Skip to content

Instantly share code, notes, and snippets.

@sanchezcarlosjr

sanchezcarlosjr/signal-processing.ipynb

Last active June 25, 2023 23:57
Show Gist options
  • Save sanchezcarlosjr/2d017462b549ebe3baf7842cf79d1e33 to your computer and use it in GitHub Desktop.
Save sanchezcarlosjr/2d017462b549ebe3baf7842cf79d1e33 to your computer and use it in GitHub Desktop.
Download ZIP
signal-processing.ipynb
Display the source blob
Display the rendered blob
Raw
signal-processing.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"gpuType": "T4",
"authorship_tag": "ABX9TyMaXaVhXbmA/M1AprF/yxz1",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
},
"accelerator": "GPU"
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/sanchezcarlosjr/2d017462b549ebe3baf7842cf79d1e33/signal-processing.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"source": [
"# Curve fitting\n",
"\n",
"$f(x)=2x-1$"
],
"metadata": {
"id": "f8MEDcyDxKBo"
}
},
{
"cell_type": "code",
"source": [
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"\n",
"# Training Set\n",
"x = np.arange(0, 12, 2)\n",
"y = 2*x-1 # In real world, you don't have this. For it serves to illustrate purposes."
],
"metadata": {
"id": "Uz6ogtt-zFzo"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"plt.figure(figsize=(8,6))\n",
"plt.plot(x, y, 'o', label='Original')\n",
"plt.legend()\n",
"plt.show()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 528
},
"id": "3Cxj_mh1zhVr",
"outputId": "927e2d33-6acb-49ef-803f-5d1d54506169"
},
"execution_count": null,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 800x600 with 1 Axes>"
],
"image/png": "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\n"
},
"metadata": {}
}
]
},
{
"cell_type": "markdown",
"source": [
"## Interpolation"
],
"metadata": {
"id": "zjKsym1Zz_vf"
}
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "a8R89U8AxAyK",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 528
},
"outputId": "178b3b9d-1886-4654-cfed-3d2648d44db8"
},
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 800x600 with 1 Axes>"
],
"image/png": "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\n"
},
"metadata": {}
}
],
"source": [
"from scipy import interpolate\n",
"\n",
"model = interpolate.interp1d(x, y, kind='cubic')\n",
"\n",
"plt.figure(figsize=(8,6))\n",
"plt.plot(x, y, 'o', label='Original')\n",
"plt.plot(np.arange(0, 10, 0.01), model(np.arange(0, 10, 0.01)), '-', label='Model')\n",
"plt.legend()\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"source": [
"## Fast Fourier Transform and Inverse Fast Fourier Transform"
],
"metadata": {
"id": "1OybZjWs0KFx"
}
},
{
"cell_type": "code",
"source": [
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"\n",
"plt.figure(figsize=(8,6))\n",
"plt.plot(x, y, 'o', label='Original')\n",
"plt.plot(x, np.real(np.fft.ifft(np.fft.fft(y))), '-', label='Model')\n",
"plt.legend()\n",
"plt.show()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 528
},
"id": "j4rqDMnLz-1e",
"outputId": "63889524-8bb7-4a22-d9a8-cd9e13f0e203"
},
"execution_count": null,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 800x600 with 1 Axes>"
],
"image/png": "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\n"
},
"metadata": {}
}
]
},
{
"cell_type": "markdown",
"source": [
"## Regression"
],
"metadata": {
"id": "cMfG9dyS2W_P"
}
},
{
"cell_type": "code",
"source": [
"from sklearn.linear_model import LinearRegression\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"\n",
"model = LinearRegression()\n",
"model.fit(x.reshape(-1, 1), y)\n",
"\n",
"plt.figure(figsize=(8,6))\n",
"plt.plot(x, y, 'o', label='Original')\n",
"plt.plot(np.arange(0, 10, 0.01), model.predict(np.arange(0, 10, 0.01).reshape(-1, 1) ), '-', label='Model')\n",
"plt.legend()\n",
"plt.show()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 528
},
"id": "F1nepnNa2Yuk",
"outputId": "95316bed-32ac-453d-9760-72e27593a9cf"
},
"execution_count": null,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 800x600 with 1 Axes>"
],
"image/png": "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\n"
},
"metadata": {}
}
]
},
{
"cell_type": "markdown",
"source": [
"## SVR"
],
"metadata": {
"id": "wFmMgtt04tkH"
}
},
{
"cell_type": "code",
"source": [
"from sklearn.svm import SVR\n",
"model = SVR(kernel='linear', C=100, gamma=0.001, epsilon=.000001)\n",
"model.fit(x.reshape(-1, 1), y)\n",
"plt.figure(figsize=(8,6))\n",
"plt.plot(x, y, 'o', label='Original')\n",
"plt.plot(np.arange(0, 10, 0.01), model.predict(np.arange(0, 10, 0.01).reshape(-1, 1)), '-', label='Model')\n",
"plt.legend()\n",
"plt.show()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 528
},
"id": "KFBxZG9u4wRb",
"outputId": "90a7fe3e-9b83-469e-8ae9-02c4faab21bd"
},
"execution_count": null,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 800x600 with 1 Axes>"
],
"image/png": "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\n"
},
"metadata": {}
}
]
},
{
"cell_type": "markdown",
"source": [
"## Neuronal Network"
],
"metadata": {
"id": "dt5b3xxQ4vqu"
}
},
{
"cell_type": "code",
"source": [
"import numpy as np\n",
"import tensorflow as tf\n",
"from tensorflow.keras.models import Sequential\n",
"from tensorflow.keras.layers import Dense\n",
"\n",
"model = Sequential([\n",
" Dense(64, activation='relu', input_shape=(x.reshape(-1, 1).shape[1],)),\n",
" Dense(64, activation='relu'),\n",
" Dense(1)\n",
"])\n",
"\n",
"model.compile(optimizer='adam', loss='mse', metrics=['mae'])\n",
"\n",
"model.fit(x.reshape(-1, 1), y.reshape(-1, 1), epochs=100, batch_size=1, verbose=1)\n",
"\n",
"plt.figure(figsize=(8,6))\n",
"plt.plot(x, y, 'o', label='Original')\n",
"plt.plot(np.arange(0, 10, 0.01), model.predict(np.arange(0, 10, 0.01).reshape(-1, 1)), '-', label='Model')\n",
"plt.legend()\n",
"plt.show()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"id": "qg0ve8J6-kcc",
"outputId": "491f71f1-26d0-4c5a-aa09-695a4451075e"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/100\n",
"6/6 [==============================] - 3s 4ms/step - loss: 110.0455 - mae: 8.6372\n",
"Epoch 2/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 91.2532 - mae: 7.9128\n",
"Epoch 3/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 78.8783 - mae: 7.3213\n",
"Epoch 4/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 62.3848 - mae: 6.5455\n",
"Epoch 5/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 52.8810 - mae: 5.9853\n",
"Epoch 6/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 43.2447 - mae: 5.3895\n",
"Epoch 7/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 33.0851 - mae: 4.6914\n",
"Epoch 8/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 23.5645 - mae: 3.9477\n",
"Epoch 9/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 15.0551 - mae: 3.2037\n",
"Epoch 10/100\n",
"6/6 [==============================] - 0s 5ms/step - loss: 10.3860 - mae: 2.6595\n",
"Epoch 11/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 7.3316 - mae: 2.2078\n",
"Epoch 12/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 3.0631 - mae: 1.5076\n",
"Epoch 13/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 2.1020 - mae: 1.2027\n",
"Epoch 14/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 1.0924 - mae: 0.9052\n",
"Epoch 15/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.8061 - mae: 0.7731\n",
"Epoch 16/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.8186 - mae: 0.7596\n",
"Epoch 17/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.8058 - mae: 0.7378\n",
"Epoch 18/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.7691 - mae: 0.7152\n",
"Epoch 19/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.7297 - mae: 0.7046\n",
"Epoch 20/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.7157 - mae: 0.7081\n",
"Epoch 21/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.7020 - mae: 0.7163\n",
"Epoch 22/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.6719 - mae: 0.6975\n",
"Epoch 23/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.6520 - mae: 0.6871\n",
"Epoch 24/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.6417 - mae: 0.6853\n",
"Epoch 25/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.6114 - mae: 0.6587\n",
"Epoch 26/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.5928 - mae: 0.6499\n",
"Epoch 27/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.5703 - mae: 0.6311\n",
"Epoch 28/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.5554 - mae: 0.6224\n",
"Epoch 29/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.5393 - mae: 0.6178\n",
"Epoch 30/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.5306 - mae: 0.6195\n",
"Epoch 31/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.5057 - mae: 0.6038\n",
"Epoch 32/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.4911 - mae: 0.5967\n",
"Epoch 33/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.4794 - mae: 0.5898\n",
"Epoch 34/100\n",
"6/6 [==============================] - 0s 5ms/step - loss: 0.4560 - mae: 0.5610\n",
"Epoch 35/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.4427 - mae: 0.5540\n",
"Epoch 36/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.4151 - mae: 0.5504\n",
"Epoch 37/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.3951 - mae: 0.5323\n",
"Epoch 38/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.3807 - mae: 0.5172\n",
"Epoch 39/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.3691 - mae: 0.5034\n",
"Epoch 40/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.3493 - mae: 0.4908\n",
"Epoch 41/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.3520 - mae: 0.5118\n",
"Epoch 42/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.3335 - mae: 0.4878\n",
"Epoch 43/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.3109 - mae: 0.4570\n",
"Epoch 44/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.2871 - mae: 0.4327\n",
"Epoch 45/100\n",
"6/6 [==============================] - 0s 5ms/step - loss: 0.3161 - mae: 0.4964\n",
"Epoch 46/100\n",
"6/6 [==============================] - 0s 5ms/step - loss: 0.2689 - mae: 0.4421\n",
"Epoch 47/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.2726 - mae: 0.4316\n",
"Epoch 48/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.2462 - mae: 0.4188\n",
"Epoch 49/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.2335 - mae: 0.4158\n",
"Epoch 50/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.2137 - mae: 0.3898\n",
"Epoch 51/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.1991 - mae: 0.3647\n",
"Epoch 52/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.1887 - mae: 0.3533\n",
"Epoch 53/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.1719 - mae: 0.3356\n",
"Epoch 54/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.1703 - mae: 0.3508\n",
"Epoch 55/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.1552 - mae: 0.3322\n",
"Epoch 56/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.1565 - mae: 0.3329\n",
"Epoch 57/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.1436 - mae: 0.3192\n",
"Epoch 58/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.1316 - mae: 0.2916\n",
"Epoch 59/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.1135 - mae: 0.2696\n",
"Epoch 60/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.1066 - mae: 0.2775\n",
"Epoch 61/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.0950 - mae: 0.2568\n",
"Epoch 62/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.0876 - mae: 0.2449\n",
"Epoch 63/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.0804 - mae: 0.2339\n",
"Epoch 64/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.0719 - mae: 0.2263\n",
"Epoch 65/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.0649 - mae: 0.2123\n",
"Epoch 66/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.0557 - mae: 0.1891\n",
"Epoch 67/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.0520 - mae: 0.1830\n",
"Epoch 68/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.0421 - mae: 0.1628\n",
"Epoch 69/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.0420 - mae: 0.1595\n",
"Epoch 70/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.0386 - mae: 0.1675\n",
"Epoch 71/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.0283 - mae: 0.1284\n",
"Epoch 72/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.0359 - mae: 0.1516\n",
"Epoch 73/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.0268 - mae: 0.1291\n",
"Epoch 74/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.0281 - mae: 0.1481\n",
"Epoch 75/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.0245 - mae: 0.1183\n",
"Epoch 76/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.0130 - mae: 0.0737\n",
"Epoch 77/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.0154 - mae: 0.1040\n",
"Epoch 78/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.0102 - mae: 0.0646\n",
"Epoch 79/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.0113 - mae: 0.0694\n",
"Epoch 80/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.0080 - mae: 0.0591\n",
"Epoch 81/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.0072 - mae: 0.0561\n",
"Epoch 82/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.0067 - mae: 0.0482 \n",
"Epoch 83/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.0057 - mae: 0.0430\n",
"Epoch 84/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.0051 - mae: 0.0412\n",
"Epoch 85/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.0047 - mae: 0.0442\n",
"Epoch 86/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.0045 - mae: 0.0426\n",
"Epoch 87/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.0040 - mae: 0.0381\n",
"Epoch 88/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.0038 - mae: 0.0390\n",
"Epoch 89/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.0036 - mae: 0.0363\n",
"Epoch 90/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.0034 - mae: 0.0394\n",
"Epoch 91/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.0033 - mae: 0.0382 \n",
"Epoch 92/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.0030 - mae: 0.0348\n",
"Epoch 93/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.0028 - mae: 0.0341\n",
"Epoch 94/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.0027 - mae: 0.0349\n",
"Epoch 95/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.0027 - mae: 0.0381\n",
"Epoch 96/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.0025 - mae: 0.0342\n",
"Epoch 97/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.0022 - mae: 0.0314\n",
"Epoch 98/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.0024 - mae: 0.0370\n",
"Epoch 99/100\n",
"6/6 [==============================] - 0s 4ms/step - loss: 0.0022 - mae: 0.0321\n",
"Epoch 100/100\n",
"6/6 [==============================] - 0s 3ms/step - loss: 0.0021 - mae: 0.0332\n",
"32/32 [==============================] - 0s 2ms/step\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 800x600 with 1 Axes>"
],
"image/png": "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\n"
},
"metadata": {}
}
]
},
{
"cell_type": "markdown",
"source": [
"# $f(x)=3sin(4x-2)+3$"
],
"metadata": {
"id": "QCs_7MakAoYc"
}
},
{
"cell_type": "code",
"source": [
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"\n",
"x = np.arange(0, 12, 0.1)\n",
"y = 3*np.sin(4*x-2)+3"
],
"metadata": {
"id": "vAvohaPGAvts"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"## Interpolation"
],
"metadata": {
"id": "ja74MsLiA4PP"
}
},
{
"cell_type": "code",
"source": [
"from scipy import interpolate\n",
"\n",
"model = interpolate.interp1d(x, y, kind='cubic')\n",
"\n",
"plt.figure(figsize=(8,6))\n",
"plt.plot(x, y, 'o', label='Original')\n",
"plt.plot(np.arange(0, 10, 0.01), model(np.arange(0, 10, 0.01)), '-', label='Model')\n",
"plt.legend()\n",
"plt.show()"
],
"metadata": {
"id": "MUXi5wnmA6L-",
"outputId": "668ddc49-b8ed-4b76-c4f0-97a9c8005d12",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 522
}
},
"execution_count": null,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 800x600 with 1 Axes>"
],
"image/png": "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\n"
},
"metadata": {}
}
]
},
{
"cell_type": "markdown",
"source": [
"## Fast Fourier Transform and Inverse Fast Fourier Transform"
],
"metadata": {
"id": "828stWwiCXAm"
}
},
{
"cell_type": "code",
"source": [
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"\n",
"plt.figure(figsize=(8,6))\n",
"plt.plot(x, y, 'o', label='Original')\n",
"plt.plot(x, np.real(np.fft.ifft(np.fft.fft(y))), '-', label='Model')\n",
"plt.legend()\n",
"plt.show()"
],
"metadata": {
"id": "84hCeiP7CaSq",
"outputId": "30f49658-8b8a-409d-8cca-4a1fb2f5d8a6",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 522
}
},
"execution_count": null,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 800x600 with 1 Axes>"
],
"image/png": "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\n"
},
"metadata": {}
}
]
},
{
"cell_type": "markdown",
"source": [
"# XOR Problem"
],
"metadata": {
"id": "2aMB3xAc-6VE"
}
},
{
"cell_type": "code",
"source": [
"import numpy as np\n",
"from tensorflow.keras.models import Sequential\n",
"from tensorflow.keras.layers import Dense\n",
"import matplotlib.pyplot as plt\n",
"\n",
"# XOR function inputs and outputs\n",
"inputs = np.array([[0, 0], [0, 1], [1, 0], [1, 1]], \"float32\")\n",
"outputs = np.array([[0], [1], [1], [0]], \"float32\")\n",
"\n",
"# Building the model\n",
"model = Sequential()\n",
"model.add(Dense(8, input_dim=2, activation='relu'))\n",
"model.add(Dense(1, activation='sigmoid'))\n",
"\n",
"# Compiling the model\n",
"model.compile(loss='mean_squared_error',\n",
" optimizer='adam',\n",
" metrics=['binary_accuracy'])\n",
"\n",
"# Training the model\n",
"model.fit(inputs, outputs, epochs=1000, verbose=2)\n",
"\n",
"predictions = model.predict(inputs)\n",
"\n",
"# plot results\n",
"for i in range(4):\n",
" if outputs[i] == 0:\n",
" plt.scatter(inputs[i][0], inputs[i][1], c='red')\n",
" else:\n",
" plt.scatter(inputs[i][0], inputs[i][1], c='blue')\n",
"\n",
"# plot model predictions\n",
"for i in range(4):\n",
" if predictions[i].round() == 0:\n",
" plt.scatter(inputs[i][0], inputs[i][1], c='red', marker='x')\n",
" else:\n",
" plt.scatter(inputs[i][0], inputs[i][1], c='blue', marker='x')\n",
"\n",
"plt.show()"
],
"metadata": {
"id": "bLkzQs8R-8Y7",
"outputId": "3f7eb568-1d7a-41c4-bc90-65584b3e491e",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
}
},
"execution_count": 2,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/1000\n",
"1/1 - 1s - loss: 0.2763 - binary_accuracy: 0.5000 - 1s/epoch - 1s/step\n",
"Epoch 2/1000\n",
"1/1 - 0s - loss: 0.2759 - binary_accuracy: 0.2500 - 11ms/epoch - 11ms/step\n",
"Epoch 3/1000\n",
"1/1 - 0s - loss: 0.2755 - binary_accuracy: 0.2500 - 9ms/epoch - 9ms/step\n",
"Epoch 4/1000\n",
"1/1 - 0s - loss: 0.2751 - binary_accuracy: 0.2500 - 9ms/epoch - 9ms/step\n",
"Epoch 5/1000\n",
"1/1 - 0s - loss: 0.2748 - binary_accuracy: 0.2500 - 10ms/epoch - 10ms/step\n",
"Epoch 6/1000\n",
"1/1 - 0s - loss: 0.2744 - binary_accuracy: 0.2500 - 14ms/epoch - 14ms/step\n",
"Epoch 7/1000\n",
"1/1 - 0s - loss: 0.2740 - binary_accuracy: 0.2500 - 11ms/epoch - 11ms/step\n",
"Epoch 8/1000\n",
"1/1 - 0s - loss: 0.2737 - binary_accuracy: 0.2500 - 10ms/epoch - 10ms/step\n",
"Epoch 9/1000\n",
"1/1 - 0s - loss: 0.2733 - binary_accuracy: 0.2500 - 8ms/epoch - 8ms/step\n",
"Epoch 10/1000\n",
"1/1 - 0s - loss: 0.2729 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 11/1000\n",
"1/1 - 0s - loss: 0.2726 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 12/1000\n",
"1/1 - 0s - loss: 0.2722 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 13/1000\n",
"1/1 - 0s - loss: 0.2719 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 14/1000\n",
"1/1 - 0s - loss: 0.2715 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 15/1000\n",
"1/1 - 0s - loss: 0.2712 - binary_accuracy: 0.2500 - 8ms/epoch - 8ms/step\n",
"Epoch 16/1000\n",
"1/1 - 0s - loss: 0.2709 - binary_accuracy: 0.2500 - 9ms/epoch - 9ms/step\n",
"Epoch 17/1000\n",
"1/1 - 0s - loss: 0.2705 - binary_accuracy: 0.2500 - 8ms/epoch - 8ms/step\n",
"Epoch 18/1000\n",
"1/1 - 0s - loss: 0.2702 - binary_accuracy: 0.2500 - 8ms/epoch - 8ms/step\n",
"Epoch 19/1000\n",
"1/1 - 0s - loss: 0.2699 - binary_accuracy: 0.2500 - 8ms/epoch - 8ms/step\n",
"Epoch 20/1000\n",
"1/1 - 0s - loss: 0.2696 - binary_accuracy: 0.2500 - 8ms/epoch - 8ms/step\n",
"Epoch 21/1000\n",
"1/1 - 0s - loss: 0.2692 - binary_accuracy: 0.2500 - 9ms/epoch - 9ms/step\n",
"Epoch 22/1000\n",
"1/1 - 0s - loss: 0.2689 - binary_accuracy: 0.2500 - 9ms/epoch - 9ms/step\n",
"Epoch 23/1000\n",
"1/1 - 0s - loss: 0.2686 - binary_accuracy: 0.2500 - 8ms/epoch - 8ms/step\n",
"Epoch 24/1000\n",
"1/1 - 0s - loss: 0.2683 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 25/1000\n",
"1/1 - 0s - loss: 0.2680 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 26/1000\n",
"1/1 - 0s - loss: 0.2677 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 27/1000\n",
"1/1 - 0s - loss: 0.2673 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 28/1000\n",
"1/1 - 0s - loss: 0.2670 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 29/1000\n",
"1/1 - 0s - loss: 0.2667 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 30/1000\n",
"1/1 - 0s - loss: 0.2664 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 31/1000\n",
"1/1 - 0s - loss: 0.2661 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 32/1000\n",
"1/1 - 0s - loss: 0.2658 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 33/1000\n",
"1/1 - 0s - loss: 0.2655 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 34/1000\n",
"1/1 - 0s - loss: 0.2652 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 35/1000\n",
"1/1 - 0s - loss: 0.2649 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 36/1000\n",
"1/1 - 0s - loss: 0.2646 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 37/1000\n",
"1/1 - 0s - loss: 0.2643 - binary_accuracy: 0.2500 - 8ms/epoch - 8ms/step\n",
"Epoch 38/1000\n",
"1/1 - 0s - loss: 0.2641 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 39/1000\n",
"1/1 - 0s - loss: 0.2638 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 40/1000\n",
"1/1 - 0s - loss: 0.2635 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 41/1000\n",
"1/1 - 0s - loss: 0.2632 - binary_accuracy: 0.2500 - 8ms/epoch - 8ms/step\n",
"Epoch 42/1000\n",
"1/1 - 0s - loss: 0.2629 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 43/1000\n",
"1/1 - 0s - loss: 0.2626 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 44/1000\n",
"1/1 - 0s - loss: 0.2624 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 45/1000\n",
"1/1 - 0s - loss: 0.2621 - binary_accuracy: 0.2500 - 9ms/epoch - 9ms/step\n",
"Epoch 46/1000\n",
"1/1 - 0s - loss: 0.2618 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 47/1000\n",
"1/1 - 0s - loss: 0.2615 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 48/1000\n",
"1/1 - 0s - loss: 0.2613 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 49/1000\n",
"1/1 - 0s - loss: 0.2610 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 50/1000\n",
"1/1 - 0s - loss: 0.2608 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 51/1000\n",
"1/1 - 0s - loss: 0.2605 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 52/1000\n",
"1/1 - 0s - loss: 0.2602 - binary_accuracy: 0.2500 - 8ms/epoch - 8ms/step\n",
"Epoch 53/1000\n",
"1/1 - 0s - loss: 0.2600 - binary_accuracy: 0.2500 - 8ms/epoch - 8ms/step\n",
"Epoch 54/1000\n",
"1/1 - 0s - loss: 0.2597 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 55/1000\n",
"1/1 - 0s - loss: 0.2595 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 56/1000\n",
"1/1 - 0s - loss: 0.2592 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 57/1000\n",
"1/1 - 0s - loss: 0.2590 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 58/1000\n",
"1/1 - 0s - loss: 0.2587 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 59/1000\n",
"1/1 - 0s - loss: 0.2585 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 60/1000\n",
"1/1 - 0s - loss: 0.2583 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 61/1000\n",
"1/1 - 0s - loss: 0.2580 - binary_accuracy: 0.2500 - 8ms/epoch - 8ms/step\n",
"Epoch 62/1000\n",
"1/1 - 0s - loss: 0.2578 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 63/1000\n",
"1/1 - 0s - loss: 0.2576 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 64/1000\n",
"1/1 - 0s - loss: 0.2573 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 65/1000\n",
"1/1 - 0s - loss: 0.2571 - binary_accuracy: 0.2500 - 8ms/epoch - 8ms/step\n",
"Epoch 66/1000\n",
"1/1 - 0s - loss: 0.2569 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 67/1000\n",
"1/1 - 0s - loss: 0.2566 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 68/1000\n",
"1/1 - 0s - loss: 0.2564 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 69/1000\n",
"1/1 - 0s - loss: 0.2562 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 70/1000\n",
"1/1 - 0s - loss: 0.2560 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 71/1000\n",
"1/1 - 0s - loss: 0.2557 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 72/1000\n",
"1/1 - 0s - loss: 0.2555 - binary_accuracy: 0.2500 - 8ms/epoch - 8ms/step\n",
"Epoch 73/1000\n",
"1/1 - 0s - loss: 0.2553 - binary_accuracy: 0.2500 - 7ms/epoch - 7ms/step\n",
"Epoch 74/1000\n",
"1/1 - 0s - loss: 0.2551 - binary_accuracy: 0.5000 - 8ms/epoch - 8ms/step\n",
"Epoch 75/1000\n",
"1/1 - 0s - loss: 0.2549 - binary_accuracy: 0.5000 - 8ms/epoch - 8ms/step\n",
"Epoch 76/1000\n",
"1/1 - 0s - loss: 0.2547 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 77/1000\n",
"1/1 - 0s - loss: 0.2544 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 78/1000\n",
"1/1 - 0s - loss: 0.2542 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 79/1000\n",
"1/1 - 0s - loss: 0.2540 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 80/1000\n",
"1/1 - 0s - loss: 0.2538 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 81/1000\n",
"1/1 - 0s - loss: 0.2536 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 82/1000\n",
"1/1 - 0s - loss: 0.2534 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 83/1000\n",
"1/1 - 0s - loss: 0.2532 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 84/1000\n",
"1/1 - 0s - loss: 0.2530 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 85/1000\n",
"1/1 - 0s - loss: 0.2528 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 86/1000\n",
"1/1 - 0s - loss: 0.2526 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 87/1000\n",
"1/1 - 0s - loss: 0.2524 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 88/1000\n",
"1/1 - 0s - loss: 0.2522 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 89/1000\n",
"1/1 - 0s - loss: 0.2520 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 90/1000\n",
"1/1 - 0s - loss: 0.2518 - binary_accuracy: 0.5000 - 8ms/epoch - 8ms/step\n",
"Epoch 91/1000\n",
"1/1 - 0s - loss: 0.2516 - binary_accuracy: 0.5000 - 8ms/epoch - 8ms/step\n",
"Epoch 92/1000\n",
"1/1 - 0s - loss: 0.2514 - binary_accuracy: 0.5000 - 8ms/epoch - 8ms/step\n",
"Epoch 93/1000\n",
"1/1 - 0s - loss: 0.2512 - binary_accuracy: 0.5000 - 8ms/epoch - 8ms/step\n",
"Epoch 94/1000\n",
"1/1 - 0s - loss: 0.2510 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 95/1000\n",
"1/1 - 0s - loss: 0.2508 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 96/1000\n",
"1/1 - 0s - loss: 0.2506 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 97/1000\n",
"1/1 - 0s - loss: 0.2504 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 98/1000\n",
"1/1 - 0s - loss: 0.2502 - binary_accuracy: 0.5000 - 8ms/epoch - 8ms/step\n",
"Epoch 99/1000\n",
"1/1 - 0s - loss: 0.2500 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 100/1000\n",
"1/1 - 0s - loss: 0.2498 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 101/1000\n",
"1/1 - 0s - loss: 0.2496 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 102/1000\n",
"1/1 - 0s - loss: 0.2494 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 103/1000\n",
"1/1 - 0s - loss: 0.2492 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 104/1000\n",
"1/1 - 0s - loss: 0.2490 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 105/1000\n",
"1/1 - 0s - loss: 0.2489 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 106/1000\n",
"1/1 - 0s - loss: 0.2487 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 107/1000\n",
"1/1 - 0s - loss: 0.2485 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 108/1000\n",
"1/1 - 0s - loss: 0.2483 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 109/1000\n",
"1/1 - 0s - loss: 0.2481 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 110/1000\n",
"1/1 - 0s - loss: 0.2479 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 111/1000\n",
"1/1 - 0s - loss: 0.2477 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 112/1000\n",
"1/1 - 0s - loss: 0.2475 - binary_accuracy: 0.5000 - 8ms/epoch - 8ms/step\n",
"Epoch 113/1000\n",
"1/1 - 0s - loss: 0.2473 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 114/1000\n",
"1/1 - 0s - loss: 0.2471 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 115/1000\n",
"1/1 - 0s - loss: 0.2470 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 116/1000\n",
"1/1 - 0s - loss: 0.2468 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 117/1000\n",
"1/1 - 0s - loss: 0.2466 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 118/1000\n",
"1/1 - 0s - loss: 0.2464 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 119/1000\n",
"1/1 - 0s - loss: 0.2462 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 120/1000\n",
"1/1 - 0s - loss: 0.2460 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 121/1000\n",
"1/1 - 0s - loss: 0.2458 - binary_accuracy: 0.5000 - 8ms/epoch - 8ms/step\n",
"Epoch 122/1000\n",
"1/1 - 0s - loss: 0.2456 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 123/1000\n",
"1/1 - 0s - loss: 0.2455 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 124/1000\n",
"1/1 - 0s - loss: 0.2453 - binary_accuracy: 0.5000 - 8ms/epoch - 8ms/step\n",
"Epoch 125/1000\n",
"1/1 - 0s - loss: 0.2451 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 126/1000\n",
"1/1 - 0s - loss: 0.2449 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 127/1000\n",
"1/1 - 0s - loss: 0.2447 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 128/1000\n",
"1/1 - 0s - loss: 0.2445 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 129/1000\n",
"1/1 - 0s - loss: 0.2444 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 130/1000\n",
"1/1 - 0s - loss: 0.2442 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 131/1000\n",
"1/1 - 0s - loss: 0.2440 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 132/1000\n",
"1/1 - 0s - loss: 0.2438 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 133/1000\n",
"1/1 - 0s - loss: 0.2436 - binary_accuracy: 0.5000 - 8ms/epoch - 8ms/step\n",
"Epoch 134/1000\n",
"1/1 - 0s - loss: 0.2434 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 135/1000\n",
"1/1 - 0s - loss: 0.2432 - binary_accuracy: 0.5000 - 8ms/epoch - 8ms/step\n",
"Epoch 136/1000\n",
"1/1 - 0s - loss: 0.2430 - binary_accuracy: 0.5000 - 8ms/epoch - 8ms/step\n",
"Epoch 137/1000\n",
"1/1 - 0s - loss: 0.2429 - binary_accuracy: 0.5000 - 7ms/epoch - 7ms/step\n",
"Epoch 138/1000\n",
"1/1 - 0s - loss: 0.2427 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 139/1000\n",
"1/1 - 0s - loss: 0.2425 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 140/1000\n",
"1/1 - 0s - loss: 0.2423 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 141/1000\n",
"1/1 - 0s - loss: 0.2421 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 142/1000\n",
"1/1 - 0s - loss: 0.2419 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 143/1000\n",
"1/1 - 0s - loss: 0.2417 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 144/1000\n",
"1/1 - 0s - loss: 0.2415 - binary_accuracy: 0.7500 - 10ms/epoch - 10ms/step\n",
"Epoch 145/1000\n",
"1/1 - 0s - loss: 0.2414 - binary_accuracy: 0.7500 - 12ms/epoch - 12ms/step\n",
"Epoch 146/1000\n",
"1/1 - 0s - loss: 0.2412 - binary_accuracy: 0.7500 - 11ms/epoch - 11ms/step\n",
"Epoch 147/1000\n",
"1/1 - 0s - loss: 0.2410 - binary_accuracy: 0.7500 - 6ms/epoch - 6ms/step\n",
"Epoch 148/1000\n",
"1/1 - 0s - loss: 0.2408 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 149/1000\n",
"1/1 - 0s - loss: 0.2406 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 150/1000\n",
"1/1 - 0s - loss: 0.2404 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 151/1000\n",
"1/1 - 0s - loss: 0.2402 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 152/1000\n",
"1/1 - 0s - loss: 0.2400 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 153/1000\n",
"1/1 - 0s - loss: 0.2398 - binary_accuracy: 0.7500 - 11ms/epoch - 11ms/step\n",
"Epoch 154/1000\n",
"1/1 - 0s - loss: 0.2396 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 155/1000\n",
"1/1 - 0s - loss: 0.2394 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 156/1000\n",
"1/1 - 0s - loss: 0.2393 - binary_accuracy: 0.7500 - 10ms/epoch - 10ms/step\n",
"Epoch 157/1000\n",
"1/1 - 0s - loss: 0.2391 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 158/1000\n",
"1/1 - 0s - loss: 0.2389 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 159/1000\n",
"1/1 - 0s - loss: 0.2387 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 160/1000\n",
"1/1 - 0s - loss: 0.2385 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 161/1000\n",
"1/1 - 0s - loss: 0.2383 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 162/1000\n",
"1/1 - 0s - loss: 0.2381 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 163/1000\n",
"1/1 - 0s - loss: 0.2379 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 164/1000\n",
"1/1 - 0s - loss: 0.2377 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 165/1000\n",
"1/1 - 0s - loss: 0.2375 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 166/1000\n",
"1/1 - 0s - loss: 0.2373 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 167/1000\n",
"1/1 - 0s - loss: 0.2371 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 168/1000\n",
"1/1 - 0s - loss: 0.2369 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 169/1000\n",
"1/1 - 0s - loss: 0.2367 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 170/1000\n",
"1/1 - 0s - loss: 0.2365 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 171/1000\n",
"1/1 - 0s - loss: 0.2363 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 172/1000\n",
"1/1 - 0s - loss: 0.2361 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 173/1000\n",
"1/1 - 0s - loss: 0.2358 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 174/1000\n",
"1/1 - 0s - loss: 0.2356 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 175/1000\n",
"1/1 - 0s - loss: 0.2354 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 176/1000\n",
"1/1 - 0s - loss: 0.2352 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 177/1000\n",
"1/1 - 0s - loss: 0.2350 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 178/1000\n",
"1/1 - 0s - loss: 0.2348 - binary_accuracy: 0.7500 - 10ms/epoch - 10ms/step\n",
"Epoch 179/1000\n",
"1/1 - 0s - loss: 0.2346 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 180/1000\n",
"1/1 - 0s - loss: 0.2344 - binary_accuracy: 0.7500 - 12ms/epoch - 12ms/step\n",
"Epoch 181/1000\n",
"1/1 - 0s - loss: 0.2342 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 182/1000\n",
"1/1 - 0s - loss: 0.2339 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 183/1000\n",
"1/1 - 0s - loss: 0.2337 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 184/1000\n",
"1/1 - 0s - loss: 0.2335 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 185/1000\n",
"1/1 - 0s - loss: 0.2333 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 186/1000\n",
"1/1 - 0s - loss: 0.2331 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 187/1000\n",
"1/1 - 0s - loss: 0.2329 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 188/1000\n",
"1/1 - 0s - loss: 0.2326 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 189/1000\n",
"1/1 - 0s - loss: 0.2324 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 190/1000\n",
"1/1 - 0s - loss: 0.2322 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 191/1000\n",
"1/1 - 0s - loss: 0.2320 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 192/1000\n",
"1/1 - 0s - loss: 0.2317 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 193/1000\n",
"1/1 - 0s - loss: 0.2315 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 194/1000\n",
"1/1 - 0s - loss: 0.2313 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 195/1000\n",
"1/1 - 0s - loss: 0.2311 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 196/1000\n",
"1/1 - 0s - loss: 0.2308 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 197/1000\n",
"1/1 - 0s - loss: 0.2306 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 198/1000\n",
"1/1 - 0s - loss: 0.2304 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 199/1000\n",
"1/1 - 0s - loss: 0.2301 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 200/1000\n",
"1/1 - 0s - loss: 0.2299 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 201/1000\n",
"1/1 - 0s - loss: 0.2297 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 202/1000\n",
"1/1 - 0s - loss: 0.2295 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 203/1000\n",
"1/1 - 0s - loss: 0.2293 - binary_accuracy: 0.7500 - 11ms/epoch - 11ms/step\n",
"Epoch 204/1000\n",
"1/1 - 0s - loss: 0.2290 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 205/1000\n",
"1/1 - 0s - loss: 0.2288 - binary_accuracy: 0.7500 - 10ms/epoch - 10ms/step\n",
"Epoch 206/1000\n",
"1/1 - 0s - loss: 0.2286 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 207/1000\n",
"1/1 - 0s - loss: 0.2284 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 208/1000\n",
"1/1 - 0s - loss: 0.2281 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 209/1000\n",
"1/1 - 0s - loss: 0.2279 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 210/1000\n",
"1/1 - 0s - loss: 0.2277 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 211/1000\n",
"1/1 - 0s - loss: 0.2274 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 212/1000\n",
"1/1 - 0s - loss: 0.2272 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 213/1000\n",
"1/1 - 0s - loss: 0.2270 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 214/1000\n",
"1/1 - 0s - loss: 0.2267 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 215/1000\n",
"1/1 - 0s - loss: 0.2265 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 216/1000\n",
"1/1 - 0s - loss: 0.2263 - binary_accuracy: 0.7500 - 6ms/epoch - 6ms/step\n",
"Epoch 217/1000\n",
"1/1 - 0s - loss: 0.2260 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 218/1000\n",
"1/1 - 0s - loss: 0.2258 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 219/1000\n",
"1/1 - 0s - loss: 0.2255 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 220/1000\n",
"1/1 - 0s - loss: 0.2253 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 221/1000\n",
"1/1 - 0s - loss: 0.2251 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 222/1000\n",
"1/1 - 0s - loss: 0.2248 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 223/1000\n",
"1/1 - 0s - loss: 0.2246 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 224/1000\n",
"1/1 - 0s - loss: 0.2243 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 225/1000\n",
"1/1 - 0s - loss: 0.2241 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 226/1000\n",
"1/1 - 0s - loss: 0.2238 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 227/1000\n",
"1/1 - 0s - loss: 0.2236 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 228/1000\n",
"1/1 - 0s - loss: 0.2233 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 229/1000\n",
"1/1 - 0s - loss: 0.2231 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 230/1000\n",
"1/1 - 0s - loss: 0.2229 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 231/1000\n",
"1/1 - 0s - loss: 0.2226 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 232/1000\n",
"1/1 - 0s - loss: 0.2224 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 233/1000\n",
"1/1 - 0s - loss: 0.2221 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 234/1000\n",
"1/1 - 0s - loss: 0.2219 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 235/1000\n",
"1/1 - 0s - loss: 0.2216 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 236/1000\n",
"1/1 - 0s - loss: 0.2214 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 237/1000\n",
"1/1 - 0s - loss: 0.2211 - binary_accuracy: 0.7500 - 12ms/epoch - 12ms/step\n",
"Epoch 238/1000\n",
"1/1 - 0s - loss: 0.2208 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 239/1000\n",
"1/1 - 0s - loss: 0.2206 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 240/1000\n",
"1/1 - 0s - loss: 0.2203 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 241/1000\n",
"1/1 - 0s - loss: 0.2201 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 242/1000\n",
"1/1 - 0s - loss: 0.2198 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 243/1000\n",
"1/1 - 0s - loss: 0.2196 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 244/1000\n",
"1/1 - 0s - loss: 0.2193 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 245/1000\n",
"1/1 - 0s - loss: 0.2190 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 246/1000\n",
"1/1 - 0s - loss: 0.2188 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 247/1000\n",
"1/1 - 0s - loss: 0.2185 - binary_accuracy: 0.7500 - 10ms/epoch - 10ms/step\n",
"Epoch 248/1000\n",
"1/1 - 0s - loss: 0.2183 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 249/1000\n",
"1/1 - 0s - loss: 0.2180 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 250/1000\n",
"1/1 - 0s - loss: 0.2178 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 251/1000\n",
"1/1 - 0s - loss: 0.2176 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 252/1000\n",
"1/1 - 0s - loss: 0.2174 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 253/1000\n",
"1/1 - 0s - loss: 0.2172 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 254/1000\n",
"1/1 - 0s - loss: 0.2170 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 255/1000\n",
"1/1 - 0s - loss: 0.2167 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 256/1000\n",
"1/1 - 0s - loss: 0.2165 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 257/1000\n",
"1/1 - 0s - loss: 0.2163 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 258/1000\n",
"1/1 - 0s - loss: 0.2161 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 259/1000\n",
"1/1 - 0s - loss: 0.2159 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 260/1000\n",
"1/1 - 0s - loss: 0.2156 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 261/1000\n",
"1/1 - 0s - loss: 0.2154 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 262/1000\n",
"1/1 - 0s - loss: 0.2152 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 263/1000\n",
"1/1 - 0s - loss: 0.2150 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 264/1000\n",
"1/1 - 0s - loss: 0.2147 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 265/1000\n",
"1/1 - 0s - loss: 0.2145 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 266/1000\n",
"1/1 - 0s - loss: 0.2143 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 267/1000\n",
"1/1 - 0s - loss: 0.2140 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 268/1000\n",
"1/1 - 0s - loss: 0.2138 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 269/1000\n",
"1/1 - 0s - loss: 0.2136 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 270/1000\n",
"1/1 - 0s - loss: 0.2134 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 271/1000\n",
"1/1 - 0s - loss: 0.2132 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 272/1000\n",
"1/1 - 0s - loss: 0.2129 - binary_accuracy: 0.7500 - 10ms/epoch - 10ms/step\n",
"Epoch 273/1000\n",
"1/1 - 0s - loss: 0.2127 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 274/1000\n",
"1/1 - 0s - loss: 0.2124 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 275/1000\n",
"1/1 - 0s - loss: 0.2122 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 276/1000\n",
"1/1 - 0s - loss: 0.2120 - binary_accuracy: 0.7500 - 6ms/epoch - 6ms/step\n",
"Epoch 277/1000\n",
"1/1 - 0s - loss: 0.2118 - binary_accuracy: 0.7500 - 6ms/epoch - 6ms/step\n",
"Epoch 278/1000\n",
"1/1 - 0s - loss: 0.2115 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 279/1000\n",
"1/1 - 0s - loss: 0.2113 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 280/1000\n",
"1/1 - 0s - loss: 0.2111 - binary_accuracy: 0.7500 - 6ms/epoch - 6ms/step\n",
"Epoch 281/1000\n",
"1/1 - 0s - loss: 0.2108 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 282/1000\n",
"1/1 - 0s - loss: 0.2106 - binary_accuracy: 0.7500 - 6ms/epoch - 6ms/step\n",
"Epoch 283/1000\n",
"1/1 - 0s - loss: 0.2104 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 284/1000\n",
"1/1 - 0s - loss: 0.2101 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 285/1000\n",
"1/1 - 0s - loss: 0.2099 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 286/1000\n",
"1/1 - 0s - loss: 0.2097 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 287/1000\n",
"1/1 - 0s - loss: 0.2094 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 288/1000\n",
"1/1 - 0s - loss: 0.2092 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 289/1000\n",
"1/1 - 0s - loss: 0.2089 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 290/1000\n",
"1/1 - 0s - loss: 0.2087 - binary_accuracy: 0.7500 - 6ms/epoch - 6ms/step\n",
"Epoch 291/1000\n",
"1/1 - 0s - loss: 0.2085 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 292/1000\n",
"1/1 - 0s - loss: 0.2082 - binary_accuracy: 0.7500 - 6ms/epoch - 6ms/step\n",
"Epoch 293/1000\n",
"1/1 - 0s - loss: 0.2080 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 294/1000\n",
"1/1 - 0s - loss: 0.2078 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 295/1000\n",
"1/1 - 0s - loss: 0.2075 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 296/1000\n",
"1/1 - 0s - loss: 0.2073 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 297/1000\n",
"1/1 - 0s - loss: 0.2070 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 298/1000\n",
"1/1 - 0s - loss: 0.2068 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 299/1000\n",
"1/1 - 0s - loss: 0.2065 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 300/1000\n",
"1/1 - 0s - loss: 0.2063 - binary_accuracy: 0.7500 - 11ms/epoch - 11ms/step\n",
"Epoch 301/1000\n",
"1/1 - 0s - loss: 0.2061 - binary_accuracy: 0.7500 - 12ms/epoch - 12ms/step\n",
"Epoch 302/1000\n",
"1/1 - 0s - loss: 0.2058 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 303/1000\n",
"1/1 - 0s - loss: 0.2056 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 304/1000\n",
"1/1 - 0s - loss: 0.2053 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 305/1000\n",
"1/1 - 0s - loss: 0.2051 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 306/1000\n",
"1/1 - 0s - loss: 0.2048 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 307/1000\n",
"1/1 - 0s - loss: 0.2046 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 308/1000\n",
"1/1 - 0s - loss: 0.2043 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 309/1000\n",
"1/1 - 0s - loss: 0.2041 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 310/1000\n",
"1/1 - 0s - loss: 0.2038 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 311/1000\n",
"1/1 - 0s - loss: 0.2036 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 312/1000\n",
"1/1 - 0s - loss: 0.2034 - binary_accuracy: 0.7500 - 6ms/epoch - 6ms/step\n",
"Epoch 313/1000\n",
"1/1 - 0s - loss: 0.2031 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 314/1000\n",
"1/1 - 0s - loss: 0.2028 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 315/1000\n",
"1/1 - 0s - loss: 0.2026 - binary_accuracy: 0.7500 - 10ms/epoch - 10ms/step\n",
"Epoch 316/1000\n",
"1/1 - 0s - loss: 0.2023 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 317/1000\n",
"1/1 - 0s - loss: 0.2021 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 318/1000\n",
"1/1 - 0s - loss: 0.2018 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 319/1000\n",
"1/1 - 0s - loss: 0.2016 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 320/1000\n",
"1/1 - 0s - loss: 0.2013 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 321/1000\n",
"1/1 - 0s - loss: 0.2011 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 322/1000\n",
"1/1 - 0s - loss: 0.2008 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 323/1000\n",
"1/1 - 0s - loss: 0.2006 - binary_accuracy: 0.7500 - 11ms/epoch - 11ms/step\n",
"Epoch 324/1000\n",
"1/1 - 0s - loss: 0.2003 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 325/1000\n",
"1/1 - 0s - loss: 0.2001 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 326/1000\n",
"1/1 - 0s - loss: 0.1998 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 327/1000\n",
"1/1 - 0s - loss: 0.1995 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 328/1000\n",
"1/1 - 0s - loss: 0.1993 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 329/1000\n",
"1/1 - 0s - loss: 0.1990 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 330/1000\n",
"1/1 - 0s - loss: 0.1988 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 331/1000\n",
"1/1 - 0s - loss: 0.1985 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 332/1000\n",
"1/1 - 0s - loss: 0.1982 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 333/1000\n",
"1/1 - 0s - loss: 0.1980 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 334/1000\n",
"1/1 - 0s - loss: 0.1977 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 335/1000\n",
"1/1 - 0s - loss: 0.1975 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 336/1000\n",
"1/1 - 0s - loss: 0.1972 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 337/1000\n",
"1/1 - 0s - loss: 0.1969 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 338/1000\n",
"1/1 - 0s - loss: 0.1967 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 339/1000\n",
"1/1 - 0s - loss: 0.1964 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 340/1000\n",
"1/1 - 0s - loss: 0.1961 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 341/1000\n",
"1/1 - 0s - loss: 0.1959 - binary_accuracy: 0.7500 - 13ms/epoch - 13ms/step\n",
"Epoch 342/1000\n",
"1/1 - 0s - loss: 0.1956 - binary_accuracy: 0.7500 - 6ms/epoch - 6ms/step\n",
"Epoch 343/1000\n",
"1/1 - 0s - loss: 0.1954 - binary_accuracy: 0.7500 - 6ms/epoch - 6ms/step\n",
"Epoch 344/1000\n",
"1/1 - 0s - loss: 0.1951 - binary_accuracy: 0.7500 - 6ms/epoch - 6ms/step\n",
"Epoch 345/1000\n",
"1/1 - 0s - loss: 0.1948 - binary_accuracy: 0.7500 - 6ms/epoch - 6ms/step\n",
"Epoch 346/1000\n",
"1/1 - 0s - loss: 0.1945 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 347/1000\n",
"1/1 - 0s - loss: 0.1943 - binary_accuracy: 0.7500 - 6ms/epoch - 6ms/step\n",
"Epoch 348/1000\n",
"1/1 - 0s - loss: 0.1940 - binary_accuracy: 0.7500 - 6ms/epoch - 6ms/step\n",
"Epoch 349/1000\n",
"1/1 - 0s - loss: 0.1937 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 350/1000\n",
"1/1 - 0s - loss: 0.1935 - binary_accuracy: 0.7500 - 9ms/epoch - 9ms/step\n",
"Epoch 351/1000\n",
"1/1 - 0s - loss: 0.1932 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 352/1000\n",
"1/1 - 0s - loss: 0.1929 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 353/1000\n",
"1/1 - 0s - loss: 0.1927 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 354/1000\n",
"1/1 - 0s - loss: 0.1924 - binary_accuracy: 0.7500 - 11ms/epoch - 11ms/step\n",
"Epoch 355/1000\n",
"1/1 - 0s - loss: 0.1921 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 356/1000\n",
"1/1 - 0s - loss: 0.1919 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 357/1000\n",
"1/1 - 0s - loss: 0.1916 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 358/1000\n",
"1/1 - 0s - loss: 0.1914 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 359/1000\n",
"1/1 - 0s - loss: 0.1911 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 360/1000\n",
"1/1 - 0s - loss: 0.1908 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 361/1000\n",
"1/1 - 0s - loss: 0.1906 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 362/1000\n",
"1/1 - 0s - loss: 0.1903 - binary_accuracy: 0.7500 - 10ms/epoch - 10ms/step\n",
"Epoch 363/1000\n",
"1/1 - 0s - loss: 0.1901 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 364/1000\n",
"1/1 - 0s - loss: 0.1898 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 365/1000\n",
"1/1 - 0s - loss: 0.1895 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 366/1000\n",
"1/1 - 0s - loss: 0.1893 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 367/1000\n",
"1/1 - 0s - loss: 0.1890 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 368/1000\n",
"1/1 - 0s - loss: 0.1887 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 369/1000\n",
"1/1 - 0s - loss: 0.1885 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 370/1000\n",
"1/1 - 0s - loss: 0.1882 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 371/1000\n",
"1/1 - 0s - loss: 0.1879 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 372/1000\n",
"1/1 - 0s - loss: 0.1877 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 373/1000\n",
"1/1 - 0s - loss: 0.1874 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 374/1000\n",
"1/1 - 0s - loss: 0.1871 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 375/1000\n",
"1/1 - 0s - loss: 0.1869 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 376/1000\n",
"1/1 - 0s - loss: 0.1867 - binary_accuracy: 0.7500 - 11ms/epoch - 11ms/step\n",
"Epoch 377/1000\n",
"1/1 - 0s - loss: 0.1864 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 378/1000\n",
"1/1 - 0s - loss: 0.1861 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 379/1000\n",
"1/1 - 0s - loss: 0.1859 - binary_accuracy: 0.7500 - 10ms/epoch - 10ms/step\n",
"Epoch 380/1000\n",
"1/1 - 0s - loss: 0.1856 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 381/1000\n",
"1/1 - 0s - loss: 0.1853 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 382/1000\n",
"1/1 - 0s - loss: 0.1851 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 383/1000\n",
"1/1 - 0s - loss: 0.1848 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 384/1000\n",
"1/1 - 0s - loss: 0.1845 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 385/1000\n",
"1/1 - 0s - loss: 0.1842 - binary_accuracy: 0.7500 - 8ms/epoch - 8ms/step\n",
"Epoch 386/1000\n",
"1/1 - 0s - loss: 0.1840 - binary_accuracy: 0.7500 - 7ms/epoch - 7ms/step\n",
"Epoch 387/1000\n",
"1/1 - 0s - loss: 0.1837 - binary_accuracy: 0.7500 - 12ms/epoch - 12ms/step\n",
"Epoch 388/1000\n",
"1/1 - 0s - loss: 0.1835 - binary_accuracy: 0.7500 - 10ms/epoch - 10ms/step\n",
"Epoch 389/1000\n",
"1/1 - 0s - loss: 0.1832 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 390/1000\n",
"1/1 - 0s - loss: 0.1829 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 391/1000\n",
"1/1 - 0s - loss: 0.1826 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 392/1000\n",
"1/1 - 0s - loss: 0.1824 - binary_accuracy: 1.0000 - 6ms/epoch - 6ms/step\n",
"Epoch 393/1000\n",
"1/1 - 0s - loss: 0.1821 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 394/1000\n",
"1/1 - 0s - loss: 0.1818 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 395/1000\n",
"1/1 - 0s - loss: 0.1816 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 396/1000\n",
"1/1 - 0s - loss: 0.1813 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 397/1000\n",
"1/1 - 0s - loss: 0.1810 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 398/1000\n",
"1/1 - 0s - loss: 0.1808 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 399/1000\n",
"1/1 - 0s - loss: 0.1805 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 400/1000\n",
"1/1 - 0s - loss: 0.1802 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 401/1000\n",
"1/1 - 0s - loss: 0.1800 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 402/1000\n",
"1/1 - 0s - loss: 0.1797 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 403/1000\n",
"1/1 - 0s - loss: 0.1794 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 404/1000\n",
"1/1 - 0s - loss: 0.1792 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 405/1000\n",
"1/1 - 0s - loss: 0.1789 - binary_accuracy: 1.0000 - 15ms/epoch - 15ms/step\n",
"Epoch 406/1000\n",
"1/1 - 0s - loss: 0.1786 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 407/1000\n",
"1/1 - 0s - loss: 0.1783 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 408/1000\n",
"1/1 - 0s - loss: 0.1781 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 409/1000\n",
"1/1 - 0s - loss: 0.1778 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 410/1000\n",
"1/1 - 0s - loss: 0.1776 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 411/1000\n",
"1/1 - 0s - loss: 0.1773 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 412/1000\n",
"1/1 - 0s - loss: 0.1770 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 413/1000\n",
"1/1 - 0s - loss: 0.1767 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 414/1000\n",
"1/1 - 0s - loss: 0.1765 - binary_accuracy: 1.0000 - 14ms/epoch - 14ms/step\n",
"Epoch 415/1000\n",
"1/1 - 0s - loss: 0.1762 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 416/1000\n",
"1/1 - 0s - loss: 0.1759 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 417/1000\n",
"1/1 - 0s - loss: 0.1757 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 418/1000\n",
"1/1 - 0s - loss: 0.1754 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 419/1000\n",
"1/1 - 0s - loss: 0.1752 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 420/1000\n",
"1/1 - 0s - loss: 0.1749 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 421/1000\n",
"1/1 - 0s - loss: 0.1747 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 422/1000\n",
"1/1 - 0s - loss: 0.1744 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 423/1000\n",
"1/1 - 0s - loss: 0.1741 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 424/1000\n",
"1/1 - 0s - loss: 0.1739 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 425/1000\n",
"1/1 - 0s - loss: 0.1736 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 426/1000\n",
"1/1 - 0s - loss: 0.1734 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 427/1000\n",
"1/1 - 0s - loss: 0.1731 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 428/1000\n",
"1/1 - 0s - loss: 0.1728 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 429/1000\n",
"1/1 - 0s - loss: 0.1726 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 430/1000\n",
"1/1 - 0s - loss: 0.1723 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 431/1000\n",
"1/1 - 0s - loss: 0.1721 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 432/1000\n",
"1/1 - 0s - loss: 0.1718 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 433/1000\n",
"1/1 - 0s - loss: 0.1716 - binary_accuracy: 1.0000 - 6ms/epoch - 6ms/step\n",
"Epoch 434/1000\n",
"1/1 - 0s - loss: 0.1713 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 435/1000\n",
"1/1 - 0s - loss: 0.1710 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 436/1000\n",
"1/1 - 0s - loss: 0.1708 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 437/1000\n",
"1/1 - 0s - loss: 0.1706 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 438/1000\n",
"1/1 - 0s - loss: 0.1703 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 439/1000\n",
"1/1 - 0s - loss: 0.1700 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 440/1000\n",
"1/1 - 0s - loss: 0.1698 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 441/1000\n",
"1/1 - 0s - loss: 0.1695 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 442/1000\n",
"1/1 - 0s - loss: 0.1693 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 443/1000\n",
"1/1 - 0s - loss: 0.1690 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 444/1000\n",
"1/1 - 0s - loss: 0.1688 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 445/1000\n",
"1/1 - 0s - loss: 0.1685 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 446/1000\n",
"1/1 - 0s - loss: 0.1683 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 447/1000\n",
"1/1 - 0s - loss: 0.1680 - binary_accuracy: 1.0000 - 6ms/epoch - 6ms/step\n",
"Epoch 448/1000\n",
"1/1 - 0s - loss: 0.1678 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 449/1000\n",
"1/1 - 0s - loss: 0.1675 - binary_accuracy: 1.0000 - 6ms/epoch - 6ms/step\n",
"Epoch 450/1000\n",
"1/1 - 0s - loss: 0.1673 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 451/1000\n",
"1/1 - 0s - loss: 0.1670 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 452/1000\n",
"1/1 - 0s - loss: 0.1668 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 453/1000\n",
"1/1 - 0s - loss: 0.1666 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 454/1000\n",
"1/1 - 0s - loss: 0.1663 - binary_accuracy: 1.0000 - 6ms/epoch - 6ms/step\n",
"Epoch 455/1000\n",
"1/1 - 0s - loss: 0.1661 - binary_accuracy: 1.0000 - 6ms/epoch - 6ms/step\n",
"Epoch 456/1000\n",
"1/1 - 0s - loss: 0.1658 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 457/1000\n",
"1/1 - 0s - loss: 0.1655 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 458/1000\n",
"1/1 - 0s - loss: 0.1653 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 459/1000\n",
"1/1 - 0s - loss: 0.1651 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 460/1000\n",
"1/1 - 0s - loss: 0.1648 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 461/1000\n",
"1/1 - 0s - loss: 0.1646 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 462/1000\n",
"1/1 - 0s - loss: 0.1643 - binary_accuracy: 1.0000 - 12ms/epoch - 12ms/step\n",
"Epoch 463/1000\n",
"1/1 - 0s - loss: 0.1641 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 464/1000\n",
"1/1 - 0s - loss: 0.1638 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 465/1000\n",
"1/1 - 0s - loss: 0.1636 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 466/1000\n",
"1/1 - 0s - loss: 0.1633 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 467/1000\n",
"1/1 - 0s - loss: 0.1631 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 468/1000\n",
"1/1 - 0s - loss: 0.1629 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 469/1000\n",
"1/1 - 0s - loss: 0.1626 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 470/1000\n",
"1/1 - 0s - loss: 0.1624 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 471/1000\n",
"1/1 - 0s - loss: 0.1621 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 472/1000\n",
"1/1 - 0s - loss: 0.1619 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 473/1000\n",
"1/1 - 0s - loss: 0.1616 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 474/1000\n",
"1/1 - 0s - loss: 0.1614 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 475/1000\n",
"1/1 - 0s - loss: 0.1611 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 476/1000\n",
"1/1 - 0s - loss: 0.1609 - binary_accuracy: 1.0000 - 13ms/epoch - 13ms/step\n",
"Epoch 477/1000\n",
"1/1 - 0s - loss: 0.1607 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 478/1000\n",
"1/1 - 0s - loss: 0.1604 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 479/1000\n",
"1/1 - 0s - loss: 0.1602 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 480/1000\n",
"1/1 - 0s - loss: 0.1599 - binary_accuracy: 1.0000 - 6ms/epoch - 6ms/step\n",
"Epoch 481/1000\n",
"1/1 - 0s - loss: 0.1597 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 482/1000\n",
"1/1 - 0s - loss: 0.1595 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 483/1000\n",
"1/1 - 0s - loss: 0.1592 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 484/1000\n",
"1/1 - 0s - loss: 0.1590 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 485/1000\n",
"1/1 - 0s - loss: 0.1587 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 486/1000\n",
"1/1 - 0s - loss: 0.1585 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 487/1000\n",
"1/1 - 0s - loss: 0.1582 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 488/1000\n",
"1/1 - 0s - loss: 0.1580 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 489/1000\n",
"1/1 - 0s - loss: 0.1578 - binary_accuracy: 1.0000 - 14ms/epoch - 14ms/step\n",
"Epoch 490/1000\n",
"1/1 - 0s - loss: 0.1575 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 491/1000\n",
"1/1 - 0s - loss: 0.1573 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 492/1000\n",
"1/1 - 0s - loss: 0.1571 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 493/1000\n",
"1/1 - 0s - loss: 0.1568 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 494/1000\n",
"1/1 - 0s - loss: 0.1566 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 495/1000\n",
"1/1 - 0s - loss: 0.1564 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 496/1000\n",
"1/1 - 0s - loss: 0.1561 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 497/1000\n",
"1/1 - 0s - loss: 0.1559 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 498/1000\n",
"1/1 - 0s - loss: 0.1556 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 499/1000\n",
"1/1 - 0s - loss: 0.1554 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 500/1000\n",
"1/1 - 0s - loss: 0.1552 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 501/1000\n",
"1/1 - 0s - loss: 0.1549 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 502/1000\n",
"1/1 - 0s - loss: 0.1547 - binary_accuracy: 1.0000 - 13ms/epoch - 13ms/step\n",
"Epoch 503/1000\n",
"1/1 - 0s - loss: 0.1545 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 504/1000\n",
"1/1 - 0s - loss: 0.1543 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 505/1000\n",
"1/1 - 0s - loss: 0.1540 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 506/1000\n",
"1/1 - 0s - loss: 0.1538 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 507/1000\n",
"1/1 - 0s - loss: 0.1536 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 508/1000\n",
"1/1 - 0s - loss: 0.1533 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 509/1000\n",
"1/1 - 0s - loss: 0.1531 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 510/1000\n",
"1/1 - 0s - loss: 0.1528 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 511/1000\n",
"1/1 - 0s - loss: 0.1526 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 512/1000\n",
"1/1 - 0s - loss: 0.1524 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 513/1000\n",
"1/1 - 0s - loss: 0.1522 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 514/1000\n",
"1/1 - 0s - loss: 0.1519 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 515/1000\n",
"1/1 - 0s - loss: 0.1517 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 516/1000\n",
"1/1 - 0s - loss: 0.1515 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 517/1000\n",
"1/1 - 0s - loss: 0.1512 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 518/1000\n",
"1/1 - 0s - loss: 0.1510 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 519/1000\n",
"1/1 - 0s - loss: 0.1508 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 520/1000\n",
"1/1 - 0s - loss: 0.1506 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 521/1000\n",
"1/1 - 0s - loss: 0.1503 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 522/1000\n",
"1/1 - 0s - loss: 0.1501 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 523/1000\n",
"1/1 - 0s - loss: 0.1499 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 524/1000\n",
"1/1 - 0s - loss: 0.1497 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 525/1000\n",
"1/1 - 0s - loss: 0.1494 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 526/1000\n",
"1/1 - 0s - loss: 0.1492 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 527/1000\n",
"1/1 - 0s - loss: 0.1490 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 528/1000\n",
"1/1 - 0s - loss: 0.1488 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 529/1000\n",
"1/1 - 0s - loss: 0.1485 - binary_accuracy: 1.0000 - 6ms/epoch - 6ms/step\n",
"Epoch 530/1000\n",
"1/1 - 0s - loss: 0.1483 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 531/1000\n",
"1/1 - 0s - loss: 0.1481 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 532/1000\n",
"1/1 - 0s - loss: 0.1479 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 533/1000\n",
"1/1 - 0s - loss: 0.1476 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 534/1000\n",
"1/1 - 0s - loss: 0.1474 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 535/1000\n",
"1/1 - 0s - loss: 0.1472 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 536/1000\n",
"1/1 - 0s - loss: 0.1470 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 537/1000\n",
"1/1 - 0s - loss: 0.1468 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 538/1000\n",
"1/1 - 0s - loss: 0.1465 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 539/1000\n",
"1/1 - 0s - loss: 0.1463 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 540/1000\n",
"1/1 - 0s - loss: 0.1461 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 541/1000\n",
"1/1 - 0s - loss: 0.1459 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 542/1000\n",
"1/1 - 0s - loss: 0.1457 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 543/1000\n",
"1/1 - 0s - loss: 0.1454 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 544/1000\n",
"1/1 - 0s - loss: 0.1452 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 545/1000\n",
"1/1 - 0s - loss: 0.1450 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 546/1000\n",
"1/1 - 0s - loss: 0.1448 - binary_accuracy: 1.0000 - 6ms/epoch - 6ms/step\n",
"Epoch 547/1000\n",
"1/1 - 0s - loss: 0.1446 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 548/1000\n",
"1/1 - 0s - loss: 0.1443 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 549/1000\n",
"1/1 - 0s - loss: 0.1441 - binary_accuracy: 1.0000 - 6ms/epoch - 6ms/step\n",
"Epoch 550/1000\n",
"1/1 - 0s - loss: 0.1439 - binary_accuracy: 1.0000 - 6ms/epoch - 6ms/step\n",
"Epoch 551/1000\n",
"1/1 - 0s - loss: 0.1437 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 552/1000\n",
"1/1 - 0s - loss: 0.1435 - binary_accuracy: 1.0000 - 11ms/epoch - 11ms/step\n",
"Epoch 553/1000\n",
"1/1 - 0s - loss: 0.1432 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 554/1000\n",
"1/1 - 0s - loss: 0.1430 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 555/1000\n",
"1/1 - 0s - loss: 0.1428 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 556/1000\n",
"1/1 - 0s - loss: 0.1426 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 557/1000\n",
"1/1 - 0s - loss: 0.1424 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 558/1000\n",
"1/1 - 0s - loss: 0.1422 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 559/1000\n",
"1/1 - 0s - loss: 0.1420 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 560/1000\n",
"1/1 - 0s - loss: 0.1417 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 561/1000\n",
"1/1 - 0s - loss: 0.1415 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 562/1000\n",
"1/1 - 0s - loss: 0.1413 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 563/1000\n",
"1/1 - 0s - loss: 0.1411 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 564/1000\n",
"1/1 - 0s - loss: 0.1409 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 565/1000\n",
"1/1 - 0s - loss: 0.1407 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 566/1000\n",
"1/1 - 0s - loss: 0.1405 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 567/1000\n",
"1/1 - 0s - loss: 0.1403 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 568/1000\n",
"1/1 - 0s - loss: 0.1400 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 569/1000\n",
"1/1 - 0s - loss: 0.1398 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 570/1000\n",
"1/1 - 0s - loss: 0.1396 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 571/1000\n",
"1/1 - 0s - loss: 0.1394 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 572/1000\n",
"1/1 - 0s - loss: 0.1392 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 573/1000\n",
"1/1 - 0s - loss: 0.1390 - binary_accuracy: 1.0000 - 11ms/epoch - 11ms/step\n",
"Epoch 574/1000\n",
"1/1 - 0s - loss: 0.1388 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 575/1000\n",
"1/1 - 0s - loss: 0.1386 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 576/1000\n",
"1/1 - 0s - loss: 0.1384 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 577/1000\n",
"1/1 - 0s - loss: 0.1382 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 578/1000\n",
"1/1 - 0s - loss: 0.1380 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 579/1000\n",
"1/1 - 0s - loss: 0.1377 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 580/1000\n",
"1/1 - 0s - loss: 0.1375 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 581/1000\n",
"1/1 - 0s - loss: 0.1373 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 582/1000\n",
"1/1 - 0s - loss: 0.1371 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 583/1000\n",
"1/1 - 0s - loss: 0.1369 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 584/1000\n",
"1/1 - 0s - loss: 0.1367 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 585/1000\n",
"1/1 - 0s - loss: 0.1365 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 586/1000\n",
"1/1 - 0s - loss: 0.1363 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 587/1000\n",
"1/1 - 0s - loss: 0.1361 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 588/1000\n",
"1/1 - 0s - loss: 0.1359 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 589/1000\n",
"1/1 - 0s - loss: 0.1357 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 590/1000\n",
"1/1 - 0s - loss: 0.1355 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 591/1000\n",
"1/1 - 0s - loss: 0.1353 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 592/1000\n",
"1/1 - 0s - loss: 0.1351 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 593/1000\n",
"1/1 - 0s - loss: 0.1349 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 594/1000\n",
"1/1 - 0s - loss: 0.1347 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 595/1000\n",
"1/1 - 0s - loss: 0.1345 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 596/1000\n",
"1/1 - 0s - loss: 0.1343 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 597/1000\n",
"1/1 - 0s - loss: 0.1341 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 598/1000\n",
"1/1 - 0s - loss: 0.1339 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 599/1000\n",
"1/1 - 0s - loss: 0.1337 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 600/1000\n",
"1/1 - 0s - loss: 0.1335 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 601/1000\n",
"1/1 - 0s - loss: 0.1333 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 602/1000\n",
"1/1 - 0s - loss: 0.1331 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 603/1000\n",
"1/1 - 0s - loss: 0.1328 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 604/1000\n",
"1/1 - 0s - loss: 0.1327 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 605/1000\n",
"1/1 - 0s - loss: 0.1325 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 606/1000\n",
"1/1 - 0s - loss: 0.1322 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 607/1000\n",
"1/1 - 0s - loss: 0.1320 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 608/1000\n",
"1/1 - 0s - loss: 0.1319 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 609/1000\n",
"1/1 - 0s - loss: 0.1317 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 610/1000\n",
"1/1 - 0s - loss: 0.1315 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 611/1000\n",
"1/1 - 0s - loss: 0.1313 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 612/1000\n",
"1/1 - 0s - loss: 0.1311 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 613/1000\n",
"1/1 - 0s - loss: 0.1309 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 614/1000\n",
"1/1 - 0s - loss: 0.1307 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 615/1000\n",
"1/1 - 0s - loss: 0.1305 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 616/1000\n",
"1/1 - 0s - loss: 0.1303 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 617/1000\n",
"1/1 - 0s - loss: 0.1301 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 618/1000\n",
"1/1 - 0s - loss: 0.1299 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 619/1000\n",
"1/1 - 0s - loss: 0.1297 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 620/1000\n",
"1/1 - 0s - loss: 0.1295 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 621/1000\n",
"1/1 - 0s - loss: 0.1293 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 622/1000\n",
"1/1 - 0s - loss: 0.1291 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 623/1000\n",
"1/1 - 0s - loss: 0.1289 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 624/1000\n",
"1/1 - 0s - loss: 0.1287 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 625/1000\n",
"1/1 - 0s - loss: 0.1285 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 626/1000\n",
"1/1 - 0s - loss: 0.1283 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 627/1000\n",
"1/1 - 0s - loss: 0.1281 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 628/1000\n",
"1/1 - 0s - loss: 0.1280 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 629/1000\n",
"1/1 - 0s - loss: 0.1278 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 630/1000\n",
"1/1 - 0s - loss: 0.1276 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 631/1000\n",
"1/1 - 0s - loss: 0.1274 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 632/1000\n",
"1/1 - 0s - loss: 0.1272 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 633/1000\n",
"1/1 - 0s - loss: 0.1270 - binary_accuracy: 1.0000 - 11ms/epoch - 11ms/step\n",
"Epoch 634/1000\n",
"1/1 - 0s - loss: 0.1268 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 635/1000\n",
"1/1 - 0s - loss: 0.1266 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 636/1000\n",
"1/1 - 0s - loss: 0.1264 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 637/1000\n",
"1/1 - 0s - loss: 0.1262 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 638/1000\n",
"1/1 - 0s - loss: 0.1260 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 639/1000\n",
"1/1 - 0s - loss: 0.1259 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 640/1000\n",
"1/1 - 0s - loss: 0.1257 - binary_accuracy: 1.0000 - 11ms/epoch - 11ms/step\n",
"Epoch 641/1000\n",
"1/1 - 0s - loss: 0.1255 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 642/1000\n",
"1/1 - 0s - loss: 0.1253 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 643/1000\n",
"1/1 - 0s - loss: 0.1251 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 644/1000\n",
"1/1 - 0s - loss: 0.1249 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 645/1000\n",
"1/1 - 0s - loss: 0.1247 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 646/1000\n",
"1/1 - 0s - loss: 0.1245 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 647/1000\n",
"1/1 - 0s - loss: 0.1243 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 648/1000\n",
"1/1 - 0s - loss: 0.1241 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 649/1000\n",
"1/1 - 0s - loss: 0.1240 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 650/1000\n",
"1/1 - 0s - loss: 0.1238 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 651/1000\n",
"1/1 - 0s - loss: 0.1236 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 652/1000\n",
"1/1 - 0s - loss: 0.1234 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 653/1000\n",
"1/1 - 0s - loss: 0.1232 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 654/1000\n",
"1/1 - 0s - loss: 0.1230 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 655/1000\n",
"1/1 - 0s - loss: 0.1229 - binary_accuracy: 1.0000 - 12ms/epoch - 12ms/step\n",
"Epoch 656/1000\n",
"1/1 - 0s - loss: 0.1227 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 657/1000\n",
"1/1 - 0s - loss: 0.1225 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 658/1000\n",
"1/1 - 0s - loss: 0.1223 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 659/1000\n",
"1/1 - 0s - loss: 0.1221 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 660/1000\n",
"1/1 - 0s - loss: 0.1219 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 661/1000\n",
"1/1 - 0s - loss: 0.1218 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 662/1000\n",
"1/1 - 0s - loss: 0.1216 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 663/1000\n",
"1/1 - 0s - loss: 0.1214 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 664/1000\n",
"1/1 - 0s - loss: 0.1212 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 665/1000\n",
"1/1 - 0s - loss: 0.1210 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 666/1000\n",
"1/1 - 0s - loss: 0.1208 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 667/1000\n",
"1/1 - 0s - loss: 0.1207 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 668/1000\n",
"1/1 - 0s - loss: 0.1205 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 669/1000\n",
"1/1 - 0s - loss: 0.1203 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 670/1000\n",
"1/1 - 0s - loss: 0.1201 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 671/1000\n",
"1/1 - 0s - loss: 0.1199 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 672/1000\n",
"1/1 - 0s - loss: 0.1197 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 673/1000\n",
"1/1 - 0s - loss: 0.1196 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 674/1000\n",
"1/1 - 0s - loss: 0.1194 - binary_accuracy: 1.0000 - 16ms/epoch - 16ms/step\n",
"Epoch 675/1000\n",
"1/1 - 0s - loss: 0.1192 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 676/1000\n",
"1/1 - 0s - loss: 0.1190 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 677/1000\n",
"1/1 - 0s - loss: 0.1189 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 678/1000\n",
"1/1 - 0s - loss: 0.1187 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 679/1000\n",
"1/1 - 0s - loss: 0.1185 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 680/1000\n",
"1/1 - 0s - loss: 0.1183 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 681/1000\n",
"1/1 - 0s - loss: 0.1181 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 682/1000\n",
"1/1 - 0s - loss: 0.1180 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 683/1000\n",
"1/1 - 0s - loss: 0.1178 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 684/1000\n",
"1/1 - 0s - loss: 0.1176 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 685/1000\n",
"1/1 - 0s - loss: 0.1174 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 686/1000\n",
"1/1 - 0s - loss: 0.1172 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 687/1000\n",
"1/1 - 0s - loss: 0.1171 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 688/1000\n",
"1/1 - 0s - loss: 0.1169 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 689/1000\n",
"1/1 - 0s - loss: 0.1167 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 690/1000\n",
"1/1 - 0s - loss: 0.1165 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 691/1000\n",
"1/1 - 0s - loss: 0.1164 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 692/1000\n",
"1/1 - 0s - loss: 0.1162 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 693/1000\n",
"1/1 - 0s - loss: 0.1160 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 694/1000\n",
"1/1 - 0s - loss: 0.1158 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 695/1000\n",
"1/1 - 0s - loss: 0.1157 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 696/1000\n",
"1/1 - 0s - loss: 0.1155 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 697/1000\n",
"1/1 - 0s - loss: 0.1153 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 698/1000\n",
"1/1 - 0s - loss: 0.1151 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 699/1000\n",
"1/1 - 0s - loss: 0.1150 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 700/1000\n",
"1/1 - 0s - loss: 0.1148 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 701/1000\n",
"1/1 - 0s - loss: 0.1146 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 702/1000\n",
