val_mean_squared_error: 1504.5613\n",
"Epoch 782/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1204.0657 - mean_squared_error: 1204.0657 - val_loss: 1567.6423 - val_mean_squared_error: 1504.2139\n",
"Epoch 783/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1203.7629 - mean_squared_error: 1203.7629 - val_loss: 1567.2847 - val_mean_squared_error: 1503.8665\n",
"Epoch 784/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1203.4602 - mean_squared_error: 1203.4602 - val_loss: 1566.9272 - val_mean_squared_error: 1503.5193\n",
"Epoch 785/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1203.1575 - mean_squared_error: 1203.1575 - val_loss: 1566.5698 - val_mean_squared_error: 1503.1721\n",
"Epoch 786/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1202.8547 - mean_squared_error: 1202.8547 - val_loss: 1566.2124 - val_mean_squared_error: 1502.8248\n",
"Epoch 787/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1202.5521 - mean_squared_error: 1202.5521 - val_loss: 1565.8547 - val_mean_squared_error: 1502.4775\n",
"Epoch 788/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1202.2494 - mean_squared_error: 1202.2494 - val_loss: 1565.4971 - val_mean_squared_error: 1502.1301\n",
"Epoch 789/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1201.9467 - mean_squared_error: 1201.9467 - val_loss: 1565.1398 - val_mean_squared_error: 1501.7830\n",
"Epoch 790/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1201.6442 - mean_squared_error: 1201.6442 - val_loss: 1564.7822 - val_mean_squared_error: 1501.4358\n",
"Epoch 791/1000\n",
"5/5 [==============================] - 8s 2s/step - loss: 1201.3414 - mean_squared_error: 1201.3414 - val_loss: 1564.4248 - val_mean_squared_error: 1501.0886\n",
"Epoch 792/1000\n",
"5/5 [==============================] - 7s 1s/step - loss: 1201.0388 - mean_squared_error: 1201.0388 - val_loss: 1564.0674 - val_mean_squared_error: 1500.7415\n",
"Epoch 793/1000\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "fc4slEg55o4o",
"colab_type": "code",
"colab": {}
},
"source": [
"test_set = df[df[\"full_path\"] < '02'].sample(100)\n",
"\n",
"from PIL import Image\n",
"images = []\n",
"for img_path in test_set[\"full_path\"]:\n",
" img = Image.open(\"./drive/My Drive/mlin/celebs/imdb/\" + img_path[0]).resize((128, 128)).convert('L')\n",
" images.append(\n",
" np.asarray(img, dtype=\"int32\")\n",
" )\n",
"\n",
"test_imgs = np.array(images)\n",
"\n",
"test_ages = test_set[\"age\"].astype('int').to_numpy()"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "1RTNgpy75fbu",
"colab_type": "code",
"colab": {}
},
"source": [
"regressor.evaluate(x=test_imgs, y=test_ages)"
],
"execution_count": 0,
"outputs": []
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment