{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "name": "DNN on pima.ipynb", "provenance": [] }, "kernelspec": { "display_name": "Python 3", "name": "python3" }, "language_info": { "name": "python" } }, "cells": [ { "cell_type": "code", "metadata": { "colab": { "resources": { "http://localhost:8080/nbextensions/google.colab/files.js": { "data": "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", "ok": true, "headers": [ [ "content-type", "application/javascript" ] ], "status": 200, "status_text": "OK" } }, "base_uri": "https://localhost:8080/", "height": 484 }, "id": "Qw0pwVfzQ4wg", "outputId": "f8b0b74a-a6bd-4af6-de3e-f1d7d7f77511" }, "source": [ "from google.colab import files\n", "import pandas as pd\n", "uploaded = files.upload()\n", "import io \n", "dataset = pd.read_csv(io.BytesIO(uploaded['pimadiabetes.csv']))\n", "dataset" ], "execution_count": 10, "outputs": [ { "output_type": "display_data", "data": { "text/html": [ "\n", " \n", " \n", " Upload widget is only available when the cell has been executed in the\n", " current browser session. Please rerun this cell to enable.\n", " \n", " " ], "text/plain": [ "" ] }, "metadata": { "tags": [] } }, { "output_type": "stream", "text": [ "Saving pimadiabetes.csv to pimadiabetes (3).csv\n" ], "name": "stdout" }, { "output_type": "execute_result", "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
PregnanciesGlucoseBloodPressureSkinThicknessInsulinBMIDiabetesPedigreeFunctionAgeOutcome
061487235033.60.627501
11856629026.60.351310
28183640023.30.672321
318966239428.10.167210
40137403516843.12.288331
..............................
76310101764818032.90.171630
76421227027036.80.340270
7655121722311226.20.245300
7661126600030.10.349471
7671937031030.40.315230
\n", "

768 rows × 9 columns

\n", "
" ], "text/plain": [ " Pregnancies Glucose ... Age Outcome\n", "0 6 148 ... 50 1\n", "1 1 85 ... 31 0\n", "2 8 183 ... 32 1\n", "3 1 89 ... 21 0\n", "4 0 137 ... 33 1\n", ".. ... ... ... ... ...\n", "763 10 101 ... 63 0\n", "764 2 122 ... 27 0\n", "765 5 121 ... 30 0\n", "766 1 126 ... 47 1\n", "767 1 93 ... 23 0\n", "\n", "[768 rows x 9 columns]" ] }, "metadata": { "tags": [] }, "execution_count": 10 } ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "8uHo_DrxRr5X", "outputId": "a779bbf8-689e-42af-aea1-6acbbec38740" }, "source": [ "#import all libraries\n", "\n", "import tensorflow as tf\n", "from numpy import loadtxt\n", "from keras.models import Sequential\n", "from keras.layers import Dense\n", "from sklearn.model_selection import train_test_split\n", "from sklearn import preprocessing\n", "\n", "X = dataset.iloc[:,0:8].values\n", "Y = dataset.iloc[:,8].values\n", "X = preprocessing.scale(X)\n", "x_train,x_test,y_train,y_test=train_test_split(X,Y,test_size=0.2, random_state=2)\n", "\n", "#define the keras models\n", "model = Sequential()\n", "model.add(Dense(16, input_dim=8, activation='relu'))\n", "model.add(Dense(14, activation='relu'))\n", "model.add(Dense(12,activation ='relu'))\n", "\n", "model.add(Dense(10, input_dim=6, activation='relu'))\n", "model.add(Dense(8, activation='relu'))\n", "model.add(Dense(6,activation ='relu'))\n", "\n", "model.add(Dense(6, input_dim=4, activation='relu'))\n", "model.add(Dense(4, activation='relu'))\n", "model.add(Dense(1,activation ='sigmoid'))\n", "model.summary()" ], "execution_count": 11, "outputs": [ { "output_type": "stream", "text": [ "Model: \"sequential_2\"\n", "_________________________________________________________________\n", "Layer (type) Output Shape Param # \n", "=================================================================\n", "dense_18 (Dense) (None, 16) 144 \n", "_________________________________________________________________\n", "dense_19 (Dense) (None, 14) 238 \n", "_________________________________________________________________\n", "dense_20 (Dense) (None, 12) 180 \n", "_________________________________________________________________\n", "dense_21 (Dense) (None, 10) 130 \n", "_________________________________________________________________\n", "dense_22 (Dense) (None, 8) 88 \n", "_________________________________________________________________\n", "dense_23 (Dense) (None, 6) 54 \n", "_________________________________________________________________\n", "dense_24 (Dense) (None, 6) 42 \n", "_________________________________________________________________\n", "dense_25 (Dense) (None, 4) 28 \n", "_________________________________________________________________\n", "dense_26 (Dense) (None, 1) 5 \n", "=================================================================\n", "Total params: 909\n", "Trainable params: 909\n", "Non-trainable params: 0\n", "_________________________________________________________________\n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "vJX-yDwdSRus", "outputId": "302ed56e-83b4-421b-b0fa-a353a838245d" }, "source": [ "#Compile the model\n", "model.compile(loss=\"binary_crossentropy\", optimizer=\"adam\", metrics=['accuracy'])\n", "\n", "#fit the keras model on the dataset\n", "history=model.fit(X,Y, epochs=500, batch_size=50 )\n", "\n", "#evaluate the keras model\n", "_,accuracy = model.evaluate(x_train,y_train)\n", "print('Train Accuracy: %.2f' % (accuracy*100))\n", "predictions = model.predict_classes(x_train)\n", "\n", "_,accuracy = model.evaluate(x_test,y_test)\n", "print('Test Accuracy: %.2f' % (accuracy*100))\n", "predictions = model.predict_classes(x_test)\n", "\n", "\n", "# summarize the first 15 cases\n", "for i in range(15):\n", "\tprint('%s => %d (expected %d)' % (x_test[i].tolist(), predictions[i], y_test[i]))\n" ], "execution_count": 35, "outputs": [ { "output_type": "stream", "text": [ "Epoch 1/500\n", "16/16 [==============================] - 1s 2ms/step - loss: 0.0109 - accuracy: 0.9983\n", "Epoch 2/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 0.0335 - accuracy: 0.9941\n", "Epoch 3/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 0.1022 - accuracy: 0.9878\n", "Epoch 4/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 0.0109 - accuracy: 0.9975\n", "Epoch 5/500\n", "16/16 [==============================] - 0s 1ms/step - loss: 0.0203 - accuracy: 0.9966\n", "Epoch 6/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.1338e-04 - accuracy: 1.0000\n", "Epoch 7/500\n", "16/16 [==============================] - 0s 1ms/step - loss: 0.0020 - accuracy: 0.9994\n", "Epoch 8/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 0.0090 - accuracy: 0.9986\n", "Epoch 9/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 0.0063 - accuracy: 0.9979\n", "Epoch 10/500\n", "16/16 [==============================] - 0s 1ms/step - loss: 0.0990 - accuracy: 0.9957\n", "Epoch 11/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 0.1019 - accuracy: 0.9943\n", "Epoch 12/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 0.0529 - accuracy: 0.9923\n", "Epoch 13/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 0.0657 - accuracy: 0.9890\n", "Epoch 14/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 0.0463 - accuracy: 0.9923\n", "Epoch 15/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 0.0336 - accuracy: 0.9928\n", "Epoch 16/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 0.0128 - accuracy: 0.9952\n", "Epoch 17/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 0.0163 - accuracy: 0.9957\n", "Epoch 18/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 0.0059 - accuracy: 0.9981\n", "Epoch 19/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 0.0031 - accuracy: 1.0000\n", "Epoch 20/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.9593e-04 - accuracy: 1.0000\n", "Epoch 21/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.5930e-04 - accuracy: 1.0000\n", "Epoch 22/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.2290e-04 - accuracy: 1.0000\n", "Epoch 23/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.9363e-04 - accuracy: 1.0000\n", "Epoch 24/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.5696e-04 - accuracy: 1.0000\n", "Epoch 25/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.9473e-04 - accuracy: 1.0000\n", "Epoch 26/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.5746e-04 - accuracy: 1.0000\n", "Epoch 27/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.2536e-04 - accuracy: 1.0000\n", "Epoch 28/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.8620e-04 - accuracy: 1.0000\n", "Epoch 29/500\n", "16/16 [==============================] - 0s 1ms/step - loss: 1.2136e-04 - accuracy: 1.0000\n", "Epoch 30/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.3163e-04 - accuracy: 1.0000\n", "Epoch 31/500\n", "16/16 [==============================] - 0s 1ms/step - loss: 8.3302e-05 - accuracy: 1.0000\n", "Epoch 32/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 8.6653e-05 - accuracy: 1.0000\n", "Epoch 33/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 8.6600e-05 - accuracy: 1.0000\n", "Epoch 34/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 9.7743e-05 - accuracy: 1.0000\n", "Epoch 35/500\n", "16/16 [==============================] - 0s 1ms/step - loss: 8.9654e-05 - accuracy: 1.0000\n", "Epoch 36/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 8.1509e-05 - accuracy: 1.0000\n", "Epoch 37/500\n", "16/16 [==============================] - 0s 1ms/step - loss: 6.2648e-05 - accuracy: 1.0000\n", "Epoch 38/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 8.0588e-05 - accuracy: 1.0000\n", "Epoch 39/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 8.4114e-05 - accuracy: 1.0000\n", "Epoch 40/500\n", "16/16 [==============================] - 0s 1ms/step - loss: 9.6937e-05 - accuracy: 1.0000\n", "Epoch 41/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.2656e-05 - accuracy: 1.0000\n", "Epoch 42/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.0285e-05 - accuracy: 1.0000\n", "Epoch 43/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.2008e-05 - accuracy: 1.0000\n", "Epoch 44/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.3084e-05 - accuracy: 1.0000\n", "Epoch 45/500\n", "16/16 [==============================] - 0s 1ms/step - loss: 5.1538e-05 - accuracy: 1.0000\n", "Epoch 46/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.9588e-05 - accuracy: 1.0000\n", "Epoch 47/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.9849e-05 - accuracy: 1.0000\n", "Epoch 48/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.7411e-05 - accuracy: 1.0000\n", "Epoch 49/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.9275e-05 - accuracy: 1.0000\n", "Epoch 50/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.7819e-05 - accuracy: 1.0000\n", "Epoch 51/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.2392e-05 - accuracy: 1.0000\n", "Epoch 52/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.1965e-05 - accuracy: 1.0000\n", "Epoch 53/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.7118e-05 - accuracy: 1.0000\n", "Epoch 54/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.5719e-05 - accuracy: 1.0000\n", "Epoch 55/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.7843e-05 - accuracy: 1.0000\n", "Epoch 56/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.9626e-05 - accuracy: 1.0000\n", "Epoch 57/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.7736e-05 - accuracy: 1.0000\n", "Epoch 58/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.1028e-05 - accuracy: 1.0000\n", "Epoch 59/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.7475e-05 - accuracy: 1.0000\n", "Epoch 60/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.4412e-05 - accuracy: 1.0000\n", "Epoch 61/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.0539e-05 - accuracy: 1.0000\n", "Epoch 62/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.6439e-05 - accuracy: 1.0000\n", "Epoch 63/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.4391e-05 - accuracy: 1.0000\n", "Epoch 64/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.3806e-05 - accuracy: 1.0000\n", "Epoch 65/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.0890e-05 - accuracy: 1.0000\n", "Epoch 66/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.2174e-05 - accuracy: 1.0000\n", "Epoch 67/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.4171e-05 - accuracy: 1.0000\n", "Epoch 68/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.6563e-05 - accuracy: 1.0000\n", "Epoch 69/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.8718e-05 - accuracy: 1.0000\n", "Epoch 70/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.9620e-05 - accuracy: 1.0000\n", "Epoch 71/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.3876e-05 - accuracy: 1.0000\n", "Epoch 72/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.4948e-05 - accuracy: 1.0000\n", "Epoch 73/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.9625e-05 - accuracy: 1.0000\n", "Epoch 74/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.4803e-05 - accuracy: 1.0000\n", "Epoch 75/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.3840e-05 - accuracy: 1.0000\n", "Epoch 76/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.0455e-05 - accuracy: 1.0000\n", "Epoch 77/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.1140e-05 - accuracy: 1.0000\n", "Epoch 78/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.8839e-05 - accuracy: 1.0000\n", "Epoch 79/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.6842e-05 - accuracy: 1.0000\n", "Epoch 80/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.5906e-05 - accuracy: 1.0000\n", "Epoch 81/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.0156e-05 - accuracy: 1.0000\n", "Epoch 82/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.6469e-05 - accuracy: 1.0000\n", "Epoch 83/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.8434e-05 - accuracy: 1.0000\n", "Epoch 84/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.3064e-05 - accuracy: 1.0000\n", "Epoch 85/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.2559e-05 - accuracy: 1.0000\n", "Epoch 86/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.4841e-05 - accuracy: 1.0000\n", "Epoch 87/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.9066e-05 - accuracy: 1.0000\n", "Epoch 88/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.7453e-05 - accuracy: 1.0000\n", "Epoch 89/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.3744e-05 - accuracy: 1.0000\n", "Epoch 90/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.7898e-05 - accuracy: 1.0000\n", "Epoch 91/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.7220e-05 - accuracy: 1.0000\n", "Epoch 92/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.0643e-05 - accuracy: 1.0000\n", "Epoch 93/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.6146e-05 - accuracy: 1.0000\n", "Epoch 94/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.7818e-05 - accuracy: 1.0000\n", "Epoch 95/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.6528e-05 - accuracy: 1.0000\n", "Epoch 96/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.0796e-05 - accuracy: 1.0000\n", "Epoch 97/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.1113e-05 - accuracy: 1.0000\n", "Epoch 98/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.6924e-05 - accuracy: 1.0000\n", "Epoch 99/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.1567e-05 - accuracy: 1.0000\n", "Epoch 100/500\n", "16/16 [==============================] - 0s 3ms/step - loss: 2.4634e-05 - accuracy: 1.0000\n", "Epoch 101/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.7239e-05 - accuracy: 1.0000\n", "Epoch 102/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.1350e-05 - accuracy: 1.0000\n", "Epoch 103/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.8953e-05 - accuracy: 1.0000\n", "Epoch 104/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.0450e-05 - accuracy: 1.0000\n", "Epoch 105/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.4468e-05 - accuracy: 1.0000\n", "Epoch 106/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.6787e-05 - accuracy: 1.0000\n", "Epoch 107/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.3703e-05 - accuracy: 1.0000\n", "Epoch 108/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.5709e-05 - accuracy: 1.0000\n", "Epoch 109/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.5058e-05 - accuracy: 1.0000\n", "Epoch 110/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.3074e-05 - accuracy: 1.0000\n", "Epoch 111/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.0007e-05 - accuracy: 1.0000\n", "Epoch 112/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.6402e-05 - accuracy: 1.0000\n", "Epoch 113/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.1575e-05 - accuracy: 1.0000\n", "Epoch 114/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.5988e-05 - accuracy: 1.0000\n", "Epoch 115/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.1510e-05 - accuracy: 1.0000\n", "Epoch 116/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.8949e-05 - accuracy: 1.0000\n", "Epoch 117/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.8263e-05 - accuracy: 1.0000\n", "Epoch 118/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.8245e-05 - accuracy: 1.0000\n", "Epoch 119/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.6808e-05 - accuracy: 1.0000\n", "Epoch 120/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.1533e-05 - accuracy: 1.0000\n", "Epoch 121/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.4002e-05 - accuracy: 1.0000\n", "Epoch 122/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.6573e-05 - accuracy: 1.0000\n", "Epoch 123/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.1727e-05 - accuracy: 1.0000\n", "Epoch 124/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.9905e-05 - accuracy: 1.0000\n", "Epoch 125/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.4462e-05 - accuracy: 1.0000\n", "Epoch 126/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.9585e-05 - accuracy: 1.0000\n", "Epoch 127/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.1594e-05 - accuracy: 1.0000\n", "Epoch 128/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.3744e-05 - accuracy: 1.0000\n", "Epoch 129/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.6854e-05 - accuracy: 1.0000\n", "Epoch 130/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.1371e-05 - accuracy: 1.0000\n", "Epoch 131/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.0249e-05 - accuracy: 1.0000\n", "Epoch 132/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.4659e-05 - accuracy: 1.0000\n", "Epoch 133/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.7333e-05 - accuracy: 1.0000\n", "Epoch 134/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.9890e-05 - accuracy: 1.0000\n", "Epoch 135/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.4944e-05 - accuracy: 1.0000\n", "Epoch 136/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.8564e-05 - accuracy: 1.0000\n", "Epoch 137/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.9040e-05 - accuracy: 1.0000\n", "Epoch 138/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.6166e-05 - accuracy: 1.0000\n", "Epoch 139/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.3010e-05 - accuracy: 1.0000\n", "Epoch 140/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.6001e-05 - accuracy: 1.0000\n", "Epoch 141/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.4663e-05 - accuracy: 1.0000\n", "Epoch 142/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.7118e-05 - accuracy: 1.0000\n", "Epoch 143/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.5340e-05 - accuracy: 1.0000\n", "Epoch 144/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.3419e-05 - accuracy: 1.0000\n", "Epoch 145/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.5667e-05 - accuracy: 1.0000\n", "Epoch 146/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.6601e-05 - accuracy: 1.0000\n", "Epoch 147/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.6966e-05 - accuracy: 1.0000\n", "Epoch 148/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.7423e-05 - accuracy: 1.0000\n", "Epoch 149/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.4279e-05 - accuracy: 1.0000\n", "Epoch 150/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.7175e-05 - accuracy: 1.0000\n", "Epoch 151/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.6299e-05 - accuracy: 1.0000\n", "Epoch 152/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.3905e-05 - accuracy: 1.0000\n", "Epoch 153/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.8746e-05 - accuracy: 1.0000\n", "Epoch 154/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.1728e-05 - accuracy: 1.0000\n", "Epoch 155/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.0132e-05 - accuracy: 1.0000\n", "Epoch 156/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.8553e-05 - accuracy: 1.0000\n", "Epoch 157/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.5694e-05 - accuracy: 1.0000\n", "Epoch 158/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.4999e-05 - accuracy: 1.0000\n", "Epoch 159/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.7868e-05 - accuracy: 1.0000\n", "Epoch 160/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.4006e-05 - accuracy: 1.0000\n", "Epoch 161/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.4313e-05 - accuracy: 1.0000\n", "Epoch 162/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.1549e-05 - accuracy: 1.0000\n", "Epoch 163/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.1764e-05 - accuracy: 1.0000\n", "Epoch 164/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.5811e-05 - accuracy: 1.0000\n", "Epoch 165/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.4540e-05 - accuracy: 1.0000\n", "Epoch 166/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.5782e-05 - accuracy: 1.0000\n", "Epoch 167/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.4975e-05 - accuracy: 1.0000\n", "Epoch 168/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.3666e-05 - accuracy: 1.0000\n", "Epoch 169/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.2288e-05 - accuracy: 1.0000\n", "Epoch 170/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.2482e-05 - accuracy: 1.0000\n", "Epoch 171/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.2288e-05 - accuracy: 1.0000\n", "Epoch 172/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.1673e-05 - accuracy: 1.0000\n", "Epoch 173/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.5460e-05 - accuracy: 1.0000\n", "Epoch 174/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.1394e-05 - accuracy: 1.0000\n", "Epoch 175/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.5484e-05 - accuracy: 1.0000\n", "Epoch 176/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.6328e-05 - accuracy: 1.0000\n", "Epoch 177/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.3159e-05 - accuracy: 1.0000\n", "Epoch 178/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.4142e-05 - accuracy: 1.0000\n", "Epoch 179/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.4172e-05 - accuracy: 1.0000\n", "Epoch 180/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.1418e-05 - accuracy: 1.0000\n", "Epoch 181/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.7098e-05 - accuracy: 1.0000\n", "Epoch 182/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.2341e-05 - accuracy: 1.0000\n", "Epoch 183/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.3434e-05 - accuracy: 1.0000\n", "Epoch 184/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.2595e-05 - accuracy: 1.0000\n", "Epoch 185/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.0052e-05 - accuracy: 1.0000\n", "Epoch 186/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.5031e-05 - accuracy: 1.0000\n", "Epoch 187/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.5196e-05 - accuracy: 1.0000\n", "Epoch 188/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.4337e-05 - accuracy: 1.0000\n", "Epoch 189/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.0523e-05 - accuracy: 1.0000\n", "Epoch 190/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.0133e-05 - accuracy: 1.0000\n", "Epoch 191/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.7317e-05 - accuracy: 1.0000\n", "Epoch 192/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.3846e-05 - accuracy: 1.0000\n", "Epoch 193/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.5827e-05 - accuracy: 1.0000\n", "Epoch 194/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.6816e-05 - accuracy: 1.0000\n", "Epoch 195/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 9.2179e-06 - accuracy: 1.0000\n", "Epoch 196/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.2208e-05 - accuracy: 1.0000\n", "Epoch 197/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.2430e-05 - accuracy: 1.0000\n", "Epoch 198/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 9.8042e-06 - accuracy: 1.0000\n", "Epoch 199/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.2540e-05 - accuracy: 1.0000\n", "Epoch 200/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.2058e-05 - accuracy: 1.0000\n", "Epoch 201/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.0997e-05 - accuracy: 1.0000\n", "Epoch 202/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.0221e-05 - accuracy: 1.0000\n", "Epoch 203/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.1685e-05 - accuracy: 1.0000\n", "Epoch 204/500\n", "16/16 [==============================] - 0s 3ms/step - loss: 9.2379e-06 - accuracy: 1.0000\n", "Epoch 205/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.0005e-05 - accuracy: 1.0000\n", "Epoch 206/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 9.8159e-06 - accuracy: 1.0000\n", "Epoch 207/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.2437e-05 - accuracy: 1.0000\n", "Epoch 208/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.2458e-05 - accuracy: 1.0000\n", "Epoch 209/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.0787e-05 - accuracy: 1.0000\n", "Epoch 210/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.0431e-05 - accuracy: 1.0000\n", "Epoch 211/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.0263e-05 - accuracy: 1.0000\n", "Epoch 212/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.0082e-05 - accuracy: 1.0000\n", "Epoch 213/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.1031e-05 - accuracy: 1.0000\n", "Epoch 214/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 9.5764e-06 - accuracy: 1.0000\n", "Epoch 215/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.1661e-05 - accuracy: 1.0000\n", "Epoch 216/500\n", "16/16 [==============================] - 0s 3ms/step - loss: 1.3727e-05 - accuracy: 1.0000\n", "Epoch 217/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.1254e-05 - accuracy: 1.0000\n", "Epoch 218/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.1421e-05 - accuracy: 1.0000\n", "Epoch 219/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.0640e-05 - accuracy: 1.0000\n", "Epoch 220/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.0789e-05 - accuracy: 1.0000\n", "Epoch 221/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.2558e-05 - accuracy: 1.0000\n", "Epoch 222/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 9.7645e-06 - accuracy: 1.0000\n", "Epoch 223/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.2337e-05 - accuracy: 1.0000\n", "Epoch 224/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.0657e-05 - accuracy: 1.0000\n", "Epoch 225/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.0150e-05 - accuracy: 1.0000\n", "Epoch 226/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 9.4178e-06 - accuracy: 1.0000\n", "Epoch 227/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.1393e-05 - accuracy: 1.0000\n", "Epoch 228/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.1296e-05 - accuracy: 1.0000\n", "Epoch 229/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.2052e-05 - accuracy: 1.0000\n", "Epoch 230/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.2043e-05 - accuracy: 1.0000\n", "Epoch 231/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.1008e-05 - accuracy: 1.0000\n", "Epoch 232/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.7623e-06 - accuracy: 1.0000\n", "Epoch 233/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 8.2891e-06 - accuracy: 1.0000\n", "Epoch 234/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 8.2832e-06 - accuracy: 1.0000\n", "Epoch 235/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.1464e-05 - accuracy: 1.0000\n", "Epoch 236/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 9.9744e-06 - accuracy: 1.0000\n", "Epoch 237/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.2524e-06 - accuracy: 1.0000\n", "Epoch 238/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 9.2705e-06 - accuracy: 1.0000\n", "Epoch 239/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 9.3350e-06 - accuracy: 1.0000\n", "Epoch 240/500\n", "16/16 [==============================] - 0s 3ms/step - loss: 1.3099e-05 - accuracy: 1.0000\n", "Epoch 241/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.0832e-05 - accuracy: 1.0000\n", "Epoch 242/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 8.0116e-06 - accuracy: 1.0000\n", "Epoch 243/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.0035e-05 - accuracy: 1.0000\n", "Epoch 244/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.6537e-06 - accuracy: 1.0000\n", "Epoch 245/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.6538e-06 - accuracy: 1.0000\n", "Epoch 246/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 9.8581e-06 - accuracy: 1.0000\n", "Epoch 247/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.0643e-05 - accuracy: 1.0000\n", "Epoch 248/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 8.3363e-06 - accuracy: 1.0000\n", "Epoch 249/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.1604e-05 - accuracy: 1.0000\n", "Epoch 250/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 9.6953e-06 - accuracy: 1.0000\n", "Epoch 251/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 8.1633e-06 - accuracy: 1.0000\n", "Epoch 252/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.0682e-05 - accuracy: 1.0000\n", "Epoch 253/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.6458e-06 - accuracy: 1.0000\n", "Epoch 254/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.6923e-06 - accuracy: 1.0000\n", "Epoch 255/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.0675e-05 - accuracy: 1.0000\n", "Epoch 256/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.1627e-05 - accuracy: 1.0000\n", "Epoch 257/500\n", "16/16 [==============================] - 0s 3ms/step - loss: 9.0458e-06 - accuracy: 1.0000\n", "Epoch 258/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.0389e-05 - accuracy: 1.0000\n", "Epoch 259/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.1235e-05 - accuracy: 1.0000\n", "Epoch 260/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.0694e-05 - accuracy: 1.0000\n", "Epoch 261/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.5404e-06 - accuracy: 1.0000\n", "Epoch 262/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.4752e-06 - accuracy: 1.0000\n", "Epoch 263/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 8.9731e-06 - accuracy: 1.0000\n", "Epoch 264/500\n", "16/16 [==============================] - 0s 3ms/step - loss: 9.5734e-06 - accuracy: 1.0000\n", "Epoch 265/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.6809e-06 - accuracy: 1.0000\n", "Epoch 266/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.7246e-06 - accuracy: 1.0000\n", "Epoch 267/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 9.9449e-06 - accuracy: 1.0000\n", "Epoch 268/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.1924e-06 - accuracy: 1.0000\n", "Epoch 269/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.2775e-06 - accuracy: 1.0000\n", "Epoch 270/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.0775e-05 - accuracy: 1.0000\n", "Epoch 271/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.2919e-06 - accuracy: 1.0000\n", "Epoch 272/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.1024e-06 - accuracy: 1.0000\n", "Epoch 273/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 9.5185e-06 - accuracy: 1.0000\n", "Epoch 274/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.1556e-05 - accuracy: 1.0000\n", "Epoch 275/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.3936e-06 - accuracy: 1.0000\n", "Epoch 276/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.8023e-06 - accuracy: 1.0000\n", "Epoch 277/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 8.2336e-06 - accuracy: 1.0000\n", "Epoch 278/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.3436e-06 - accuracy: 1.0000\n", "Epoch 279/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.9565e-06 - accuracy: 1.0000\n", "Epoch 280/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 8.2685e-06 - accuracy: 1.0000\n", "Epoch 281/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.1900e-05 - accuracy: 1.0000\n", "Epoch 282/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 8.5213e-06 - accuracy: 1.0000\n", "Epoch 283/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.4407e-06 - accuracy: 1.0000\n", "Epoch 284/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.0629e-05 - accuracy: 1.0000\n", "Epoch 285/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.6545e-06 - accuracy: 1.0000\n", "Epoch 286/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 8.3563e-06 - accuracy: 1.0000\n", "Epoch 287/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 9.5695e-06 - accuracy: 1.0000\n", "Epoch 288/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.0055e-06 - accuracy: 1.0000\n", "Epoch 289/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.0400e-06 - accuracy: 1.0000\n", "Epoch 290/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.4379e-06 - accuracy: 1.0000\n", "Epoch 291/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.4177e-06 - accuracy: 1.0000\n", "Epoch 292/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.3835e-06 - accuracy: 1.0000\n", "Epoch 293/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.4944e-06 - accuracy: 1.0000\n", "Epoch 294/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.5406e-06 - accuracy: 1.0000\n", "Epoch 295/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.0463e-06 - accuracy: 1.0000\n", "Epoch 296/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.1221e-06 - accuracy: 1.0000\n", "Epoch 297/500\n", "16/16 [==============================] - 0s 3ms/step - loss: 7.4464e-06 - accuracy: 1.0000\n", "Epoch 298/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.1961e-06 - accuracy: 1.0000\n", "Epoch 299/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 9.9969e-06 - accuracy: 1.0000\n", "Epoch 300/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.7176e-06 - accuracy: 1.0000\n", "Epoch 301/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.5319e-06 - accuracy: 1.0000\n", "Epoch 302/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.1193e-06 - accuracy: 1.0000\n", "Epoch 303/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.3155e-06 - accuracy: 1.0000\n", "Epoch 304/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.6391e-06 - accuracy: 1.0000\n", "Epoch 305/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 8.0558e-06 - accuracy: 1.0000\n", "Epoch 306/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.1286e-05 - accuracy: 1.0000\n", "Epoch 307/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.8932e-06 - accuracy: 1.0000\n", "Epoch 308/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 8.4289e-06 - accuracy: 1.0000\n", "Epoch 309/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.1162e-06 - accuracy: 1.0000\n", "Epoch 310/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.0746e-06 - accuracy: 1.0000\n", "Epoch 311/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 8.3369e-06 - accuracy: 1.0000\n", "Epoch 312/500\n", "16/16 [==============================] - 0s 3ms/step - loss: 4.8371e-06 - accuracy: 1.0000\n", "Epoch 313/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.3728e-06 - accuracy: 1.0000\n", "Epoch 314/500\n", "16/16 [==============================] - 0s 3ms/step - loss: 5.9809e-06 - accuracy: 1.0000\n", "Epoch 315/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.8312e-06 - accuracy: 1.0000\n", "Epoch 316/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.2378e-06 - accuracy: 1.0000\n", "Epoch 317/500\n", "16/16 [==============================] - 0s 3ms/step - loss: 7.2470e-06 - accuracy: 1.0000\n", "Epoch 318/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 8.2929e-06 - accuracy: 1.0000\n", "Epoch 319/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.9408e-06 - accuracy: 1.0000\n", "Epoch 320/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.7033e-06 - accuracy: 1.0000\n", "Epoch 321/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.7317e-06 - accuracy: 1.0000\n", "Epoch 322/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.9378e-06 - accuracy: 1.0000\n", "Epoch 323/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.7811e-06 - accuracy: 1.0000\n", "Epoch 324/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.6032e-06 - accuracy: 1.0000\n", "Epoch 325/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.0249e-06 - accuracy: 1.0000\n", "Epoch 326/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.1040e-06 - accuracy: 1.0000\n", "Epoch 327/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.4627e-06 - accuracy: 1.0000\n", "Epoch 328/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.3615e-06 - accuracy: 1.0000\n", "Epoch 329/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.3665e-06 - accuracy: 1.0000\n", "Epoch 330/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.7421e-06 - accuracy: 1.0000\n", "Epoch 331/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.0334e-06 - accuracy: 1.0000\n", "Epoch 332/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.7920e-06 - accuracy: 1.0000\n", "Epoch 333/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.7384e-06 - accuracy: 1.0000\n", "Epoch 334/500\n", "16/16 [==============================] - 0s 3ms/step - loss: 5.0372e-06 - accuracy: 1.0000\n", "Epoch 335/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.4770e-06 - accuracy: 1.0000\n", "Epoch 336/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.0275e-06 - accuracy: 1.0000\n", "Epoch 337/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.2139e-06 - accuracy: 1.0000\n", "Epoch 338/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.3050e-06 - accuracy: 1.0000\n", "Epoch 339/500\n", "16/16 [==============================] - 0s 3ms/step - loss: 5.7897e-06 - accuracy: 1.0000\n", "Epoch 340/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.7578e-06 - accuracy: 1.0000\n", "Epoch 341/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.8276e-06 - accuracy: 1.0000\n", "Epoch 342/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.2239e-06 - accuracy: 1.0000\n", "Epoch 343/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.0292e-06 - accuracy: 1.0000\n", "Epoch 344/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.6066e-06 - accuracy: 1.0000\n", "Epoch 345/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.2642e-06 - accuracy: 1.0000\n", "Epoch 346/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.3814e-06 - accuracy: 1.0000\n", "Epoch 347/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.7402e-06 - accuracy: 1.0000\n", "Epoch 348/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.0313e-06 - accuracy: 1.0000\n", "Epoch 349/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.4775e-06 - accuracy: 1.0000\n", "Epoch 350/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.0324e-06 - accuracy: 1.0000\n", "Epoch 351/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.8316e-06 - accuracy: 1.0000\n", "Epoch 352/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.5549e-06 - accuracy: 1.0000\n", "Epoch 353/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.2868e-06 - accuracy: 1.0000\n", "Epoch 354/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.3619e-06 - accuracy: 1.0000\n", "Epoch 355/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.3050e-06 - accuracy: 1.0000\n", "Epoch 356/500\n", "16/16 [==============================] - 0s 3ms/step - loss: 6.2270e-06 - accuracy: 1.0000\n", "Epoch 357/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.9644e-06 - accuracy: 1.0000\n", "Epoch 358/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.3171e-06 - accuracy: 1.0000\n", "Epoch 359/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.0025e-06 - accuracy: 1.0000\n", "Epoch 360/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.0733e-06 - accuracy: 1.0000\n", "Epoch 361/500\n", "16/16 [==============================] - 0s 3ms/step - loss: 4.8507e-06 - accuracy: 1.0000\n", "Epoch 362/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.7223e-06 - accuracy: 1.0000\n", "Epoch 363/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 8.7416e-06 - accuracy: 1.0000\n", "Epoch 364/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.7700e-06 - accuracy: 1.0000\n", "Epoch 365/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.4674e-06 - accuracy: 1.0000\n", "Epoch 366/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 9.1421e-06 - accuracy: 1.0000\n", "Epoch 367/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.2047e-06 - accuracy: 1.0000\n", "Epoch 368/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.1644e-06 - accuracy: 1.0000\n", "Epoch 369/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.2653e-06 - accuracy: 1.0000\n", "Epoch 370/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.4170e-06 - accuracy: 1.0000\n", "Epoch 371/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.8750e-06 - accuracy: 1.0000\n", "Epoch 372/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.9676e-06 - accuracy: 1.0000\n", "Epoch 373/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.8009e-06 - accuracy: 1.0000\n", "Epoch 374/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.0832e-06 - accuracy: 1.0000\n", "Epoch 375/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.6859e-06 - accuracy: 1.0000\n", "Epoch 376/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.0478e-06 - accuracy: 1.0000\n", "Epoch 377/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.3122e-06 - accuracy: 1.0000\n", "Epoch 378/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.3241e-06 - accuracy: 1.0000\n", "Epoch 379/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.3097e-06 - accuracy: 1.0000\n", "Epoch 380/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.8262e-06 - accuracy: 1.0000\n", "Epoch 381/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.1132e-06 - accuracy: 1.0000\n", "Epoch 382/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.6963e-06 - accuracy: 1.0000\n", "Epoch 383/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.4468e-06 - accuracy: 1.0000\n", "Epoch 384/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.4379e-06 - accuracy: 1.0000\n", "Epoch 385/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.4271e-06 - accuracy: 1.0000\n", "Epoch 386/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 8.4998e-06 - accuracy: 1.0000\n", "Epoch 387/500\n", "16/16 [==============================] - 0s 3ms/step - loss: 4.1934e-06 - accuracy: 1.0000\n", "Epoch 388/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.3380e-06 - accuracy: 1.0000\n", "Epoch 389/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.8077e-06 - accuracy: 1.0000\n", "Epoch 390/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.2602e-06 - accuracy: 1.0000\n", "Epoch 391/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 8.6443e-06 - accuracy: 1.0000\n", "Epoch 392/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.5742e-06 - accuracy: 1.0000\n", "Epoch 393/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.6861e-06 - accuracy: 1.0000\n", "Epoch 394/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.8358e-06 - accuracy: 1.0000\n", "Epoch 395/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.2181e-06 - accuracy: 1.0000\n", "Epoch 396/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.5187e-06 - accuracy: 1.0000\n", "Epoch 397/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.9903e-06 - accuracy: 1.0000\n", "Epoch 398/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.8975e-06 - accuracy: 1.0000\n", "Epoch 399/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.1671e-06 - accuracy: 1.0000\n", "Epoch 400/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.5283e-06 - accuracy: 1.0000\n", "Epoch 401/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.5031e-06 - accuracy: 1.0000\n", "Epoch 402/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.8671e-06 - accuracy: 1.0000\n", "Epoch 403/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.4674e-06 - accuracy: 1.0000\n", "Epoch 404/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.1360e-06 - accuracy: 1.0000\n", "Epoch 405/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.6218e-06 - accuracy: 1.0000\n", "Epoch 406/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.7691e-06 - accuracy: 1.0000\n", "Epoch 407/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.0429e-06 - accuracy: 1.0000\n", "Epoch 408/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.7649e-06 - accuracy: 1.0000\n", "Epoch 409/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.7919e-06 - accuracy: 1.0000\n", "Epoch 410/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.1652e-06 - accuracy: 1.0000\n", "Epoch 411/500\n", "16/16 [==============================] - 0s 3ms/step - loss: 5.7039e-06 - accuracy: 1.0000\n", "Epoch 412/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.7744e-06 - accuracy: 1.0000\n", "Epoch 413/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.7897e-06 - accuracy: 1.0000\n", "Epoch 414/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.6385e-06 - accuracy: 1.0000\n", "Epoch 415/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.0692e-06 - accuracy: 1.0000\n", "Epoch 416/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.8055e-06 - accuracy: 1.0000\n", "Epoch 417/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.9926e-06 - accuracy: 1.0000\n", "Epoch 418/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 7.1928e-06 - accuracy: 1.0000\n", "Epoch 419/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.2792e-06 - accuracy: 1.0000\n", "Epoch 420/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.0418e-06 - accuracy: 1.0000\n", "Epoch 421/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.8722e-06 - accuracy: 1.0000\n", "Epoch 422/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.3391e-06 - accuracy: 1.0000\n", "Epoch 423/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.4134e-06 - accuracy: 1.0000\n", "Epoch 424/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.8664e-06 - accuracy: 1.0000\n", "Epoch 425/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.0464e-06 - accuracy: 1.0000\n", "Epoch 426/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.1715e-06 - accuracy: 1.0000\n", "Epoch 427/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.9170e-06 - accuracy: 1.0000\n", "Epoch 428/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.0820e-06 - accuracy: 1.0000\n", "Epoch 429/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.4111e-06 - accuracy: 1.0000\n", "Epoch 430/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.0171e-06 - accuracy: 1.0000\n", "Epoch 431/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.5979e-06 - accuracy: 1.0000\n", "Epoch 432/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.0082e-06 - accuracy: 1.0000\n", "Epoch 433/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.2469e-06 - accuracy: 1.0000\n", "Epoch 434/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.0115e-06 - accuracy: 1.0000\n", "Epoch 435/500\n", "16/16 [==============================] - 0s 3ms/step - loss: 3.5258e-06 - accuracy: 1.0000\n", "Epoch 436/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.3860e-06 - accuracy: 1.0000\n", "Epoch 437/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.8139e-06 - accuracy: 1.0000\n", "Epoch 438/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.2580e-06 - accuracy: 1.0000\n", "Epoch 439/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.6618e-06 - accuracy: 1.0000\n", "Epoch 440/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.4300e-06 - accuracy: 1.0000\n", "Epoch 441/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.2788e-06 - accuracy: 1.0000\n", "Epoch 442/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.7196e-06 - accuracy: 1.0000\n", "Epoch 443/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.9321e-06 - accuracy: 1.0000\n", "Epoch 444/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.6859e-06 - accuracy: 1.0000\n", "Epoch 445/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.9526e-06 - accuracy: 1.0000\n", "Epoch 446/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.4410e-06 - accuracy: 1.0000\n", "Epoch 447/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.8549e-06 - accuracy: 1.0000\n", "Epoch 448/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.9731e-06 - accuracy: 1.0000\n", "Epoch 449/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.5662e-06 - accuracy: 1.0000\n", "Epoch 450/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.9994e-06 - accuracy: 1.0000\n", "Epoch 451/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.8729e-06 - accuracy: 1.0000\n", "Epoch 452/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.3770e-06 - accuracy: 1.0000\n", "Epoch 453/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 6.1516e-06 - accuracy: 1.0000\n", "Epoch 454/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.6614e-06 - accuracy: 1.0000\n", "Epoch 455/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.9183e-06 - accuracy: 1.0000\n", "Epoch 456/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.8460e-06 - accuracy: 1.0000\n", "Epoch 457/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.4603e-06 - accuracy: 1.0000\n", "Epoch 458/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.9782e-06 - accuracy: 1.0000\n", "Epoch 459/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.1053e-06 - accuracy: 1.0000\n", "Epoch 460/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.9864e-06 - accuracy: 1.0000\n", "Epoch 461/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.3644e-06 - accuracy: 1.0000\n", "Epoch 462/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.7043e-06 - accuracy: 1.0000\n", "Epoch 463/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.7622e-06 - accuracy: 1.0000\n", "Epoch 464/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.8914e-06 - accuracy: 1.0000\n", "Epoch 465/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.0626e-06 - accuracy: 1.0000\n", "Epoch 466/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.6657e-06 - accuracy: 1.0000\n", "Epoch 467/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.1931e-06 - accuracy: 1.0000\n", "Epoch 468/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.8351e-06 - accuracy: 1.0000\n", "Epoch 469/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.8834e-06 - accuracy: 1.0000\n", "Epoch 470/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.0511e-06 - accuracy: 1.0000\n", "Epoch 471/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.1497e-06 - accuracy: 1.0000\n", "Epoch 472/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.9922e-06 - accuracy: 1.0000\n", "Epoch 473/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.1291e-06 - accuracy: 1.0000\n", "Epoch 474/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.1955e-06 - accuracy: 1.0000\n", "Epoch 475/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.5443e-06 - accuracy: 1.0000\n", "Epoch 476/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.1407e-06 - accuracy: 1.0000\n", "Epoch 477/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.4077e-06 - accuracy: 1.0000\n", "Epoch 478/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.2412e-06 - accuracy: 1.0000\n", "Epoch 479/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.8473e-06 - accuracy: 1.0000\n", "Epoch 480/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.2846e-06 - accuracy: 1.0000\n", "Epoch 481/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.3877e-06 - accuracy: 1.0000\n", "Epoch 482/500\n", "16/16 [==============================] - 0s 3ms/step - loss: 2.0038e-06 - accuracy: 1.0000\n", "Epoch 483/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.7945e-06 - accuracy: 1.0000\n", "Epoch 484/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.4394e-06 - accuracy: 1.0000\n", "Epoch 485/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.3405e-06 - accuracy: 1.0000\n", "Epoch 486/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.7550e-06 - accuracy: 1.0000\n", "Epoch 487/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.4282e-06 - accuracy: 1.0000\n", "Epoch 488/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.1584e-06 - accuracy: 1.0000\n", "Epoch 489/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.1684e-06 - accuracy: 1.0000\n", "Epoch 490/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.9333e-06 - accuracy: 1.0000\n", "Epoch 491/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 4.4508e-06 - accuracy: 1.0000\n", "Epoch 492/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.2578e-06 - accuracy: 1.0000\n", "Epoch 493/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 1.9210e-06 - accuracy: 1.0000\n", "Epoch 494/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.1968e-06 - accuracy: 1.0000\n", "Epoch 495/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.3697e-06 - accuracy: 1.0000\n", "Epoch 496/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.5280e-06 - accuracy: 1.0000\n", "Epoch 497/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.3872e-06 - accuracy: 1.0000\n", "Epoch 498/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 3.2834e-06 - accuracy: 1.0000\n", "Epoch 499/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 5.2102e-06 - accuracy: 1.0000\n", "Epoch 500/500\n", "16/16 [==============================] - 0s 2ms/step - loss: 2.4811e-06 - accuracy: 1.0000\n", "20/20 [==============================] - 0s 1ms/step - loss: 3.1321e-06 - accuracy: 1.0000\n", "Train Accuracy: 100.00\n", "5/5 [==============================] - 0s 4ms/step - loss: 1.6906e-06 - accuracy: 1.0000\n", "Test Accuracy: 100.00\n" ], "name": "stdout" }, { "output_type": "stream", "text": [ "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/sequential.py:450: UserWarning: `model.predict_classes()` is deprecated and will be removed after 2021-01-01. Please use instead:* `np.argmax(model.predict(x), axis=-1)`, if your model does multi-class classification (e.g. if it uses a `softmax` last-layer activation).* `(model.predict(x) > 0.5).astype(\"int32\")`, if your model does binary classification (e.g. if it uses a `sigmoid` last-layer activation).\n", " warnings.warn('`model.predict_classes()` is deprecated and '\n" ], "name": "stderr" }, { "output_type": "stream", "text": [ "[-0.5479185907225461, -1.0295049249971975, 0.2530362524198983, -0.09637905219854027, -0.23269708838862568, -0.3798157572985908, -0.73351525620903, -0.9564616833488008] => 0 (expected 0)\n", "[-0.5479185907225461, 0.2536780334127995, 0.7700137513783497, -1.2882122129452358, -0.6928905722954675, -0.5067350026561672, -0.5674087289544506, -0.5310229176752926] => 0 (expected 0)\n", "[-1.1418515161634994, -0.5913448904181741, 0.45982725200327884, 1.220910230732018, 0.08857006075388653, 0.31824009216807964, -0.706334188112826, -0.7862861770793975] => 0 (expected 0)\n", "[-1.1418515161634994, 0.06589516145036094, 0.149640752628208, -1.2882122129452358, -0.6928905722954675, 0.5466947338117168, -0.6459318145657063, 1.596170910692248] => 1 (expected 1)\n", "[-0.8448850534430228, 0.723135213318896, 0.6666182515866594, 1.597278597283606, 0.8700306938032405, 1.7905033383159665, -0.4133826764092951, 1.0856443918840382] => 1 (expected 1)\n", "[-0.5479185907225461, -0.7165334717264664, -0.47073224612193365, -0.22183517438240297, 0.3490569384370045, 0.3436239412395953, -0.8271389352070656, -0.9564616833488008] => 0 (expected 0)\n", "[-0.8448850534430228, -1.0295049249971975, -0.3673367463302434, 0.21726125326111648, -0.3108431516935611, -0.26558843647677216, -0.15063235147932405, -0.8713739302140991] => 0 (expected 0)\n", "[-0.5479185907225461, 1.6933467184581619, 0.9768047509617303, -1.2882122129452358, -0.6928905722954675, -1.1540231539798074, -0.440563744505499, -0.9564616833488008] => 0 (expected 0)\n", "[0.34298079743888377, -1.498962104903294, -0.47073224612193365, -1.2882122129452358, -0.6928905722954675, -0.6590380970852588, -0.6157306277921464, -0.5310229176752926] => 0 (expected 0)\n", "[-0.2509521280020695, 1.3177809745332847, 0.046245252836517724, -0.1591071132904716, 0.21881349959544552, -0.049825719368891866, -0.6157306277921464, -0.445935164540591] => 1 (expected 1)\n", "[1.5308466483207903, -0.027996274530858355, 0.149640752628208, 0.09180513107725377, -0.2066484006203139, -1.4205535692307176, 0.7886245571783882, 1.2558198981534414] => 0 (expected 0)\n", "[1.8278131110412668, -0.4035620184557355, -0.16054574674686284, -1.2882122129452358, -0.6928905722954675, 0.05170967691716893, -0.6036501530827224, 0.7452933793452318] => 1 (expected 1)\n", "[-0.8448850534430228, 2.2566953343454776, -0.9877097450803851, -0.2845632354743343, 2.5631953987435074, -0.7732654179070779, 0.5530553003446212, -0.7862861770793975] => 0 (expected 0)\n", "[-1.1418515161634994, -0.8104249077076857, -0.2639412465385531, 1.1581821696400867, 0.21881349959544552, 1.6001244702796018, -0.31975899741125957, -0.9564616833488008] => 0 (expected 0)\n", "[0.34298079743888377, -2.4065793193884137, -0.3673367463302434, -1.2882122129452358, -0.6928905722954675, -0.8874927387288966, 0.3476872302844142, 0.234766860537022] => 0 (expected 0)\n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "7fjCG7tY9DfQ", "outputId": "02c01777-ead7-49e4-a008-157195d0edac" }, "source": [ "from sklearn.metrics import classification_report\n", "import matplotlib.pyplot as plt\n", "print(classification_report(y_test,predictions ))" ], "execution_count": 34, "outputs": [ { "output_type": "stream", "text": [ " precision recall f1-score support\n", "\n", " 0 1.00 1.00 1.00 109\n", " 1 1.00 1.00 1.00 45\n", "\n", " accuracy 1.00 154\n", " macro avg 1.00 1.00 1.00 154\n", "weighted avg 1.00 1.00 1.00 154\n", "\n" ], "name": "stdout" } ] } ] }