"1/1 - 0s - loss: 0.1145 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 703/1000\n",
"1/1 - 0s - loss: 0.1143 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 704/1000\n",
"1/1 - 0s - loss: 0.1141 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 705/1000\n",
"1/1 - 0s - loss: 0.1139 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 706/1000\n",
"1/1 - 0s - loss: 0.1138 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 707/1000\n",
"1/1 - 0s - loss: 0.1136 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 708/1000\n",
"1/1 - 0s - loss: 0.1134 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 709/1000\n",
"1/1 - 0s - loss: 0.1132 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 710/1000\n",
"1/1 - 0s - loss: 0.1131 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 711/1000\n",
"1/1 - 0s - loss: 0.1129 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 712/1000\n",
"1/1 - 0s - loss: 0.1127 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 713/1000\n",
"1/1 - 0s - loss: 0.1126 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 714/1000\n",
"1/1 - 0s - loss: 0.1124 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 715/1000\n",
"1/1 - 0s - loss: 0.1122 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 716/1000\n",
"1/1 - 0s - loss: 0.1120 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 717/1000\n",
"1/1 - 0s - loss: 0.1119 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 718/1000\n",
"1/1 - 0s - loss: 0.1117 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 719/1000\n",
"1/1 - 0s - loss: 0.1115 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 720/1000\n",
"1/1 - 0s - loss: 0.1114 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 721/1000\n",
"1/1 - 0s - loss: 0.1112 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 722/1000\n",
"1/1 - 0s - loss: 0.1110 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 723/1000\n",
"1/1 - 0s - loss: 0.1109 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 724/1000\n",
"1/1 - 0s - loss: 0.1107 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 725/1000\n",
"1/1 - 0s - loss: 0.1105 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 726/1000\n",
"1/1 - 0s - loss: 0.1103 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 727/1000\n",
"1/1 - 0s - loss: 0.1102 - binary_accuracy: 1.0000 - 14ms/epoch - 14ms/step\n",
"Epoch 728/1000\n",
"1/1 - 0s - loss: 0.1100 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 729/1000\n",
"1/1 - 0s - loss: 0.1099 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 730/1000\n",
"1/1 - 0s - loss: 0.1097 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 731/1000\n",
"1/1 - 0s - loss: 0.1095 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 732/1000\n",
"1/1 - 0s - loss: 0.1094 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 733/1000\n",
"1/1 - 0s - loss: 0.1092 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 734/1000\n",
"1/1 - 0s - loss: 0.1090 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 735/1000\n",
"1/1 - 0s - loss: 0.1088 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 736/1000\n",
"1/1 - 0s - loss: 0.1087 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 737/1000\n",
"1/1 - 0s - loss: 0.1085 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 738/1000\n",
"1/1 - 0s - loss: 0.1084 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 739/1000\n",
"1/1 - 0s - loss: 0.1082 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 740/1000\n",
"1/1 - 0s - loss: 0.1080 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 741/1000\n",
"1/1 - 0s - loss: 0.1079 - binary_accuracy: 1.0000 - 11ms/epoch - 11ms/step\n",
"Epoch 742/1000\n",
"1/1 - 0s - loss: 0.1077 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 743/1000\n",
"1/1 - 0s - loss: 0.1075 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 744/1000\n",
"1/1 - 0s - loss: 0.1074 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 745/1000\n",
"1/1 - 0s - loss: 0.1072 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 746/1000\n",
"1/1 - 0s - loss: 0.1070 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 747/1000\n",
"1/1 - 0s - loss: 0.1069 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 748/1000\n",
"1/1 - 0s - loss: 0.1067 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 749/1000\n",
"1/1 - 0s - loss: 0.1065 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 750/1000\n",
"1/1 - 0s - loss: 0.1064 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 751/1000\n",
"1/1 - 0s - loss: 0.1062 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 752/1000\n",
"1/1 - 0s - loss: 0.1060 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 753/1000\n",
"1/1 - 0s - loss: 0.1059 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 754/1000\n",
"1/1 - 0s - loss: 0.1057 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 755/1000\n",
"1/1 - 0s - loss: 0.1056 - binary_accuracy: 1.0000 - 6ms/epoch - 6ms/step\n",
"Epoch 756/1000\n",
"1/1 - 0s - loss: 0.1054 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 757/1000\n",
"1/1 - 0s - loss: 0.1052 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 758/1000\n",
"1/1 - 0s - loss: 0.1051 - binary_accuracy: 1.0000 - 6ms/epoch - 6ms/step\n",
"Epoch 759/1000\n",
"1/1 - 0s - loss: 0.1049 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 760/1000\n",
"1/1 - 0s - loss: 0.1048 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 761/1000\n",
"1/1 - 0s - loss: 0.1046 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 762/1000\n",
"1/1 - 0s - loss: 0.1044 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 763/1000\n",
"1/1 - 0s - loss: 0.1043 - binary_accuracy: 1.0000 - 6ms/epoch - 6ms/step\n",
"Epoch 764/1000\n",
"1/1 - 0s - loss: 0.1041 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 765/1000\n",
"1/1 - 0s - loss: 0.1040 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 766/1000\n",
"1/1 - 0s - loss: 0.1038 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 767/1000\n",
"1/1 - 0s - loss: 0.1036 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 768/1000\n",
"1/1 - 0s - loss: 0.1035 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 769/1000\n",
"1/1 - 0s - loss: 0.1033 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 770/1000\n",
"1/1 - 0s - loss: 0.1032 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 771/1000\n",
"1/1 - 0s - loss: 0.1030 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 772/1000\n",
"1/1 - 0s - loss: 0.1028 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 773/1000\n",
"1/1 - 0s - loss: 0.1027 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 774/1000\n",
"1/1 - 0s - loss: 0.1025 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 775/1000\n",
"1/1 - 0s - loss: 0.1024 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 776/1000\n",
"1/1 - 0s - loss: 0.1022 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 777/1000\n",
"1/1 - 0s - loss: 0.1021 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 778/1000\n",
"1/1 - 0s - loss: 0.1019 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 779/1000\n",
"1/1 - 0s - loss: 0.1017 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 780/1000\n",
"1/1 - 0s - loss: 0.1016 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 781/1000\n",
"1/1 - 0s - loss: 0.1014 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 782/1000\n",
"1/1 - 0s - loss: 0.1013 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 783/1000\n",
"1/1 - 0s - loss: 0.1011 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 784/1000\n",
"1/1 - 0s - loss: 0.1009 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 785/1000\n",
"1/1 - 0s - loss: 0.1008 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 786/1000\n",
"1/1 - 0s - loss: 0.1006 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 787/1000\n",
"1/1 - 0s - loss: 0.1005 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 788/1000\n",
"1/1 - 0s - loss: 0.1003 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 789/1000\n",
"1/1 - 0s - loss: 0.1002 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 790/1000\n",
"1/1 - 0s - loss: 0.1000 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 791/1000\n",
"1/1 - 0s - loss: 0.0999 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 792/1000\n",
"1/1 - 0s - loss: 0.0997 - binary_accuracy: 1.0000 - 11ms/epoch - 11ms/step\n",
"Epoch 793/1000\n",
"1/1 - 0s - loss: 0.0995 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 794/1000\n",
"1/1 - 0s - loss: 0.0994 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 795/1000\n",
"1/1 - 0s - loss: 0.0992 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 796/1000\n",
"1/1 - 0s - loss: 0.0991 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 797/1000\n",
"1/1 - 0s - loss: 0.0989 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 798/1000\n",
"1/1 - 0s - loss: 0.0988 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 799/1000\n",
"1/1 - 0s - loss: 0.0986 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 800/1000\n",
"1/1 - 0s - loss: 0.0985 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 801/1000\n",
"1/1 - 0s - loss: 0.0983 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 802/1000\n",
"1/1 - 0s - loss: 0.0981 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 803/1000\n",
"1/1 - 0s - loss: 0.0980 - binary_accuracy: 1.0000 - 12ms/epoch - 12ms/step\n",
"Epoch 804/1000\n",
"1/1 - 0s - loss: 0.0978 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 805/1000\n",
"1/1 - 0s - loss: 0.0977 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 806/1000\n",
"1/1 - 0s - loss: 0.0975 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 807/1000\n",
"1/1 - 0s - loss: 0.0974 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 808/1000\n",
"1/1 - 0s - loss: 0.0972 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 809/1000\n",
"1/1 - 0s - loss: 0.0971 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 810/1000\n",
"1/1 - 0s - loss: 0.0969 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 811/1000\n",
"1/1 - 0s - loss: 0.0968 - binary_accuracy: 1.0000 - 5ms/epoch - 5ms/step\n",
"Epoch 812/1000\n",
"1/1 - 0s - loss: 0.0966 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 813/1000\n",
"1/1 - 0s - loss: 0.0965 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 814/1000\n",
"1/1 - 0s - loss: 0.0963 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 815/1000\n",
"1/1 - 0s - loss: 0.0962 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 816/1000\n",
"1/1 - 0s - loss: 0.0960 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 817/1000\n",
"1/1 - 0s - loss: 0.0959 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 818/1000\n",
"1/1 - 0s - loss: 0.0957 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 819/1000\n",
"1/1 - 0s - loss: 0.0956 - binary_accuracy: 1.0000 - 12ms/epoch - 12ms/step\n",
"Epoch 820/1000\n",
"1/1 - 0s - loss: 0.0954 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 821/1000\n",
"1/1 - 0s - loss: 0.0953 - binary_accuracy: 1.0000 - 11ms/epoch - 11ms/step\n",
"Epoch 822/1000\n",
"1/1 - 0s - loss: 0.0951 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 823/1000\n",
"1/1 - 0s - loss: 0.0950 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 824/1000\n",
"1/1 - 0s - loss: 0.0948 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 825/1000\n",
"1/1 - 0s - loss: 0.0947 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 826/1000\n",
"1/1 - 0s - loss: 0.0945 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 827/1000\n",
"1/1 - 0s - loss: 0.0944 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 828/1000\n",
"1/1 - 0s - loss: 0.0942 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 829/1000\n",
"1/1 - 0s - loss: 0.0941 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 830/1000\n",
"1/1 - 0s - loss: 0.0939 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 831/1000\n",
"1/1 - 0s - loss: 0.0938 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 832/1000\n",
"1/1 - 0s - loss: 0.0936 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 833/1000\n",
"1/1 - 0s - loss: 0.0935 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 834/1000\n",
"1/1 - 0s - loss: 0.0933 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 835/1000\n",
"1/1 - 0s - loss: 0.0932 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 836/1000\n",
"1/1 - 0s - loss: 0.0930 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 837/1000\n",
"1/1 - 0s - loss: 0.0929 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 838/1000\n",
"1/1 - 0s - loss: 0.0927 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 839/1000\n",
"1/1 - 0s - loss: 0.0926 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 840/1000\n",
"1/1 - 0s - loss: 0.0924 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 841/1000\n",
"1/1 - 0s - loss: 0.0923 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 842/1000\n",
"1/1 - 0s - loss: 0.0921 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 843/1000\n",
"1/1 - 0s - loss: 0.0920 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 844/1000\n",
"1/1 - 0s - loss: 0.0918 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 845/1000\n",
"1/1 - 0s - loss: 0.0917 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 846/1000\n",
"1/1 - 0s - loss: 0.0915 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 847/1000\n",
"1/1 - 0s - loss: 0.0914 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 848/1000\n",
"1/1 - 0s - loss: 0.0913 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 849/1000\n",
"1/1 - 0s - loss: 0.0911 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 850/1000\n",
"1/1 - 0s - loss: 0.0910 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 851/1000\n",
"1/1 - 0s - loss: 0.0908 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 852/1000\n",
"1/1 - 0s - loss: 0.0907 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 853/1000\n",
"1/1 - 0s - loss: 0.0905 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 854/1000\n",
"1/1 - 0s - loss: 0.0904 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 855/1000\n",
"1/1 - 0s - loss: 0.0902 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 856/1000\n",
"1/1 - 0s - loss: 0.0901 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 857/1000\n",
"1/1 - 0s - loss: 0.0899 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 858/1000\n",
"1/1 - 0s - loss: 0.0898 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 859/1000\n",
"1/1 - 0s - loss: 0.0896 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 860/1000\n",
"1/1 - 0s - loss: 0.0895 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 861/1000\n",
"1/1 - 0s - loss: 0.0894 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 862/1000\n",
"1/1 - 0s - loss: 0.0892 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 863/1000\n",
"1/1 - 0s - loss: 0.0891 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 864/1000\n",
"1/1 - 0s - loss: 0.0889 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 865/1000\n",
"1/1 - 0s - loss: 0.0888 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 866/1000\n",
"1/1 - 0s - loss: 0.0886 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 867/1000\n",
"1/1 - 0s - loss: 0.0885 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 868/1000\n",
"1/1 - 0s - loss: 0.0883 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 869/1000\n",
"1/1 - 0s - loss: 0.0882 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 870/1000\n",
"1/1 - 0s - loss: 0.0881 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 871/1000\n",
"1/1 - 0s - loss: 0.0879 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 872/1000\n",
"1/1 - 0s - loss: 0.0878 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 873/1000\n",
"1/1 - 0s - loss: 0.0876 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 874/1000\n",
"1/1 - 0s - loss: 0.0875 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 875/1000\n",
"1/1 - 0s - loss: 0.0874 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 876/1000\n",
"1/1 - 0s - loss: 0.0872 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 877/1000\n",
"1/1 - 0s - loss: 0.0871 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 878/1000\n",
"1/1 - 0s - loss: 0.0869 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 879/1000\n",
"1/1 - 0s - loss: 0.0868 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 880/1000\n",
"1/1 - 0s - loss: 0.0866 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 881/1000\n",
"1/1 - 0s - loss: 0.0865 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 882/1000\n",
"1/1 - 0s - loss: 0.0864 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 883/1000\n",
"1/1 - 0s - loss: 0.0862 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 884/1000\n",
"1/1 - 0s - loss: 0.0861 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 885/1000\n",
"1/1 - 0s - loss: 0.0859 - binary_accuracy: 1.0000 - 11ms/epoch - 11ms/step\n",
"Epoch 886/1000\n",
"1/1 - 0s - loss: 0.0858 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 887/1000\n",
"1/1 - 0s - loss: 0.0857 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 888/1000\n",
"1/1 - 0s - loss: 0.0855 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 889/1000\n",
"1/1 - 0s - loss: 0.0854 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 890/1000\n",
"1/1 - 0s - loss: 0.0852 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 891/1000\n",
"1/1 - 0s - loss: 0.0851 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 892/1000\n",
"1/1 - 0s - loss: 0.0850 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 893/1000\n",
"1/1 - 0s - loss: 0.0848 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 894/1000\n",
"1/1 - 0s - loss: 0.0847 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 895/1000\n",
"1/1 - 0s - loss: 0.0845 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 896/1000\n",
"1/1 - 0s - loss: 0.0844 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 897/1000\n",
"1/1 - 0s - loss: 0.0842 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 898/1000\n",
"1/1 - 0s - loss: 0.0841 - binary_accuracy: 1.0000 - 12ms/epoch - 12ms/step\n",
"Epoch 899/1000\n",
"1/1 - 0s - loss: 0.0840 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 900/1000\n",
"1/1 - 0s - loss: 0.0838 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 901/1000\n",
"1/1 - 0s - loss: 0.0837 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 902/1000\n",
"1/1 - 0s - loss: 0.0836 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 903/1000\n",
"1/1 - 0s - loss: 0.0834 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 904/1000\n",
"1/1 - 0s - loss: 0.0833 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 905/1000\n",
"1/1 - 0s - loss: 0.0832 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 906/1000\n",
"1/1 - 0s - loss: 0.0830 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 907/1000\n",
"1/1 - 0s - loss: 0.0829 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 908/1000\n",
"1/1 - 0s - loss: 0.0827 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 909/1000\n",
"1/1 - 0s - loss: 0.0826 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 910/1000\n",
"1/1 - 0s - loss: 0.0825 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 911/1000\n",
"1/1 - 0s - loss: 0.0823 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 912/1000\n",
"1/1 - 0s - loss: 0.0822 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 913/1000\n",
"1/1 - 0s - loss: 0.0821 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 914/1000\n",
"1/1 - 0s - loss: 0.0819 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 915/1000\n",
"1/1 - 0s - loss: 0.0818 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 916/1000\n",
"1/1 - 0s - loss: 0.0817 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 917/1000\n",
"1/1 - 0s - loss: 0.0815 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 918/1000\n",
"1/1 - 0s - loss: 0.0814 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 919/1000\n",
"1/1 - 0s - loss: 0.0812 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 920/1000\n",
"1/1 - 0s - loss: 0.0811 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 921/1000\n",
"1/1 - 0s - loss: 0.0810 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 922/1000\n",
"1/1 - 0s - loss: 0.0808 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 923/1000\n",
"1/1 - 0s - loss: 0.0807 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 924/1000\n",
"1/1 - 0s - loss: 0.0806 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 925/1000\n",
"1/1 - 0s - loss: 0.0804 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 926/1000\n",
"1/1 - 0s - loss: 0.0803 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 927/1000\n",
"1/1 - 0s - loss: 0.0802 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 928/1000\n",
"1/1 - 0s - loss: 0.0800 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 929/1000\n",
"1/1 - 0s - loss: 0.0799 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 930/1000\n",
"1/1 - 0s - loss: 0.0798 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 931/1000\n",
"1/1 - 0s - loss: 0.0796 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 932/1000\n",
"1/1 - 0s - loss: 0.0795 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 933/1000\n",
"1/1 - 0s - loss: 0.0794 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 934/1000\n",
"1/1 - 0s - loss: 0.0792 - binary_accuracy: 1.0000 - 11ms/epoch - 11ms/step\n",
"Epoch 935/1000\n",
"1/1 - 0s - loss: 0.0791 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 936/1000\n",
"1/1 - 0s - loss: 0.0790 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 937/1000\n",
"1/1 - 0s - loss: 0.0788 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 938/1000\n",
"1/1 - 0s - loss: 0.0787 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 939/1000\n",
"1/1 - 0s - loss: 0.0786 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 940/1000\n",
"1/1 - 0s - loss: 0.0784 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 941/1000\n",
"1/1 - 0s - loss: 0.0783 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 942/1000\n",
"1/1 - 0s - loss: 0.0782 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 943/1000\n",
"1/1 - 0s - loss: 0.0780 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 944/1000\n",
"1/1 - 0s - loss: 0.0779 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 945/1000\n",
"1/1 - 0s - loss: 0.0778 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 946/1000\n",
"1/1 - 0s - loss: 0.0777 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 947/1000\n",
"1/1 - 0s - loss: 0.0775 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 948/1000\n",
"1/1 - 0s - loss: 0.0774 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 949/1000\n",
"1/1 - 0s - loss: 0.0773 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 950/1000\n",
"1/1 - 0s - loss: 0.0771 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 951/1000\n",
"1/1 - 0s - loss: 0.0770 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 952/1000\n",
"1/1 - 0s - loss: 0.0769 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 953/1000\n",
"1/1 - 0s - loss: 0.0767 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 954/1000\n",
"1/1 - 0s - loss: 0.0766 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 955/1000\n",
"1/1 - 0s - loss: 0.0765 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 956/1000\n",
"1/1 - 0s - loss: 0.0764 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 957/1000\n",
"1/1 - 0s - loss: 0.0762 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 958/1000\n",
"1/1 - 0s - loss: 0.0761 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 959/1000\n",
"1/1 - 0s - loss: 0.0760 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 960/1000\n",
"1/1 - 0s - loss: 0.0758 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 961/1000\n",
"1/1 - 0s - loss: 0.0757 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 962/1000\n",
"1/1 - 0s - loss: 0.0756 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 963/1000\n",
"1/1 - 0s - loss: 0.0755 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 964/1000\n",
"1/1 - 0s - loss: 0.0753 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 965/1000\n",
"1/1 - 0s - loss: 0.0752 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 966/1000\n",
"1/1 - 0s - loss: 0.0751 - binary_accuracy: 1.0000 - 12ms/epoch - 12ms/step\n",
"Epoch 967/1000\n",
"1/1 - 0s - loss: 0.0749 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 968/1000\n",
"1/1 - 0s - loss: 0.0748 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 969/1000\n",
"1/1 - 0s - loss: 0.0747 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 970/1000\n",
"1/1 - 0s - loss: 0.0746 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 971/1000\n",
"1/1 - 0s - loss: 0.0744 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 972/1000\n",
"1/1 - 0s - loss: 0.0743 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 973/1000\n",
"1/1 - 0s - loss: 0.0742 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 974/1000\n",
"1/1 - 0s - loss: 0.0741 - binary_accuracy: 1.0000 - 11ms/epoch - 11ms/step\n",
"Epoch 975/1000\n",
"1/1 - 0s - loss: 0.0739 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 976/1000\n",
"1/1 - 0s - loss: 0.0738 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 977/1000\n",
"1/1 - 0s - loss: 0.0737 - binary_accuracy: 1.0000 - 11ms/epoch - 11ms/step\n",
"Epoch 978/1000\n",
"1/1 - 0s - loss: 0.0735 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 979/1000\n",
"1/1 - 0s - loss: 0.0734 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 980/1000\n",
"1/1 - 0s - loss: 0.0733 - binary_accuracy: 1.0000 - 11ms/epoch - 11ms/step\n",
"Epoch 981/1000\n",
"1/1 - 0s - loss: 0.0732 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 982/1000\n",
"1/1 - 0s - loss: 0.0730 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 983/1000\n",
"1/1 - 0s - loss: 0.0729 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 984/1000\n",
"1/1 - 0s - loss: 0.0728 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 985/1000\n",
"1/1 - 0s - loss: 0.0727 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 986/1000\n",
"1/1 - 0s - loss: 0.0726 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 987/1000\n",
"1/1 - 0s - loss: 0.0724 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 988/1000\n",
"1/1 - 0s - loss: 0.0723 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 989/1000\n",
"1/1 - 0s - loss: 0.0722 - binary_accuracy: 1.0000 - 7ms/epoch - 7ms/step\n",
"Epoch 990/1000\n",
"1/1 - 0s - loss: 0.0721 - binary_accuracy: 1.0000 - 10ms/epoch - 10ms/step\n",
"Epoch 991/1000\n",
"1/1 - 0s - loss: 0.0719 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 992/1000\n",
"1/1 - 0s - loss: 0.0718 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 993/1000\n",
"1/1 - 0s - loss: 0.0717 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 994/1000\n",
"1/1 - 0s - loss: 0.0716 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 995/1000\n",
"1/1 - 0s - loss: 0.0714 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 996/1000\n",
"1/1 - 0s - loss: 0.0713 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 997/1000\n",
"1/1 - 0s - loss: 0.0712 - binary_accuracy: 1.0000 - 8ms/epoch - 8ms/step\n",
"Epoch 998/1000\n",
"1/1 - 0s - loss: 0.0711 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 999/1000\n",
"1/1 - 0s - loss: 0.0710 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"Epoch 1000/1000\n",
"1/1 - 0s - loss: 0.0708 - binary_accuracy: 1.0000 - 9ms/epoch - 9ms/step\n",
"1/1 [==============================] - 0s 46ms/step\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
],
"image/png": "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\n"
},
"metadata": {}
}
]
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment