Datasets
Models
Downloads: 1
Diff of
/tensorflow_neuralnet.ipynb
[000000]
..
[f9d9d1]
Switch to side-by-side view
--- a +++ b/tensorflow_neuralnet.ipynb @@ -0,0 +1,2656 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 64, + "id": "ed5dfd63-c548-4fd1-a481-c9007d37afc3", + "metadata": {}, + "outputs": [], + "source": [ + "%matplotlib notebook\n", + "\n", + "import pandas as pd\n", + "import numpy as np\n", + "import tensorflow as tf\n", + "from tensorflow.keras import layers\n", + "from matplotlib import pyplot as plt\n" + ] + }, + { + "cell_type": "code", + "execution_count": 74, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([ 0, 1, 1, ..., 50, 50, 50])" + ] + }, + "execution_count": 74, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "train_df = pd.read_csv(\"data/betas_20000.csv\", index_col=0)\n", + "label =pd.read_csv(\"data/label_class.csv\", index_col=0)\n", + "mylabel=label.x.unique().tolist()\n", + "mydata=dict()\n", + "for i, label_temp in enumerate(mylabel):\n", + " mydata[label_temp]=i\n", + "mydata_lable=[mydata[temp] for temp in label.x.tolist()] \n", + "np.array(mydata_lable)" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "(2801, 2000)" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "train_df.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 70, + "metadata": {}, + "outputs": [], + "source": [ + "def create_model(my_learning_rate):\n", + " \"\"\"Create and compile a deep neural net.\"\"\"\n", + " \n", + " # All models in this course are sequential.\n", + " model = tf.keras.models.Sequential()\n", + " \n", + " model.add(tf.keras.layers.Dense(units=136, activation='relu', input_shape=( 2000,)))\n", + " \n", + " # # Define a dropout regularization layer. \n", + " model.add(tf.keras.layers.Dropout(rate=0.2))\n", + " model.add(tf.keras.layers.Dense(units=91, activation='softmax')) \n", + " \n", + " # Construct the layers into a model that TensorFlow can execute. \n", + " # Notice that the loss function for multi-class classification\n", + " # is different than the loss function for binary classification. \n", + " model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=my_learning_rate),\n", + " loss=\"sparse_categorical_crossentropy\",\n", + " metrics=['accuracy'])\n", + " \n", + " return model \n", + "\n", + "def train_model(model, train_features, train_label, epochs,\n", + " batch_size=None, validation_split=0.1):\n", + " \"\"\"Train the model by feeding it data.\"\"\"\n", + "\n", + " history = model.fit(x=train_features, y=train_label, batch_size=batch_size,\n", + " epochs=epochs, shuffle=True, \n", + " validation_split=validation_split)\n", + " \n", + " # To track the progression of training, gather a snapshot\n", + " # of the model's metrics at each epoch. \n", + " epochs = history.epoch\n", + " hist = pd.DataFrame(history.history)\n", + "\n", + " return epochs, hist \n", + "\n", + "def plot_curve(epochs, hist, list_of_metrics):\n", + " plt.figure()\n", + " plt.xlabel(\"Epoch\")\n", + " plt.ylabel(\"Value\")\n", + " \n", + " for m in list_of_metrics:\n", + " x=hist[m]\n", + " plt.plot(epochs[1:], x[1:], label=m)\n", + " \n", + " plt.legend()" + ] + }, + { + "cell_type": "code", + "execution_count": 71, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/500\n", + "3/3 [==============================] - 0s 65ms/step - loss: 8.1022 - accuracy: 0.0304 - val_loss: 10.8629 - val_accuracy: 0.0250\n", + "Epoch 2/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 7.3115 - accuracy: 0.0929 - val_loss: 4.8613 - val_accuracy: 0.0838\n", + "Epoch 3/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 3.8796 - accuracy: 0.2045 - val_loss: 4.1189 - val_accuracy: 0.1301\n", + "Epoch 4/500\n", + "3/3 [==============================] - 0s 19ms/step - loss: 3.2068 - accuracy: 0.2509 - val_loss: 4.2306 - val_accuracy: 0.1301\n", + "Epoch 5/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 2.9522 - accuracy: 0.2875 - val_loss: 4.0535 - val_accuracy: 0.1854\n", + "Epoch 6/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 2.6109 - accuracy: 0.3545 - val_loss: 3.9284 - val_accuracy: 0.2282\n", + "Epoch 7/500\n", + "3/3 [==============================] - 1s 509ms/step - loss: 2.3519 - accuracy: 0.3920 - val_loss: 3.8262 - val_accuracy: 0.2317\n", + "Epoch 8/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 2.2000 - accuracy: 0.4179 - val_loss: 3.6234 - val_accuracy: 0.2335\n", + "Epoch 9/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 2.0049 - accuracy: 0.4629 - val_loss: 3.4767 - val_accuracy: 0.2389\n", + "Epoch 10/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 1.8725 - accuracy: 0.4786 - val_loss: 3.4561 - val_accuracy: 0.2816\n", + "Epoch 11/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 1.7198 - accuracy: 0.5089 - val_loss: 3.4203 - val_accuracy: 0.3012\n", + "Epoch 12/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 1.6167 - accuracy: 0.5353 - val_loss: 3.1485 - val_accuracy: 0.3547\n", + "Epoch 13/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 1.4885 - accuracy: 0.5728 - val_loss: 3.0569 - val_accuracy: 0.4135\n", + "Epoch 14/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 1.3688 - accuracy: 0.6121 - val_loss: 3.0551 - val_accuracy: 0.3922\n", + "Epoch 15/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 1.2810 - accuracy: 0.6116 - val_loss: 2.9558 - val_accuracy: 0.4385\n", + "Epoch 16/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 1.1852 - accuracy: 0.6527 - val_loss: 2.8550 - val_accuracy: 0.4920\n", + "Epoch 17/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 1.1080 - accuracy: 0.6759 - val_loss: 2.7942 - val_accuracy: 0.5294\n", + "Epoch 18/500\n", + "3/3 [==============================] - 1s 386ms/step - loss: 1.0401 - accuracy: 0.6951 - val_loss: 2.8304 - val_accuracy: 0.5258\n", + "Epoch 19/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 1.0043 - accuracy: 0.6964 - val_loss: 2.8021 - val_accuracy: 0.5615\n", + "Epoch 20/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.9464 - accuracy: 0.7134 - val_loss: 2.7443 - val_accuracy: 0.5686\n", + "Epoch 21/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.8989 - accuracy: 0.7277 - val_loss: 2.7179 - val_accuracy: 0.5865\n", + "Epoch 22/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.8427 - accuracy: 0.7312 - val_loss: 2.7421 - val_accuracy: 0.6471\n", + "Epoch 23/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.8217 - accuracy: 0.7549 - val_loss: 2.7403 - val_accuracy: 0.6043\n", + "Epoch 24/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.7731 - accuracy: 0.7563 - val_loss: 2.7153 - val_accuracy: 0.6043\n", + "Epoch 25/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.7580 - accuracy: 0.7612 - val_loss: 2.7835 - val_accuracy: 0.5793\n", + "Epoch 26/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.7343 - accuracy: 0.7580 - val_loss: 2.7090 - val_accuracy: 0.6239\n", + "Epoch 27/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.7079 - accuracy: 0.7737 - val_loss: 2.6946 - val_accuracy: 0.6506\n", + "Epoch 28/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 0.6618 - accuracy: 0.7897 - val_loss: 2.7342 - val_accuracy: 0.6774\n", + "Epoch 29/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.6673 - accuracy: 0.7871 - val_loss: 2.7232 - val_accuracy: 0.6578\n", + "Epoch 30/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.6272 - accuracy: 0.8054 - val_loss: 2.7842 - val_accuracy: 0.6399\n", + "Epoch 31/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.6284 - accuracy: 0.8009 - val_loss: 2.7238 - val_accuracy: 0.6684\n", + "Epoch 32/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.5961 - accuracy: 0.8058 - val_loss: 2.7375 - val_accuracy: 0.6595\n", + "Epoch 33/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.6083 - accuracy: 0.8085 - val_loss: 2.7851 - val_accuracy: 0.6524\n", + "Epoch 34/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.5674 - accuracy: 0.8138 - val_loss: 2.7163 - val_accuracy: 0.6702\n", + "Epoch 35/500\n", + "3/3 [==============================] - 0s 153ms/step - loss: 0.5744 - accuracy: 0.8085 - val_loss: 2.6751 - val_accuracy: 0.6952\n", + "Epoch 36/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.5685 - accuracy: 0.8174 - val_loss: 2.7026 - val_accuracy: 0.6881\n", + "Epoch 37/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.5261 - accuracy: 0.8339 - val_loss: 2.7768 - val_accuracy: 0.7184\n", + "Epoch 38/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.5189 - accuracy: 0.8388 - val_loss: 2.7659 - val_accuracy: 0.7112\n", + "Epoch 39/500\n", + "3/3 [==============================] - 0s 19ms/step - loss: 0.5318 - accuracy: 0.8353 - val_loss: 2.6409 - val_accuracy: 0.7094\n", + "Epoch 40/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.5067 - accuracy: 0.8420 - val_loss: 2.6429 - val_accuracy: 0.7558\n", + "Epoch 41/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.4789 - accuracy: 0.8504 - val_loss: 2.7366 - val_accuracy: 0.7219\n", + "Epoch 42/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.4881 - accuracy: 0.8446 - val_loss: 2.6574 - val_accuracy: 0.7433\n", + "Epoch 43/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.4512 - accuracy: 0.8554 - val_loss: 2.6640 - val_accuracy: 0.7558\n", + "Epoch 44/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.4463 - accuracy: 0.8571 - val_loss: 2.7401 - val_accuracy: 0.7433\n", + "Epoch 45/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.4672 - accuracy: 0.8420 - val_loss: 2.7048 - val_accuracy: 0.7718\n", + "Epoch 46/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.4606 - accuracy: 0.8549 - val_loss: 2.7248 - val_accuracy: 0.7433\n", + "Epoch 47/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.4456 - accuracy: 0.8558 - val_loss: 2.7857 - val_accuracy: 0.7629\n", + "Epoch 48/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.4397 - accuracy: 0.8540 - val_loss: 2.6798 - val_accuracy: 0.7558\n", + "Epoch 49/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.4188 - accuracy: 0.8634 - val_loss: 2.7205 - val_accuracy: 0.7558\n", + "Epoch 50/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.3832 - accuracy: 0.8835 - val_loss: 2.7230 - val_accuracy: 0.7629\n", + "Epoch 51/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.4038 - accuracy: 0.8705 - val_loss: 2.7941 - val_accuracy: 0.7718\n", + "Epoch 52/500\n", + "3/3 [==============================] - 0s 19ms/step - loss: 0.4088 - accuracy: 0.8687 - val_loss: 2.8485 - val_accuracy: 0.7611\n", + "Epoch 53/500\n", + "3/3 [==============================] - 0s 14ms/step - loss: 0.3845 - accuracy: 0.8759 - val_loss: 2.7727 - val_accuracy: 0.7487\n", + "Epoch 54/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.3841 - accuracy: 0.8772 - val_loss: 2.7037 - val_accuracy: 0.7540\n", + "Epoch 55/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.3663 - accuracy: 0.8804 - val_loss: 2.6858 - val_accuracy: 0.7611\n", + "Epoch 56/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.3764 - accuracy: 0.8799 - val_loss: 2.7975 - val_accuracy: 0.7772\n", + "Epoch 57/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.3831 - accuracy: 0.8781 - val_loss: 2.7318 - val_accuracy: 0.7932\n", + "Epoch 58/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.3599 - accuracy: 0.8911 - val_loss: 2.7317 - val_accuracy: 0.7897\n", + "Epoch 59/500\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "3/3 [==============================] - 0s 15ms/step - loss: 0.3606 - accuracy: 0.8830 - val_loss: 2.7506 - val_accuracy: 0.7986\n", + "Epoch 60/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.3203 - accuracy: 0.9027 - val_loss: 2.7527 - val_accuracy: 0.7861\n", + "Epoch 61/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.3547 - accuracy: 0.8920 - val_loss: 2.7845 - val_accuracy: 0.7754\n", + "Epoch 62/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.3467 - accuracy: 0.8915 - val_loss: 2.8740 - val_accuracy: 0.7736\n", + "Epoch 63/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.3388 - accuracy: 0.8884 - val_loss: 2.7419 - val_accuracy: 0.7736\n", + "Epoch 64/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.3352 - accuracy: 0.8973 - val_loss: 2.7673 - val_accuracy: 0.7950\n", + "Epoch 65/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.3243 - accuracy: 0.8973 - val_loss: 2.8504 - val_accuracy: 0.7718\n", + "Epoch 66/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.3393 - accuracy: 0.8866 - val_loss: 2.7669 - val_accuracy: 0.7879\n", + "Epoch 67/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.3233 - accuracy: 0.8942 - val_loss: 2.7359 - val_accuracy: 0.7950\n", + "Epoch 68/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.3131 - accuracy: 0.9085 - val_loss: 2.7986 - val_accuracy: 0.8039\n", + "Epoch 69/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.2916 - accuracy: 0.9067 - val_loss: 2.7160 - val_accuracy: 0.7932\n", + "Epoch 70/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.2812 - accuracy: 0.9156 - val_loss: 2.7732 - val_accuracy: 0.8075\n", + "Epoch 71/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.2910 - accuracy: 0.9062 - val_loss: 2.8327 - val_accuracy: 0.7986\n", + "Epoch 72/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.2953 - accuracy: 0.9107 - val_loss: 2.7406 - val_accuracy: 0.7914\n", + "Epoch 73/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.2830 - accuracy: 0.9196 - val_loss: 2.7630 - val_accuracy: 0.8093\n", + "Epoch 74/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.2836 - accuracy: 0.9121 - val_loss: 2.7631 - val_accuracy: 0.7879\n", + "Epoch 75/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.2727 - accuracy: 0.9112 - val_loss: 2.7862 - val_accuracy: 0.8039\n", + "Epoch 76/500\n", + "3/3 [==============================] - 0s 153ms/step - loss: 0.2810 - accuracy: 0.9179 - val_loss: 2.7986 - val_accuracy: 0.7897\n", + "Epoch 77/500\n", + "3/3 [==============================] - 0s 104ms/step - loss: 0.2798 - accuracy: 0.9098 - val_loss: 2.7958 - val_accuracy: 0.8093\n", + "Epoch 78/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.2669 - accuracy: 0.9125 - val_loss: 2.7845 - val_accuracy: 0.8004\n", + "Epoch 79/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.2597 - accuracy: 0.9152 - val_loss: 2.8868 - val_accuracy: 0.7843\n", + "Epoch 80/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.2689 - accuracy: 0.9165 - val_loss: 2.8603 - val_accuracy: 0.7968\n", + "Epoch 81/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 0.2551 - accuracy: 0.9192 - val_loss: 2.9133 - val_accuracy: 0.7968\n", + "Epoch 82/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.2607 - accuracy: 0.9165 - val_loss: 2.9144 - val_accuracy: 0.7950\n", + "Epoch 83/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.2439 - accuracy: 0.9210 - val_loss: 2.8191 - val_accuracy: 0.8075\n", + "Epoch 84/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.2671 - accuracy: 0.9192 - val_loss: 2.9166 - val_accuracy: 0.8004\n", + "Epoch 85/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.2421 - accuracy: 0.9250 - val_loss: 2.9474 - val_accuracy: 0.8128\n", + "Epoch 86/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.2479 - accuracy: 0.9214 - val_loss: 2.8581 - val_accuracy: 0.7914\n", + "Epoch 87/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.2603 - accuracy: 0.9138 - val_loss: 2.8995 - val_accuracy: 0.8200\n", + "Epoch 88/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.2462 - accuracy: 0.9263 - val_loss: 2.9085 - val_accuracy: 0.8075\n", + "Epoch 89/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.2258 - accuracy: 0.9321 - val_loss: 2.9171 - val_accuracy: 0.8271\n", + "Epoch 90/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.2435 - accuracy: 0.9232 - val_loss: 2.8813 - val_accuracy: 0.7986\n", + "Epoch 91/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.2352 - accuracy: 0.9277 - val_loss: 2.9242 - val_accuracy: 0.7843\n", + "Epoch 92/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.2367 - accuracy: 0.9219 - val_loss: 2.8809 - val_accuracy: 0.8111\n", + "Epoch 93/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 0.2276 - accuracy: 0.9330 - val_loss: 2.8483 - val_accuracy: 0.8057\n", + "Epoch 94/500\n", + "3/3 [==============================] - 0s 14ms/step - loss: 0.2246 - accuracy: 0.9335 - val_loss: 2.9111 - val_accuracy: 0.8004\n", + "Epoch 95/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.2268 - accuracy: 0.9286 - val_loss: 2.9409 - val_accuracy: 0.7932\n", + "Epoch 96/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.2320 - accuracy: 0.9312 - val_loss: 2.8713 - val_accuracy: 0.8075\n", + "Epoch 97/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.2215 - accuracy: 0.9259 - val_loss: 2.8130 - val_accuracy: 0.7986\n", + "Epoch 98/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.2245 - accuracy: 0.9277 - val_loss: 2.9014 - val_accuracy: 0.8182\n", + "Epoch 99/500\n", + "3/3 [==============================] - 0s 19ms/step - loss: 0.2245 - accuracy: 0.9295 - val_loss: 2.9285 - val_accuracy: 0.8217\n", + "Epoch 100/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.2149 - accuracy: 0.9362 - val_loss: 2.9053 - val_accuracy: 0.8182\n", + "Epoch 101/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.2259 - accuracy: 0.9246 - val_loss: 2.9373 - val_accuracy: 0.7932\n", + "Epoch 102/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.2328 - accuracy: 0.9250 - val_loss: 2.9954 - val_accuracy: 0.8164\n", + "Epoch 103/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.2329 - accuracy: 0.9214 - val_loss: 2.9089 - val_accuracy: 0.8164\n", + "Epoch 104/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.2065 - accuracy: 0.9384 - val_loss: 3.0448 - val_accuracy: 0.7897\n", + "Epoch 105/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.2068 - accuracy: 0.9344 - val_loss: 3.0119 - val_accuracy: 0.8146\n", + "Epoch 106/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.2238 - accuracy: 0.9259 - val_loss: 2.9144 - val_accuracy: 0.8164\n", + "Epoch 107/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.2243 - accuracy: 0.9263 - val_loss: 3.0165 - val_accuracy: 0.7843\n", + "Epoch 108/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.2085 - accuracy: 0.9357 - val_loss: 3.0623 - val_accuracy: 0.8164\n", + "Epoch 109/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1828 - accuracy: 0.9379 - val_loss: 3.1144 - val_accuracy: 0.8164\n", + "Epoch 110/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.2224 - accuracy: 0.9304 - val_loss: 3.0173 - val_accuracy: 0.7914\n", + "Epoch 111/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 0.2091 - accuracy: 0.9330 - val_loss: 2.8703 - val_accuracy: 0.7932\n", + "Epoch 112/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.2044 - accuracy: 0.9384 - val_loss: 2.9790 - val_accuracy: 0.8128\n", + "Epoch 113/500\n", + "3/3 [==============================] - 0s 134ms/step - loss: 0.1822 - accuracy: 0.9397 - val_loss: 3.0940 - val_accuracy: 0.7932\n", + "Epoch 114/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1925 - accuracy: 0.9429 - val_loss: 3.1540 - val_accuracy: 0.8039\n", + "Epoch 115/500\n", + "3/3 [==============================] - 0s 220ms/step - loss: 0.2025 - accuracy: 0.9362 - val_loss: 2.9488 - val_accuracy: 0.8217\n", + "Epoch 116/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1884 - accuracy: 0.9411 - val_loss: 3.0015 - val_accuracy: 0.8200\n", + "Epoch 117/500\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "3/3 [==============================] - 0s 18ms/step - loss: 0.1994 - accuracy: 0.9402 - val_loss: 3.0726 - val_accuracy: 0.8200\n", + "Epoch 118/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1901 - accuracy: 0.9455 - val_loss: 3.0537 - val_accuracy: 0.8093\n", + "Epoch 119/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1750 - accuracy: 0.9487 - val_loss: 3.0673 - val_accuracy: 0.8271\n", + "Epoch 120/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1936 - accuracy: 0.9353 - val_loss: 3.0625 - val_accuracy: 0.8111\n", + "Epoch 121/500\n", + "3/3 [==============================] - 0s 149ms/step - loss: 0.1665 - accuracy: 0.9482 - val_loss: 3.1008 - val_accuracy: 0.8004\n", + "Epoch 122/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1895 - accuracy: 0.9335 - val_loss: 3.1380 - val_accuracy: 0.8200\n", + "Epoch 123/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1767 - accuracy: 0.9451 - val_loss: 3.1362 - val_accuracy: 0.7914\n", + "Epoch 124/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 0.1946 - accuracy: 0.9339 - val_loss: 2.9370 - val_accuracy: 0.8235\n", + "Epoch 125/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1923 - accuracy: 0.9393 - val_loss: 3.0337 - val_accuracy: 0.8235\n", + "Epoch 126/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1753 - accuracy: 0.9473 - val_loss: 3.1784 - val_accuracy: 0.8324\n", + "Epoch 127/500\n", + "3/3 [==============================] - 0s 126ms/step - loss: 0.2024 - accuracy: 0.9397 - val_loss: 3.0469 - val_accuracy: 0.8324\n", + "Epoch 128/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1813 - accuracy: 0.9424 - val_loss: 3.0067 - val_accuracy: 0.8182\n", + "Epoch 129/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.2073 - accuracy: 0.9362 - val_loss: 3.0784 - val_accuracy: 0.8253\n", + "Epoch 130/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1718 - accuracy: 0.9482 - val_loss: 3.0529 - val_accuracy: 0.8146\n", + "Epoch 131/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1647 - accuracy: 0.9446 - val_loss: 2.9477 - val_accuracy: 0.8128\n", + "Epoch 132/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1883 - accuracy: 0.9478 - val_loss: 2.8586 - val_accuracy: 0.7950\n", + "Epoch 133/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1725 - accuracy: 0.9429 - val_loss: 3.1615 - val_accuracy: 0.8093\n", + "Epoch 134/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1935 - accuracy: 0.9362 - val_loss: 3.1727 - val_accuracy: 0.8200\n", + "Epoch 135/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1727 - accuracy: 0.9411 - val_loss: 3.0221 - val_accuracy: 0.7968\n", + "Epoch 136/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1700 - accuracy: 0.9455 - val_loss: 3.1363 - val_accuracy: 0.8057\n", + "Epoch 137/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 0.1830 - accuracy: 0.9375 - val_loss: 3.1210 - val_accuracy: 0.8128\n", + "Epoch 138/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1953 - accuracy: 0.9375 - val_loss: 3.3607 - val_accuracy: 0.8039\n", + "Epoch 139/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.2002 - accuracy: 0.9339 - val_loss: 3.2200 - val_accuracy: 0.7914\n", + "Epoch 140/500\n", + "3/3 [==============================] - 0s 19ms/step - loss: 0.1911 - accuracy: 0.9362 - val_loss: 3.1141 - val_accuracy: 0.7968\n", + "Epoch 141/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1854 - accuracy: 0.9411 - val_loss: 3.1925 - val_accuracy: 0.8164\n", + "Epoch 142/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1685 - accuracy: 0.9527 - val_loss: 3.2378 - val_accuracy: 0.8004\n", + "Epoch 143/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1664 - accuracy: 0.9438 - val_loss: 3.1528 - val_accuracy: 0.8021\n", + "Epoch 144/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 0.1615 - accuracy: 0.9487 - val_loss: 3.0998 - val_accuracy: 0.8200\n", + "Epoch 145/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1657 - accuracy: 0.9487 - val_loss: 3.1144 - val_accuracy: 0.8146\n", + "Epoch 146/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1693 - accuracy: 0.9420 - val_loss: 3.0132 - val_accuracy: 0.8289\n", + "Epoch 147/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1471 - accuracy: 0.9540 - val_loss: 3.1395 - val_accuracy: 0.8235\n", + "Epoch 148/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1558 - accuracy: 0.9580 - val_loss: 3.1889 - val_accuracy: 0.8128\n", + "Epoch 149/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1562 - accuracy: 0.9513 - val_loss: 2.9373 - val_accuracy: 0.8307\n", + "Epoch 150/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1637 - accuracy: 0.9464 - val_loss: 2.9766 - val_accuracy: 0.8075\n", + "Epoch 151/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1509 - accuracy: 0.9500 - val_loss: 3.1998 - val_accuracy: 0.8182\n", + "Epoch 152/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1811 - accuracy: 0.9375 - val_loss: 3.1149 - val_accuracy: 0.8164\n", + "Epoch 153/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1639 - accuracy: 0.9451 - val_loss: 3.0750 - val_accuracy: 0.8111\n", + "Epoch 154/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1711 - accuracy: 0.9451 - val_loss: 3.1738 - val_accuracy: 0.8004\n", + "Epoch 155/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1435 - accuracy: 0.9540 - val_loss: 3.2347 - val_accuracy: 0.8111\n", + "Epoch 156/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1481 - accuracy: 0.9518 - val_loss: 3.2279 - val_accuracy: 0.8075\n", + "Epoch 157/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1564 - accuracy: 0.9442 - val_loss: 3.1658 - val_accuracy: 0.7950\n", + "Epoch 158/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1698 - accuracy: 0.9438 - val_loss: 3.0846 - val_accuracy: 0.8200\n", + "Epoch 159/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1358 - accuracy: 0.9598 - val_loss: 3.4012 - val_accuracy: 0.8093\n", + "Epoch 160/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1670 - accuracy: 0.9451 - val_loss: 3.1913 - val_accuracy: 0.8111\n", + "Epoch 161/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1561 - accuracy: 0.9509 - val_loss: 2.7940 - val_accuracy: 0.8146\n", + "Epoch 162/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1648 - accuracy: 0.9469 - val_loss: 2.9987 - val_accuracy: 0.8004\n", + "Epoch 163/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1511 - accuracy: 0.9464 - val_loss: 3.2705 - val_accuracy: 0.8200\n", + "Epoch 164/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1742 - accuracy: 0.9438 - val_loss: 3.1697 - val_accuracy: 0.8324\n", + "Epoch 165/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1407 - accuracy: 0.9500 - val_loss: 3.0942 - val_accuracy: 0.8307\n", + "Epoch 166/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1362 - accuracy: 0.9513 - val_loss: 3.0865 - val_accuracy: 0.8182\n", + "Epoch 167/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1515 - accuracy: 0.9478 - val_loss: 3.1520 - val_accuracy: 0.8111\n", + "Epoch 168/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1569 - accuracy: 0.9513 - val_loss: 3.1619 - val_accuracy: 0.8289\n", + "Epoch 169/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1419 - accuracy: 0.9496 - val_loss: 3.0921 - val_accuracy: 0.8253\n", + "Epoch 170/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1451 - accuracy: 0.9491 - val_loss: 3.1316 - val_accuracy: 0.8217\n", + "Epoch 171/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1282 - accuracy: 0.9545 - val_loss: 3.1724 - val_accuracy: 0.8217\n", + "Epoch 172/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1235 - accuracy: 0.9612 - val_loss: 3.0868 - val_accuracy: 0.8324\n", + "Epoch 173/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1428 - accuracy: 0.9513 - val_loss: 3.1058 - val_accuracy: 0.8324\n", + "Epoch 174/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1589 - accuracy: 0.9504 - val_loss: 3.1856 - val_accuracy: 0.8164\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 175/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1604 - accuracy: 0.9504 - val_loss: 3.1547 - val_accuracy: 0.8217\n", + "Epoch 176/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1324 - accuracy: 0.9589 - val_loss: 3.3192 - val_accuracy: 0.8128\n", + "Epoch 177/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1633 - accuracy: 0.9487 - val_loss: 3.1716 - val_accuracy: 0.8146\n", + "Epoch 178/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1290 - accuracy: 0.9576 - val_loss: 3.1262 - val_accuracy: 0.8182\n", + "Epoch 179/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1627 - accuracy: 0.9500 - val_loss: 3.1685 - val_accuracy: 0.8271\n", + "Epoch 180/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 0.1388 - accuracy: 0.9545 - val_loss: 3.2582 - val_accuracy: 0.8307\n", + "Epoch 181/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1535 - accuracy: 0.9500 - val_loss: 3.3198 - val_accuracy: 0.8324\n", + "Epoch 182/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1307 - accuracy: 0.9585 - val_loss: 3.2408 - val_accuracy: 0.8217\n", + "Epoch 183/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1512 - accuracy: 0.9509 - val_loss: 3.1087 - val_accuracy: 0.8182\n", + "Epoch 184/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1336 - accuracy: 0.9563 - val_loss: 3.1705 - val_accuracy: 0.8324\n", + "Epoch 185/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1489 - accuracy: 0.9549 - val_loss: 3.2197 - val_accuracy: 0.8253\n", + "Epoch 186/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1416 - accuracy: 0.9540 - val_loss: 3.2992 - val_accuracy: 0.8289\n", + "Epoch 187/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1260 - accuracy: 0.9634 - val_loss: 3.3130 - val_accuracy: 0.8164\n", + "Epoch 188/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1442 - accuracy: 0.9460 - val_loss: 3.1350 - val_accuracy: 0.8235\n", + "Epoch 189/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1337 - accuracy: 0.9545 - val_loss: 3.1752 - val_accuracy: 0.8146\n", + "Epoch 190/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1377 - accuracy: 0.9522 - val_loss: 3.3670 - val_accuracy: 0.8217\n", + "Epoch 191/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1259 - accuracy: 0.9625 - val_loss: 3.3380 - val_accuracy: 0.8271\n", + "Epoch 192/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1272 - accuracy: 0.9571 - val_loss: 3.2256 - val_accuracy: 0.8253\n", + "Epoch 193/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1243 - accuracy: 0.9616 - val_loss: 3.3936 - val_accuracy: 0.8111\n", + "Epoch 194/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1229 - accuracy: 0.9625 - val_loss: 3.4608 - val_accuracy: 0.8128\n", + "Epoch 195/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1194 - accuracy: 0.9580 - val_loss: 3.2403 - val_accuracy: 0.8360\n", + "Epoch 196/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1349 - accuracy: 0.9571 - val_loss: 3.2221 - val_accuracy: 0.8253\n", + "Epoch 197/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 0.1219 - accuracy: 0.9607 - val_loss: 3.3777 - val_accuracy: 0.8128\n", + "Epoch 198/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1302 - accuracy: 0.9567 - val_loss: 3.3118 - val_accuracy: 0.8378\n", + "Epoch 199/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1288 - accuracy: 0.9554 - val_loss: 3.2091 - val_accuracy: 0.8342\n", + "Epoch 200/500\n", + "3/3 [==============================] - 0s 19ms/step - loss: 0.1283 - accuracy: 0.9563 - val_loss: 3.1435 - val_accuracy: 0.8289\n", + "Epoch 201/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1181 - accuracy: 0.9656 - val_loss: 3.2117 - val_accuracy: 0.8360\n", + "Epoch 202/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1094 - accuracy: 0.9652 - val_loss: 3.2909 - val_accuracy: 0.8182\n", + "Epoch 203/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1297 - accuracy: 0.9554 - val_loss: 3.2943 - val_accuracy: 0.8182\n", + "Epoch 204/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1320 - accuracy: 0.9558 - val_loss: 3.1315 - val_accuracy: 0.8271\n", + "Epoch 205/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1358 - accuracy: 0.9540 - val_loss: 3.2054 - val_accuracy: 0.8289\n", + "Epoch 206/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1166 - accuracy: 0.9621 - val_loss: 3.4830 - val_accuracy: 0.8253\n", + "Epoch 207/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1214 - accuracy: 0.9594 - val_loss: 3.4861 - val_accuracy: 0.8271\n", + "Epoch 208/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1242 - accuracy: 0.9594 - val_loss: 3.1450 - val_accuracy: 0.8324\n", + "Epoch 209/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1432 - accuracy: 0.9531 - val_loss: 3.2652 - val_accuracy: 0.8217\n", + "Epoch 210/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1401 - accuracy: 0.9549 - val_loss: 3.2223 - val_accuracy: 0.7897\n", + "Epoch 211/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1426 - accuracy: 0.9531 - val_loss: 3.2312 - val_accuracy: 0.8093\n", + "Epoch 212/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1471 - accuracy: 0.9487 - val_loss: 3.3002 - val_accuracy: 0.8235\n", + "Epoch 213/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1490 - accuracy: 0.9500 - val_loss: 3.2000 - val_accuracy: 0.8093\n", + "Epoch 214/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1474 - accuracy: 0.9482 - val_loss: 3.2497 - val_accuracy: 0.8075\n", + "Epoch 215/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1592 - accuracy: 0.9438 - val_loss: 3.2296 - val_accuracy: 0.8093\n", + "Epoch 216/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1495 - accuracy: 0.9522 - val_loss: 2.9942 - val_accuracy: 0.7968\n", + "Epoch 217/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1706 - accuracy: 0.9433 - val_loss: 3.2004 - val_accuracy: 0.8111\n", + "Epoch 218/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1529 - accuracy: 0.9540 - val_loss: 3.4679 - val_accuracy: 0.8039\n", + "Epoch 219/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1556 - accuracy: 0.9496 - val_loss: 3.4337 - val_accuracy: 0.8111\n", + "Epoch 220/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1544 - accuracy: 0.9496 - val_loss: 3.0612 - val_accuracy: 0.8200\n", + "Epoch 221/500\n", + "3/3 [==============================] - 0s 27ms/step - loss: 0.1630 - accuracy: 0.9429 - val_loss: 3.1624 - val_accuracy: 0.7986\n", + "Epoch 222/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1723 - accuracy: 0.9402 - val_loss: 3.4154 - val_accuracy: 0.8093\n", + "Epoch 223/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1404 - accuracy: 0.9531 - val_loss: 3.4807 - val_accuracy: 0.7968\n", + "Epoch 224/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1449 - accuracy: 0.9522 - val_loss: 3.2386 - val_accuracy: 0.8039\n", + "Epoch 225/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1395 - accuracy: 0.9522 - val_loss: 3.1111 - val_accuracy: 0.8039\n", + "Epoch 226/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1783 - accuracy: 0.9362 - val_loss: 3.1432 - val_accuracy: 0.8111\n", + "Epoch 227/500\n", + "3/3 [==============================] - 0s 21ms/step - loss: 0.1338 - accuracy: 0.9571 - val_loss: 3.4125 - val_accuracy: 0.7986\n", + "Epoch 228/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1360 - accuracy: 0.9554 - val_loss: 3.5563 - val_accuracy: 0.7932\n", + "Epoch 229/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 0.1282 - accuracy: 0.9563 - val_loss: 3.1964 - val_accuracy: 0.7986\n", + "Epoch 230/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1381 - accuracy: 0.9549 - val_loss: 3.0907 - val_accuracy: 0.8182\n", + "Epoch 231/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1285 - accuracy: 0.9598 - val_loss: 3.3284 - val_accuracy: 0.8021\n", + "Epoch 232/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1377 - accuracy: 0.9504 - val_loss: 3.3697 - val_accuracy: 0.8039\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 233/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1235 - accuracy: 0.9563 - val_loss: 3.2361 - val_accuracy: 0.8182\n", + "Epoch 234/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1398 - accuracy: 0.9563 - val_loss: 3.1242 - val_accuracy: 0.8128\n", + "Epoch 235/500\n", + "3/3 [==============================] - 0s 20ms/step - loss: 0.1236 - accuracy: 0.9580 - val_loss: 3.1575 - val_accuracy: 0.8289\n", + "Epoch 236/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1406 - accuracy: 0.9558 - val_loss: 3.2175 - val_accuracy: 0.8164\n", + "Epoch 237/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1277 - accuracy: 0.9603 - val_loss: 3.3241 - val_accuracy: 0.8182\n", + "Epoch 238/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1246 - accuracy: 0.9589 - val_loss: 3.2664 - val_accuracy: 0.8414\n", + "Epoch 239/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1213 - accuracy: 0.9585 - val_loss: 3.3026 - val_accuracy: 0.7968\n", + "Epoch 240/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1289 - accuracy: 0.9567 - val_loss: 3.4185 - val_accuracy: 0.7950\n", + "Epoch 241/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1281 - accuracy: 0.9563 - val_loss: 3.4039 - val_accuracy: 0.7986\n", + "Epoch 242/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1220 - accuracy: 0.9612 - val_loss: 3.3447 - val_accuracy: 0.7986\n", + "Epoch 243/500\n", + "3/3 [==============================] - 1s 258ms/step - loss: 0.1522 - accuracy: 0.9513 - val_loss: 3.3611 - val_accuracy: 0.7861\n", + "Epoch 244/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1039 - accuracy: 0.9692 - val_loss: 3.4383 - val_accuracy: 0.8182\n", + "Epoch 245/500\n", + "3/3 [==============================] - 0s 14ms/step - loss: 0.1111 - accuracy: 0.9643 - val_loss: 3.4672 - val_accuracy: 0.8200\n", + "Epoch 246/500\n", + "3/3 [==============================] - 0s 23ms/step - loss: 0.1123 - accuracy: 0.9603 - val_loss: 3.3799 - val_accuracy: 0.8146\n", + "Epoch 247/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1252 - accuracy: 0.9625 - val_loss: 3.4479 - val_accuracy: 0.7986\n", + "Epoch 248/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1206 - accuracy: 0.9589 - val_loss: 3.3533 - val_accuracy: 0.8182\n", + "Epoch 249/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1451 - accuracy: 0.9473 - val_loss: 3.2581 - val_accuracy: 0.8004\n", + "Epoch 250/500\n", + "3/3 [==============================] - 0s 14ms/step - loss: 0.1213 - accuracy: 0.9603 - val_loss: 3.3730 - val_accuracy: 0.7879\n", + "Epoch 251/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1327 - accuracy: 0.9549 - val_loss: 3.3880 - val_accuracy: 0.8128\n", + "Epoch 252/500\n", + "3/3 [==============================] - 0s 14ms/step - loss: 0.1264 - accuracy: 0.9603 - val_loss: 3.4151 - val_accuracy: 0.8128\n", + "Epoch 253/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1157 - accuracy: 0.9612 - val_loss: 3.3689 - val_accuracy: 0.8253\n", + "Epoch 254/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1361 - accuracy: 0.9567 - val_loss: 3.3656 - val_accuracy: 0.8039\n", + "Epoch 255/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1230 - accuracy: 0.9616 - val_loss: 3.3204 - val_accuracy: 0.8146\n", + "Epoch 256/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 0.1199 - accuracy: 0.9661 - val_loss: 3.4041 - val_accuracy: 0.8307\n", + "Epoch 257/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1016 - accuracy: 0.9670 - val_loss: 3.5122 - val_accuracy: 0.8164\n", + "Epoch 258/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1246 - accuracy: 0.9607 - val_loss: 3.4578 - val_accuracy: 0.8111\n", + "Epoch 259/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1082 - accuracy: 0.9643 - val_loss: 3.5107 - val_accuracy: 0.8057\n", + "Epoch 260/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1053 - accuracy: 0.9661 - val_loss: 3.5691 - val_accuracy: 0.8217\n", + "Epoch 261/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1192 - accuracy: 0.9580 - val_loss: 3.5103 - val_accuracy: 0.8200\n", + "Epoch 262/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1145 - accuracy: 0.9612 - val_loss: 3.3533 - val_accuracy: 0.8111\n", + "Epoch 263/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1263 - accuracy: 0.9576 - val_loss: 3.4351 - val_accuracy: 0.8075\n", + "Epoch 264/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1189 - accuracy: 0.9629 - val_loss: 3.5318 - val_accuracy: 0.8307\n", + "Epoch 265/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1115 - accuracy: 0.9625 - val_loss: 3.6668 - val_accuracy: 0.8057\n", + "Epoch 266/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1368 - accuracy: 0.9504 - val_loss: 3.4787 - val_accuracy: 0.8164\n", + "Epoch 267/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1064 - accuracy: 0.9621 - val_loss: 3.4085 - val_accuracy: 0.8235\n", + "Epoch 268/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0973 - accuracy: 0.9701 - val_loss: 3.3725 - val_accuracy: 0.8253\n", + "Epoch 269/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 0.0958 - accuracy: 0.9661 - val_loss: 3.4961 - val_accuracy: 0.8182\n", + "Epoch 270/500\n", + "3/3 [==============================] - 0s 28ms/step - loss: 0.1064 - accuracy: 0.9661 - val_loss: 3.6018 - val_accuracy: 0.8289\n", + "Epoch 271/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1169 - accuracy: 0.9585 - val_loss: 3.3914 - val_accuracy: 0.8289\n", + "Epoch 272/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0949 - accuracy: 0.9701 - val_loss: 3.2555 - val_accuracy: 0.8271\n", + "Epoch 273/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1437 - accuracy: 0.9482 - val_loss: 3.5002 - val_accuracy: 0.8217\n", + "Epoch 274/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1182 - accuracy: 0.9621 - val_loss: 3.5930 - val_accuracy: 0.8271\n", + "Epoch 275/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1010 - accuracy: 0.9656 - val_loss: 3.4905 - val_accuracy: 0.8217\n", + "Epoch 276/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0942 - accuracy: 0.9696 - val_loss: 3.4673 - val_accuracy: 0.8200\n", + "Epoch 277/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1035 - accuracy: 0.9679 - val_loss: 3.3489 - val_accuracy: 0.8271\n", + "Epoch 278/500\n", + "3/3 [==============================] - 0s 21ms/step - loss: 0.0932 - accuracy: 0.9656 - val_loss: 3.4957 - val_accuracy: 0.8164\n", + "Epoch 279/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0968 - accuracy: 0.9656 - val_loss: 3.5927 - val_accuracy: 0.8217\n", + "Epoch 280/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.0956 - accuracy: 0.9688 - val_loss: 3.5349 - val_accuracy: 0.8164\n", + "Epoch 281/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0940 - accuracy: 0.9674 - val_loss: 3.4397 - val_accuracy: 0.8217\n", + "Epoch 282/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0933 - accuracy: 0.9674 - val_loss: 3.5364 - val_accuracy: 0.8182\n", + "Epoch 283/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1056 - accuracy: 0.9625 - val_loss: 3.5316 - val_accuracy: 0.8324\n", + "Epoch 284/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0942 - accuracy: 0.9692 - val_loss: 3.3578 - val_accuracy: 0.8307\n", + "Epoch 285/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 0.0980 - accuracy: 0.9679 - val_loss: 3.4109 - val_accuracy: 0.8182\n", + "Epoch 286/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0963 - accuracy: 0.9683 - val_loss: 3.7121 - val_accuracy: 0.8182\n", + "Epoch 287/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0947 - accuracy: 0.9674 - val_loss: 3.8286 - val_accuracy: 0.8182\n", + "Epoch 288/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0954 - accuracy: 0.9705 - val_loss: 3.6221 - val_accuracy: 0.8289\n", + "Epoch 289/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 0.0953 - accuracy: 0.9701 - val_loss: 3.5977 - val_accuracy: 0.8146\n", + "Epoch 290/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0857 - accuracy: 0.9723 - val_loss: 3.7337 - val_accuracy: 0.8324\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 291/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1078 - accuracy: 0.9607 - val_loss: 3.7470 - val_accuracy: 0.8360\n", + "Epoch 292/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0792 - accuracy: 0.9759 - val_loss: 3.6461 - val_accuracy: 0.8146\n", + "Epoch 293/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1050 - accuracy: 0.9629 - val_loss: 3.6083 - val_accuracy: 0.8217\n", + "Epoch 294/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0996 - accuracy: 0.9696 - val_loss: 3.6849 - val_accuracy: 0.8289\n", + "Epoch 295/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1101 - accuracy: 0.9621 - val_loss: 3.7585 - val_accuracy: 0.8200\n", + "Epoch 296/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0865 - accuracy: 0.9719 - val_loss: 3.7206 - val_accuracy: 0.8111\n", + "Epoch 297/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 0.0894 - accuracy: 0.9728 - val_loss: 3.6203 - val_accuracy: 0.8307\n", + "Epoch 298/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1039 - accuracy: 0.9647 - val_loss: 3.7966 - val_accuracy: 0.8200\n", + "Epoch 299/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0732 - accuracy: 0.9777 - val_loss: 3.8585 - val_accuracy: 0.8021\n", + "Epoch 300/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0982 - accuracy: 0.9643 - val_loss: 3.8914 - val_accuracy: 0.8021\n", + "Epoch 301/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1021 - accuracy: 0.9683 - val_loss: 3.5062 - val_accuracy: 0.8271\n", + "Epoch 302/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1023 - accuracy: 0.9634 - val_loss: 3.3687 - val_accuracy: 0.8378\n", + "Epoch 303/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.0789 - accuracy: 0.9741 - val_loss: 3.7674 - val_accuracy: 0.8200\n", + "Epoch 304/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0976 - accuracy: 0.9696 - val_loss: 4.0810 - val_accuracy: 0.8200\n", + "Epoch 305/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1075 - accuracy: 0.9652 - val_loss: 3.6278 - val_accuracy: 0.8271\n", + "Epoch 306/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0750 - accuracy: 0.9754 - val_loss: 3.4697 - val_accuracy: 0.8057\n", + "Epoch 307/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1064 - accuracy: 0.9629 - val_loss: 3.8019 - val_accuracy: 0.8217\n", + "Epoch 308/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 0.0853 - accuracy: 0.9719 - val_loss: 4.0418 - val_accuracy: 0.8164\n", + "Epoch 309/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1105 - accuracy: 0.9616 - val_loss: 3.6298 - val_accuracy: 0.8182\n", + "Epoch 310/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0952 - accuracy: 0.9679 - val_loss: 3.6392 - val_accuracy: 0.8200\n", + "Epoch 311/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0890 - accuracy: 0.9688 - val_loss: 4.0134 - val_accuracy: 0.8200\n", + "Epoch 312/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1008 - accuracy: 0.9634 - val_loss: 3.8818 - val_accuracy: 0.8271\n", + "Epoch 313/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 0.0797 - accuracy: 0.9750 - val_loss: 3.4721 - val_accuracy: 0.8093\n", + "Epoch 314/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0946 - accuracy: 0.9701 - val_loss: 3.5349 - val_accuracy: 0.8324\n", + "Epoch 315/500\n", + "3/3 [==============================] - 0s 20ms/step - loss: 0.0999 - accuracy: 0.9665 - val_loss: 3.8269 - val_accuracy: 0.8235\n", + "Epoch 316/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1138 - accuracy: 0.9652 - val_loss: 3.7666 - val_accuracy: 0.8396\n", + "Epoch 317/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0908 - accuracy: 0.9714 - val_loss: 3.4518 - val_accuracy: 0.8182\n", + "Epoch 318/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1043 - accuracy: 0.9621 - val_loss: 3.5901 - val_accuracy: 0.8057\n", + "Epoch 319/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0960 - accuracy: 0.9732 - val_loss: 4.0491 - val_accuracy: 0.7914\n", + "Epoch 320/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 0.0802 - accuracy: 0.9737 - val_loss: 3.9744 - val_accuracy: 0.8253\n", + "Epoch 321/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0844 - accuracy: 0.9688 - val_loss: 3.6495 - val_accuracy: 0.8217\n", + "Epoch 322/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0974 - accuracy: 0.9683 - val_loss: 3.4948 - val_accuracy: 0.8289\n", + "Epoch 323/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0885 - accuracy: 0.9674 - val_loss: 3.6379 - val_accuracy: 0.8253\n", + "Epoch 324/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0736 - accuracy: 0.9750 - val_loss: 3.9118 - val_accuracy: 0.8271\n", + "Epoch 325/500\n", + "3/3 [==============================] - 0s 87ms/step - loss: 0.0846 - accuracy: 0.9741 - val_loss: 3.9422 - val_accuracy: 0.8200\n", + "Epoch 326/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.0823 - accuracy: 0.9754 - val_loss: 3.9003 - val_accuracy: 0.8253\n", + "Epoch 327/500\n", + "3/3 [==============================] - 0s 75ms/step - loss: 0.0903 - accuracy: 0.9714 - val_loss: 3.7012 - val_accuracy: 0.8271\n", + "Epoch 328/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0849 - accuracy: 0.9696 - val_loss: 3.6057 - val_accuracy: 0.8360\n", + "Epoch 329/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0776 - accuracy: 0.9750 - val_loss: 3.6857 - val_accuracy: 0.8271\n", + "Epoch 330/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0821 - accuracy: 0.9759 - val_loss: 3.8836 - val_accuracy: 0.8111\n", + "Epoch 331/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0797 - accuracy: 0.9723 - val_loss: 3.8368 - val_accuracy: 0.8146\n", + "Epoch 332/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0782 - accuracy: 0.9705 - val_loss: 3.7394 - val_accuracy: 0.8235\n", + "Epoch 333/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0820 - accuracy: 0.9719 - val_loss: 3.7676 - val_accuracy: 0.8324\n", + "Epoch 334/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0704 - accuracy: 0.9763 - val_loss: 3.8736 - val_accuracy: 0.8324\n", + "Epoch 335/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0966 - accuracy: 0.9705 - val_loss: 3.7719 - val_accuracy: 0.8235\n", + "Epoch 336/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 0.0777 - accuracy: 0.9746 - val_loss: 3.7411 - val_accuracy: 0.8289\n", + "Epoch 337/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0705 - accuracy: 0.9795 - val_loss: 3.9666 - val_accuracy: 0.8075\n", + "Epoch 338/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0806 - accuracy: 0.9737 - val_loss: 3.9606 - val_accuracy: 0.8253\n", + "Epoch 339/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0772 - accuracy: 0.9741 - val_loss: 3.6934 - val_accuracy: 0.8307\n", + "Epoch 340/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0885 - accuracy: 0.9692 - val_loss: 3.6097 - val_accuracy: 0.8182\n", + "Epoch 341/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 0.0931 - accuracy: 0.9701 - val_loss: 3.8871 - val_accuracy: 0.8182\n", + "Epoch 342/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.0978 - accuracy: 0.9674 - val_loss: 3.9140 - val_accuracy: 0.8128\n", + "Epoch 343/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0777 - accuracy: 0.9763 - val_loss: 3.7197 - val_accuracy: 0.8164\n", + "Epoch 344/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0955 - accuracy: 0.9701 - val_loss: 3.8124 - val_accuracy: 0.8111\n", + "Epoch 345/500\n", + "3/3 [==============================] - 0s 19ms/step - loss: 0.0893 - accuracy: 0.9741 - val_loss: 3.7833 - val_accuracy: 0.8200\n", + "Epoch 346/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0890 - accuracy: 0.9737 - val_loss: 3.5796 - val_accuracy: 0.8200\n", + "Epoch 347/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0732 - accuracy: 0.9728 - val_loss: 3.8555 - val_accuracy: 0.7968\n", + "Epoch 348/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0885 - accuracy: 0.9710 - val_loss: 4.0817 - val_accuracy: 0.8039\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 349/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0973 - accuracy: 0.9696 - val_loss: 3.8088 - val_accuracy: 0.8111\n", + "Epoch 350/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1083 - accuracy: 0.9643 - val_loss: 3.6089 - val_accuracy: 0.8182\n", + "Epoch 351/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0898 - accuracy: 0.9741 - val_loss: 3.7778 - val_accuracy: 0.8235\n", + "Epoch 352/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0803 - accuracy: 0.9732 - val_loss: 4.0751 - val_accuracy: 0.8235\n", + "Epoch 353/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 0.0861 - accuracy: 0.9701 - val_loss: 4.0391 - val_accuracy: 0.8164\n", + "Epoch 354/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1004 - accuracy: 0.9705 - val_loss: 3.7999 - val_accuracy: 0.8271\n", + "Epoch 355/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0769 - accuracy: 0.9768 - val_loss: 3.6874 - val_accuracy: 0.8307\n", + "Epoch 356/500\n", + "3/3 [==============================] - 0s 14ms/step - loss: 0.0672 - accuracy: 0.9781 - val_loss: 3.8951 - val_accuracy: 0.8057\n", + "Epoch 357/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0781 - accuracy: 0.9723 - val_loss: 3.9144 - val_accuracy: 0.8217\n", + "Epoch 358/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.0698 - accuracy: 0.9772 - val_loss: 3.8349 - val_accuracy: 0.8289\n", + "Epoch 359/500\n", + "3/3 [==============================] - 0s 137ms/step - loss: 0.0951 - accuracy: 0.9683 - val_loss: 3.7267 - val_accuracy: 0.8360\n", + "Epoch 360/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0814 - accuracy: 0.9750 - val_loss: 3.8657 - val_accuracy: 0.8324\n", + "Epoch 361/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0815 - accuracy: 0.9746 - val_loss: 3.8721 - val_accuracy: 0.8360\n", + "Epoch 362/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0665 - accuracy: 0.9795 - val_loss: 3.6426 - val_accuracy: 0.8324\n", + "Epoch 363/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0896 - accuracy: 0.9728 - val_loss: 3.6636 - val_accuracy: 0.8217\n", + "Epoch 364/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0832 - accuracy: 0.9710 - val_loss: 3.9456 - val_accuracy: 0.8200\n", + "Epoch 365/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.0644 - accuracy: 0.9790 - val_loss: 3.9795 - val_accuracy: 0.8253\n", + "Epoch 366/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0762 - accuracy: 0.9750 - val_loss: 3.6663 - val_accuracy: 0.8253\n", + "Epoch 367/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1007 - accuracy: 0.9670 - val_loss: 3.4908 - val_accuracy: 0.8146\n", + "Epoch 368/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0871 - accuracy: 0.9701 - val_loss: 3.8275 - val_accuracy: 0.8396\n", + "Epoch 369/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 0.1149 - accuracy: 0.9603 - val_loss: 4.1402 - val_accuracy: 0.8235\n", + "Epoch 370/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1132 - accuracy: 0.9634 - val_loss: 3.8217 - val_accuracy: 0.8164\n", + "Epoch 371/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1420 - accuracy: 0.9531 - val_loss: 3.5258 - val_accuracy: 0.8342\n", + "Epoch 372/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1169 - accuracy: 0.9589 - val_loss: 3.8528 - val_accuracy: 0.8200\n", + "Epoch 373/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0806 - accuracy: 0.9741 - val_loss: 4.0672 - val_accuracy: 0.7950\n", + "Epoch 374/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1207 - accuracy: 0.9616 - val_loss: 3.8518 - val_accuracy: 0.8217\n", + "Epoch 375/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0956 - accuracy: 0.9701 - val_loss: 3.7917 - val_accuracy: 0.8217\n", + "Epoch 376/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1108 - accuracy: 0.9607 - val_loss: 3.6754 - val_accuracy: 0.8217\n", + "Epoch 377/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0945 - accuracy: 0.9737 - val_loss: 3.5741 - val_accuracy: 0.8111\n", + "Epoch 378/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1062 - accuracy: 0.9665 - val_loss: 3.4700 - val_accuracy: 0.8182\n", + "Epoch 379/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1233 - accuracy: 0.9652 - val_loss: 3.6749 - val_accuracy: 0.8182\n", + "Epoch 380/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1088 - accuracy: 0.9625 - val_loss: 3.6311 - val_accuracy: 0.8146\n", + "Epoch 381/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1029 - accuracy: 0.9701 - val_loss: 3.5667 - val_accuracy: 0.8235\n", + "Epoch 382/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1023 - accuracy: 0.9647 - val_loss: 3.6927 - val_accuracy: 0.8253\n", + "Epoch 383/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0863 - accuracy: 0.9719 - val_loss: 3.8814 - val_accuracy: 0.7897\n", + "Epoch 384/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1138 - accuracy: 0.9625 - val_loss: 3.9850 - val_accuracy: 0.8253\n", + "Epoch 385/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1036 - accuracy: 0.9643 - val_loss: 3.4939 - val_accuracy: 0.8324\n", + "Epoch 386/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.0886 - accuracy: 0.9705 - val_loss: 3.4939 - val_accuracy: 0.8093\n", + "Epoch 387/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0799 - accuracy: 0.9728 - val_loss: 3.8934 - val_accuracy: 0.8093\n", + "Epoch 388/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1022 - accuracy: 0.9692 - val_loss: 4.1007 - val_accuracy: 0.8289\n", + "Epoch 389/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0952 - accuracy: 0.9705 - val_loss: 3.8190 - val_accuracy: 0.8164\n", + "Epoch 390/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1045 - accuracy: 0.9683 - val_loss: 3.3549 - val_accuracy: 0.8111\n", + "Epoch 391/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0924 - accuracy: 0.9692 - val_loss: 3.5710 - val_accuracy: 0.8200\n", + "Epoch 392/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0833 - accuracy: 0.9719 - val_loss: 4.0184 - val_accuracy: 0.8253\n", + "Epoch 393/500\n", + "3/3 [==============================] - 0s 19ms/step - loss: 0.0741 - accuracy: 0.9768 - val_loss: 4.3594 - val_accuracy: 0.8164\n", + "Epoch 394/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0795 - accuracy: 0.9746 - val_loss: 4.1295 - val_accuracy: 0.8324\n", + "Epoch 395/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0872 - accuracy: 0.9714 - val_loss: 3.7597 - val_accuracy: 0.8200\n", + "Epoch 396/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0775 - accuracy: 0.9732 - val_loss: 3.5452 - val_accuracy: 0.8289\n", + "Epoch 397/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0754 - accuracy: 0.9750 - val_loss: 3.8139 - val_accuracy: 0.8039\n", + "Epoch 398/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0780 - accuracy: 0.9750 - val_loss: 4.0652 - val_accuracy: 0.8164\n", + "Epoch 399/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0905 - accuracy: 0.9670 - val_loss: 4.1023 - val_accuracy: 0.8360\n", + "Epoch 400/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0690 - accuracy: 0.9754 - val_loss: 3.9572 - val_accuracy: 0.8378\n", + "Epoch 401/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0875 - accuracy: 0.9692 - val_loss: 3.8096 - val_accuracy: 0.8324\n", + "Epoch 402/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0686 - accuracy: 0.9741 - val_loss: 3.7491 - val_accuracy: 0.8235\n", + "Epoch 403/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0632 - accuracy: 0.9799 - val_loss: 4.0235 - val_accuracy: 0.8324\n", + "Epoch 404/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0895 - accuracy: 0.9728 - val_loss: 4.2009 - val_accuracy: 0.8217\n", + "Epoch 405/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0790 - accuracy: 0.9737 - val_loss: 4.1241 - val_accuracy: 0.8182\n", + "Epoch 406/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0991 - accuracy: 0.9643 - val_loss: 3.7753 - val_accuracy: 0.8217\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 407/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0885 - accuracy: 0.9728 - val_loss: 3.9439 - val_accuracy: 0.8093\n", + "Epoch 408/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0911 - accuracy: 0.9692 - val_loss: 3.9549 - val_accuracy: 0.8057\n", + "Epoch 409/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 0.0858 - accuracy: 0.9714 - val_loss: 3.9672 - val_accuracy: 0.8093\n", + "Epoch 410/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0927 - accuracy: 0.9683 - val_loss: 4.0103 - val_accuracy: 0.8146\n", + "Epoch 411/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1115 - accuracy: 0.9558 - val_loss: 3.8561 - val_accuracy: 0.8128\n", + "Epoch 412/500\n", + "3/3 [==============================] - 0s 20ms/step - loss: 0.0982 - accuracy: 0.9705 - val_loss: 3.9945 - val_accuracy: 0.7932\n", + "Epoch 413/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0986 - accuracy: 0.9643 - val_loss: 3.9321 - val_accuracy: 0.7968\n", + "Epoch 414/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1110 - accuracy: 0.9607 - val_loss: 4.0284 - val_accuracy: 0.7897\n", + "Epoch 415/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1102 - accuracy: 0.9625 - val_loss: 4.0008 - val_accuracy: 0.8057\n", + "Epoch 416/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1138 - accuracy: 0.9612 - val_loss: 4.1750 - val_accuracy: 0.8200\n", + "Epoch 417/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0966 - accuracy: 0.9679 - val_loss: 3.9949 - val_accuracy: 0.8182\n", + "Epoch 418/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0974 - accuracy: 0.9683 - val_loss: 3.8694 - val_accuracy: 0.8307\n", + "Epoch 419/500\n", + "3/3 [==============================] - 0s 93ms/step - loss: 0.0987 - accuracy: 0.9683 - val_loss: 4.1865 - val_accuracy: 0.8200\n", + "Epoch 420/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.0982 - accuracy: 0.9661 - val_loss: 4.2851 - val_accuracy: 0.7986\n", + "Epoch 421/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0920 - accuracy: 0.9674 - val_loss: 3.8369 - val_accuracy: 0.8182\n", + "Epoch 422/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0973 - accuracy: 0.9679 - val_loss: 4.0347 - val_accuracy: 0.8146\n", + "Epoch 423/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1011 - accuracy: 0.9683 - val_loss: 4.1624 - val_accuracy: 0.8004\n", + "Epoch 424/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0826 - accuracy: 0.9750 - val_loss: 4.2419 - val_accuracy: 0.8021\n", + "Epoch 425/500\n", + "3/3 [==============================] - 1s 326ms/step - loss: 0.0687 - accuracy: 0.9754 - val_loss: 4.0753 - val_accuracy: 0.8182\n", + "Epoch 426/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.0740 - accuracy: 0.9737 - val_loss: 4.2507 - val_accuracy: 0.8075\n", + "Epoch 427/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0879 - accuracy: 0.9701 - val_loss: 3.8113 - val_accuracy: 0.8235\n", + "Epoch 428/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0894 - accuracy: 0.9750 - val_loss: 3.6997 - val_accuracy: 0.8324\n", + "Epoch 429/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0911 - accuracy: 0.9723 - val_loss: 3.8370 - val_accuracy: 0.8271\n", + "Epoch 430/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0688 - accuracy: 0.9799 - val_loss: 4.0840 - val_accuracy: 0.8075\n", + "Epoch 431/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1020 - accuracy: 0.9683 - val_loss: 4.0864 - val_accuracy: 0.7914\n", + "Epoch 432/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 0.1059 - accuracy: 0.9625 - val_loss: 3.8069 - val_accuracy: 0.8182\n", + "Epoch 433/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0772 - accuracy: 0.9723 - val_loss: 3.9571 - val_accuracy: 0.8057\n", + "Epoch 434/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.0948 - accuracy: 0.9674 - val_loss: 4.0445 - val_accuracy: 0.8128\n", + "Epoch 435/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0910 - accuracy: 0.9701 - val_loss: 3.6635 - val_accuracy: 0.8360\n", + "Epoch 436/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0802 - accuracy: 0.9746 - val_loss: 3.6715 - val_accuracy: 0.8307\n", + "Epoch 437/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0883 - accuracy: 0.9723 - val_loss: 3.9912 - val_accuracy: 0.8217\n", + "Epoch 438/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 0.0775 - accuracy: 0.9741 - val_loss: 4.0961 - val_accuracy: 0.8146\n", + "Epoch 439/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0724 - accuracy: 0.9732 - val_loss: 3.9445 - val_accuracy: 0.8378\n", + "Epoch 440/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0623 - accuracy: 0.9812 - val_loss: 3.8161 - val_accuracy: 0.8271\n", + "Epoch 441/500\n", + "3/3 [==============================] - 0s 22ms/step - loss: 0.0942 - accuracy: 0.9679 - val_loss: 3.8594 - val_accuracy: 0.8467\n", + "Epoch 442/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0631 - accuracy: 0.9790 - val_loss: 4.1612 - val_accuracy: 0.8253\n", + "Epoch 443/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1112 - accuracy: 0.9638 - val_loss: 4.1340 - val_accuracy: 0.8182\n", + "Epoch 444/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0917 - accuracy: 0.9696 - val_loss: 4.3623 - val_accuracy: 0.7897\n", + "Epoch 445/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1528 - accuracy: 0.9540 - val_loss: 3.9424 - val_accuracy: 0.8182\n", + "Epoch 446/500\n", + "3/3 [==============================] - 0s 18ms/step - loss: 0.1331 - accuracy: 0.9576 - val_loss: 3.9227 - val_accuracy: 0.8253\n", + "Epoch 447/500\n", + "3/3 [==============================] - 0s 39ms/step - loss: 0.1209 - accuracy: 0.9612 - val_loss: 4.0155 - val_accuracy: 0.8146\n", + "Epoch 448/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1003 - accuracy: 0.9661 - val_loss: 3.7497 - val_accuracy: 0.8057\n", + "Epoch 449/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1047 - accuracy: 0.9652 - val_loss: 3.6100 - val_accuracy: 0.8217\n", + "Epoch 450/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.0999 - accuracy: 0.9679 - val_loss: 3.9842 - val_accuracy: 0.8111\n", + "Epoch 451/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1251 - accuracy: 0.9598 - val_loss: 4.0568 - val_accuracy: 0.8378\n", + "Epoch 452/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0788 - accuracy: 0.9750 - val_loss: 4.0065 - val_accuracy: 0.8271\n", + "Epoch 453/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0880 - accuracy: 0.9714 - val_loss: 3.8871 - val_accuracy: 0.8378\n", + "Epoch 454/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1070 - accuracy: 0.9665 - val_loss: 4.0148 - val_accuracy: 0.8342\n", + "Epoch 455/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1018 - accuracy: 0.9652 - val_loss: 4.0548 - val_accuracy: 0.8396\n", + "Epoch 456/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1049 - accuracy: 0.9625 - val_loss: 4.0096 - val_accuracy: 0.8021\n", + "Epoch 457/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1244 - accuracy: 0.9567 - val_loss: 4.1097 - val_accuracy: 0.8182\n", + "Epoch 458/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1455 - accuracy: 0.9504 - val_loss: 3.9897 - val_accuracy: 0.8128\n", + "Epoch 459/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1432 - accuracy: 0.9509 - val_loss: 3.7023 - val_accuracy: 0.8039\n", + "Epoch 460/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1303 - accuracy: 0.9554 - val_loss: 4.0265 - val_accuracy: 0.7807\n", + "Epoch 461/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1187 - accuracy: 0.9598 - val_loss: 4.2923 - val_accuracy: 0.8075\n", + "Epoch 462/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1034 - accuracy: 0.9665 - val_loss: 3.8971 - val_accuracy: 0.8217\n", + "Epoch 463/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1024 - accuracy: 0.9643 - val_loss: 3.8269 - val_accuracy: 0.8182\n", + "Epoch 464/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1248 - accuracy: 0.9621 - val_loss: 3.9530 - val_accuracy: 0.8378\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 465/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0939 - accuracy: 0.9705 - val_loss: 3.9372 - val_accuracy: 0.8289\n", + "Epoch 466/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1076 - accuracy: 0.9621 - val_loss: 4.1843 - val_accuracy: 0.8253\n", + "Epoch 467/500\n", + "3/3 [==============================] - 0s 20ms/step - loss: 0.1099 - accuracy: 0.9638 - val_loss: 4.2604 - val_accuracy: 0.8111\n", + "Epoch 468/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0842 - accuracy: 0.9723 - val_loss: 3.9724 - val_accuracy: 0.8289\n", + "Epoch 469/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.0996 - accuracy: 0.9674 - val_loss: 4.0019 - val_accuracy: 0.8111\n", + "Epoch 470/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0935 - accuracy: 0.9670 - val_loss: 4.1580 - val_accuracy: 0.8324\n", + "Epoch 471/500\n", + "3/3 [==============================] - 0s 14ms/step - loss: 0.0842 - accuracy: 0.9719 - val_loss: 4.1938 - val_accuracy: 0.8253\n", + "Epoch 472/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1047 - accuracy: 0.9647 - val_loss: 3.9072 - val_accuracy: 0.8396\n", + "Epoch 473/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0910 - accuracy: 0.9679 - val_loss: 3.8262 - val_accuracy: 0.8253\n", + "Epoch 474/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1006 - accuracy: 0.9661 - val_loss: 3.8356 - val_accuracy: 0.8307\n", + "Epoch 475/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1114 - accuracy: 0.9629 - val_loss: 3.7173 - val_accuracy: 0.8307\n", + "Epoch 476/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1075 - accuracy: 0.9629 - val_loss: 3.8374 - val_accuracy: 0.8253\n", + "Epoch 477/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1207 - accuracy: 0.9625 - val_loss: 3.9952 - val_accuracy: 0.7986\n", + "Epoch 478/500\n", + "3/3 [==============================] - 0s 20ms/step - loss: 0.1023 - accuracy: 0.9652 - val_loss: 4.0035 - val_accuracy: 0.8289\n", + "Epoch 479/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0924 - accuracy: 0.9656 - val_loss: 4.1198 - val_accuracy: 0.8182\n", + "Epoch 480/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1240 - accuracy: 0.9612 - val_loss: 3.9291 - val_accuracy: 0.8235\n", + "Epoch 481/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0888 - accuracy: 0.9688 - val_loss: 3.8687 - val_accuracy: 0.8396\n", + "Epoch 482/500\n", + "3/3 [==============================] - 0s 56ms/step - loss: 0.0990 - accuracy: 0.9647 - val_loss: 4.1139 - val_accuracy: 0.8431\n", + "Epoch 483/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1030 - accuracy: 0.9647 - val_loss: 4.2289 - val_accuracy: 0.8289\n", + "Epoch 484/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1054 - accuracy: 0.9661 - val_loss: 4.0827 - val_accuracy: 0.8111\n", + "Epoch 485/500\n", + "3/3 [==============================] - 0s 43ms/step - loss: 0.1109 - accuracy: 0.9625 - val_loss: 3.8768 - val_accuracy: 0.8360\n", + "Epoch 486/500\n", + "3/3 [==============================] - 0s 61ms/step - loss: 0.1020 - accuracy: 0.9625 - val_loss: 3.8905 - val_accuracy: 0.8324\n", + "Epoch 487/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.0892 - accuracy: 0.9714 - val_loss: 4.2800 - val_accuracy: 0.8200\n", + "Epoch 488/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0882 - accuracy: 0.9719 - val_loss: 4.1112 - val_accuracy: 0.8217\n", + "Epoch 489/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0815 - accuracy: 0.9692 - val_loss: 4.0338 - val_accuracy: 0.8039\n", + "Epoch 490/500\n", + "3/3 [==============================] - 0s 14ms/step - loss: 0.1132 - accuracy: 0.9589 - val_loss: 3.7588 - val_accuracy: 0.8307\n", + "Epoch 491/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1009 - accuracy: 0.9670 - val_loss: 4.0002 - val_accuracy: 0.8057\n", + "Epoch 492/500\n", + "3/3 [==============================] - 0s 16ms/step - loss: 0.1218 - accuracy: 0.9580 - val_loss: 3.8462 - val_accuracy: 0.8271\n", + "Epoch 493/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1019 - accuracy: 0.9647 - val_loss: 4.0607 - val_accuracy: 0.8182\n", + "Epoch 494/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1329 - accuracy: 0.9527 - val_loss: 4.3263 - val_accuracy: 0.8128\n", + "Epoch 495/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.0988 - accuracy: 0.9683 - val_loss: 4.1268 - val_accuracy: 0.8307\n", + "Epoch 496/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.0876 - accuracy: 0.9696 - val_loss: 3.8001 - val_accuracy: 0.8146\n", + "Epoch 497/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1131 - accuracy: 0.9629 - val_loss: 3.8902 - val_accuracy: 0.8146\n", + "Epoch 498/500\n", + "3/3 [==============================] - 0s 14ms/step - loss: 0.1416 - accuracy: 0.9531 - val_loss: 4.2596 - val_accuracy: 0.7986\n", + "Epoch 499/500\n", + "3/3 [==============================] - 0s 17ms/step - loss: 0.1524 - accuracy: 0.9504 - val_loss: 4.2255 - val_accuracy: 0.7950\n", + "Epoch 500/500\n", + "3/3 [==============================] - 0s 15ms/step - loss: 0.1492 - accuracy: 0.9487 - val_loss: 3.8500 - val_accuracy: 0.8307\n" + ] + }, + { + "data": { + "application/javascript": [ + "/* Put everything inside the global mpl namespace */\n", + "/* global mpl */\n", + "window.mpl = {};\n", + "\n", + "mpl.get_websocket_type = function () {\n", + " if (typeof WebSocket !== 'undefined') {\n", + " return WebSocket;\n", + " } else if (typeof MozWebSocket !== 'undefined') {\n", + " return MozWebSocket;\n", + " } else {\n", + " alert(\n", + " 'Your browser does not have WebSocket support. ' +\n", + " 'Please try Chrome, Safari or Firefox ≥ 6. ' +\n", + " 'Firefox 4 and 5 are also supported but you ' +\n", + " 'have to enable WebSockets in about:config.'\n", + " );\n", + " }\n", + "};\n", + "\n", + "mpl.figure = function (figure_id, websocket, ondownload, parent_element) {\n", + " this.id = figure_id;\n", + "\n", + " this.ws = websocket;\n", + "\n", + " this.supports_binary = this.ws.binaryType !== undefined;\n", + "\n", + " if (!this.supports_binary) {\n", + " var warnings = document.getElementById('mpl-warnings');\n", + " if (warnings) {\n", + " warnings.style.display = 'block';\n", + " warnings.textContent =\n", + " 'This browser does not support binary websocket messages. ' +\n", + " 'Performance may be slow.';\n", + " }\n", + " }\n", + "\n", + " this.imageObj = new Image();\n", + "\n", + " this.context = undefined;\n", + " this.message = undefined;\n", + " this.canvas = undefined;\n", + " this.rubberband_canvas = undefined;\n", + " this.rubberband_context = undefined;\n", + " this.format_dropdown = undefined;\n", + "\n", + " this.image_mode = 'full';\n", + "\n", + " this.root = document.createElement('div');\n", + " this.root.setAttribute('style', 'display: inline-block');\n", + " this._root_extra_style(this.root);\n", + "\n", + " parent_element.appendChild(this.root);\n", + "\n", + " this._init_header(this);\n", + " this._init_canvas(this);\n", + " this._init_toolbar(this);\n", + "\n", + " var fig = this;\n", + "\n", + " this.waiting = false;\n", + "\n", + " this.ws.onopen = function () {\n", + " fig.send_message('supports_binary', { value: fig.supports_binary });\n", + " fig.send_message('send_image_mode', {});\n", + " if (fig.ratio !== 1) {\n", + " fig.send_message('set_device_pixel_ratio', {\n", + " device_pixel_ratio: fig.ratio,\n", + " });\n", + " }\n", + " fig.send_message('refresh', {});\n", + " };\n", + "\n", + " this.imageObj.onload = function () {\n", + " if (fig.image_mode === 'full') {\n", + " // Full images could contain transparency (where diff images\n", + " // almost always do), so we need to clear the canvas so that\n", + " // there is no ghosting.\n", + " fig.context.clearRect(0, 0, fig.canvas.width, fig.canvas.height);\n", + " }\n", + " fig.context.drawImage(fig.imageObj, 0, 0);\n", + " };\n", + "\n", + " this.imageObj.onunload = function () {\n", + " fig.ws.close();\n", + " };\n", + "\n", + " this.ws.onmessage = this._make_on_message_function(this);\n", + "\n", + " this.ondownload = ondownload;\n", + "};\n", + "\n", + "mpl.figure.prototype._init_header = function () {\n", + " var titlebar = document.createElement('div');\n", + " titlebar.classList =\n", + " 'ui-dialog-titlebar ui-widget-header ui-corner-all ui-helper-clearfix';\n", + " var titletext = document.createElement('div');\n", + " titletext.classList = 'ui-dialog-title';\n", + " titletext.setAttribute(\n", + " 'style',\n", + " 'width: 100%; text-align: center; padding: 3px;'\n", + " );\n", + " titlebar.appendChild(titletext);\n", + " this.root.appendChild(titlebar);\n", + " this.header = titletext;\n", + "};\n", + "\n", + "mpl.figure.prototype._canvas_extra_style = function (_canvas_div) {};\n", + "\n", + "mpl.figure.prototype._root_extra_style = function (_canvas_div) {};\n", + "\n", + "mpl.figure.prototype._init_canvas = function () {\n", + " var fig = this;\n", + "\n", + " var canvas_div = (this.canvas_div = document.createElement('div'));\n", + " canvas_div.setAttribute(\n", + " 'style',\n", + " 'border: 1px solid #ddd;' +\n", + " 'box-sizing: content-box;' +\n", + " 'clear: both;' +\n", + " 'min-height: 1px;' +\n", + " 'min-width: 1px;' +\n", + " 'outline: 0;' +\n", + " 'overflow: hidden;' +\n", + " 'position: relative;' +\n", + " 'resize: both;'\n", + " );\n", + "\n", + " function on_keyboard_event_closure(name) {\n", + " return function (event) {\n", + " return fig.key_event(event, name);\n", + " };\n", + " }\n", + "\n", + " canvas_div.addEventListener(\n", + " 'keydown',\n", + " on_keyboard_event_closure('key_press')\n", + " );\n", + " canvas_div.addEventListener(\n", + " 'keyup',\n", + " on_keyboard_event_closure('key_release')\n", + " );\n", + "\n", + " this._canvas_extra_style(canvas_div);\n", + " this.root.appendChild(canvas_div);\n", + "\n", + " var canvas = (this.canvas = document.createElement('canvas'));\n", + " canvas.classList.add('mpl-canvas');\n", + " canvas.setAttribute('style', 'box-sizing: content-box;');\n", + "\n", + " this.context = canvas.getContext('2d');\n", + "\n", + " var backingStore =\n", + " this.context.backingStorePixelRatio ||\n", + " this.context.webkitBackingStorePixelRatio ||\n", + " this.context.mozBackingStorePixelRatio ||\n", + " this.context.msBackingStorePixelRatio ||\n", + " this.context.oBackingStorePixelRatio ||\n", + " this.context.backingStorePixelRatio ||\n", + " 1;\n", + "\n", + " this.ratio = (window.devicePixelRatio || 1) / backingStore;\n", + "\n", + " var rubberband_canvas = (this.rubberband_canvas = document.createElement(\n", + " 'canvas'\n", + " ));\n", + " rubberband_canvas.setAttribute(\n", + " 'style',\n", + " 'box-sizing: content-box; position: absolute; left: 0; top: 0; z-index: 1;'\n", + " );\n", + "\n", + " // Apply a ponyfill if ResizeObserver is not implemented by browser.\n", + " if (this.ResizeObserver === undefined) {\n", + " if (window.ResizeObserver !== undefined) {\n", + " this.ResizeObserver = window.ResizeObserver;\n", + " } else {\n", + " var obs = _JSXTOOLS_RESIZE_OBSERVER({});\n", + " this.ResizeObserver = obs.ResizeObserver;\n", + " }\n", + " }\n", + "\n", + " this.resizeObserverInstance = new this.ResizeObserver(function (entries) {\n", + " var nentries = entries.length;\n", + " for (var i = 0; i < nentries; i++) {\n", + " var entry = entries[i];\n", + " var width, height;\n", + " if (entry.contentBoxSize) {\n", + " if (entry.contentBoxSize instanceof Array) {\n", + " // Chrome 84 implements new version of spec.\n", + " width = entry.contentBoxSize[0].inlineSize;\n", + " height = entry.contentBoxSize[0].blockSize;\n", + " } else {\n", + " // Firefox implements old version of spec.\n", + " width = entry.contentBoxSize.inlineSize;\n", + " height = entry.contentBoxSize.blockSize;\n", + " }\n", + " } else {\n", + " // Chrome <84 implements even older version of spec.\n", + " width = entry.contentRect.width;\n", + " height = entry.contentRect.height;\n", + " }\n", + "\n", + " // Keep the size of the canvas and rubber band canvas in sync with\n", + " // the canvas container.\n", + " if (entry.devicePixelContentBoxSize) {\n", + " // Chrome 84 implements new version of spec.\n", + " canvas.setAttribute(\n", + " 'width',\n", + " entry.devicePixelContentBoxSize[0].inlineSize\n", + " );\n", + " canvas.setAttribute(\n", + " 'height',\n", + " entry.devicePixelContentBoxSize[0].blockSize\n", + " );\n", + " } else {\n", + " canvas.setAttribute('width', width * fig.ratio);\n", + " canvas.setAttribute('height', height * fig.ratio);\n", + " }\n", + " canvas.setAttribute(\n", + " 'style',\n", + " 'width: ' + width + 'px; height: ' + height + 'px;'\n", + " );\n", + "\n", + " rubberband_canvas.setAttribute('width', width);\n", + " rubberband_canvas.setAttribute('height', height);\n", + "\n", + " // And update the size in Python. We ignore the initial 0/0 size\n", + " // that occurs as the element is placed into the DOM, which should\n", + " // otherwise not happen due to the minimum size styling.\n", + " if (fig.ws.readyState == 1 && width != 0 && height != 0) {\n", + " fig.request_resize(width, height);\n", + " }\n", + " }\n", + " });\n", + " this.resizeObserverInstance.observe(canvas_div);\n", + "\n", + " function on_mouse_event_closure(name) {\n", + " return function (event) {\n", + " return fig.mouse_event(event, name);\n", + " };\n", + " }\n", + "\n", + " rubberband_canvas.addEventListener(\n", + " 'mousedown',\n", + " on_mouse_event_closure('button_press')\n", + " );\n", + " rubberband_canvas.addEventListener(\n", + " 'mouseup',\n", + " on_mouse_event_closure('button_release')\n", + " );\n", + " rubberband_canvas.addEventListener(\n", + " 'dblclick',\n", + " on_mouse_event_closure('dblclick')\n", + " );\n", + " // Throttle sequential mouse events to 1 every 20ms.\n", + " rubberband_canvas.addEventListener(\n", + " 'mousemove',\n", + " on_mouse_event_closure('motion_notify')\n", + " );\n", + "\n", + " rubberband_canvas.addEventListener(\n", + " 'mouseenter',\n", + " on_mouse_event_closure('figure_enter')\n", + " );\n", + " rubberband_canvas.addEventListener(\n", + " 'mouseleave',\n", + " on_mouse_event_closure('figure_leave')\n", + " );\n", + "\n", + " canvas_div.addEventListener('wheel', function (event) {\n", + " if (event.deltaY < 0) {\n", + " event.step = 1;\n", + " } else {\n", + " event.step = -1;\n", + " }\n", + " on_mouse_event_closure('scroll')(event);\n", + " });\n", + "\n", + " canvas_div.appendChild(canvas);\n", + " canvas_div.appendChild(rubberband_canvas);\n", + "\n", + " this.rubberband_context = rubberband_canvas.getContext('2d');\n", + " this.rubberband_context.strokeStyle = '#000000';\n", + "\n", + " this._resize_canvas = function (width, height, forward) {\n", + " if (forward) {\n", + " canvas_div.style.width = width + 'px';\n", + " canvas_div.style.height = height + 'px';\n", + " }\n", + " };\n", + "\n", + " // Disable right mouse context menu.\n", + " this.rubberband_canvas.addEventListener('contextmenu', function (_e) {\n", + " event.preventDefault();\n", + " return false;\n", + " });\n", + "\n", + " function set_focus() {\n", + " canvas.focus();\n", + " canvas_div.focus();\n", + " }\n", + "\n", + " window.setTimeout(set_focus, 100);\n", + "};\n", + "\n", + "mpl.figure.prototype._init_toolbar = function () {\n", + " var fig = this;\n", + "\n", + " var toolbar = document.createElement('div');\n", + " toolbar.classList = 'mpl-toolbar';\n", + " this.root.appendChild(toolbar);\n", + "\n", + " function on_click_closure(name) {\n", + " return function (_event) {\n", + " return fig.toolbar_button_onclick(name);\n", + " };\n", + " }\n", + "\n", + " function on_mouseover_closure(tooltip) {\n", + " return function (event) {\n", + " if (!event.currentTarget.disabled) {\n", + " return fig.toolbar_button_onmouseover(tooltip);\n", + " }\n", + " };\n", + " }\n", + "\n", + " fig.buttons = {};\n", + " var buttonGroup = document.createElement('div');\n", + " buttonGroup.classList = 'mpl-button-group';\n", + " for (var toolbar_ind in mpl.toolbar_items) {\n", + " var name = mpl.toolbar_items[toolbar_ind][0];\n", + " var tooltip = mpl.toolbar_items[toolbar_ind][1];\n", + " var image = mpl.toolbar_items[toolbar_ind][2];\n", + " var method_name = mpl.toolbar_items[toolbar_ind][3];\n", + "\n", + " if (!name) {\n", + " /* Instead of a spacer, we start a new button group. */\n", + " if (buttonGroup.hasChildNodes()) {\n", + " toolbar.appendChild(buttonGroup);\n", + " }\n", + " buttonGroup = document.createElement('div');\n", + " buttonGroup.classList = 'mpl-button-group';\n", + " continue;\n", + " }\n", + "\n", + " var button = (fig.buttons[name] = document.createElement('button'));\n", + " button.classList = 'mpl-widget';\n", + " button.setAttribute('role', 'button');\n", + " button.setAttribute('aria-disabled', 'false');\n", + " button.addEventListener('click', on_click_closure(method_name));\n", + " button.addEventListener('mouseover', on_mouseover_closure(tooltip));\n", + "\n", + " var icon_img = document.createElement('img');\n", + " icon_img.src = '_images/' + image + '.png';\n", + " icon_img.srcset = '_images/' + image + '_large.png 2x';\n", + " icon_img.alt = tooltip;\n", + " button.appendChild(icon_img);\n", + "\n", + " buttonGroup.appendChild(button);\n", + " }\n", + "\n", + " if (buttonGroup.hasChildNodes()) {\n", + " toolbar.appendChild(buttonGroup);\n", + " }\n", + "\n", + " var fmt_picker = document.createElement('select');\n", + " fmt_picker.classList = 'mpl-widget';\n", + " toolbar.appendChild(fmt_picker);\n", + " this.format_dropdown = fmt_picker;\n", + "\n", + " for (var ind in mpl.extensions) {\n", + " var fmt = mpl.extensions[ind];\n", + " var option = document.createElement('option');\n", + " option.selected = fmt === mpl.default_extension;\n", + " option.innerHTML = fmt;\n", + " fmt_picker.appendChild(option);\n", + " }\n", + "\n", + " var status_bar = document.createElement('span');\n", + " status_bar.classList = 'mpl-message';\n", + " toolbar.appendChild(status_bar);\n", + " this.message = status_bar;\n", + "};\n", + "\n", + "mpl.figure.prototype.request_resize = function (x_pixels, y_pixels) {\n", + " // Request matplotlib to resize the figure. Matplotlib will then trigger a resize in the client,\n", + " // which will in turn request a refresh of the image.\n", + " this.send_message('resize', { width: x_pixels, height: y_pixels });\n", + "};\n", + "\n", + "mpl.figure.prototype.send_message = function (type, properties) {\n", + " properties['type'] = type;\n", + " properties['figure_id'] = this.id;\n", + " this.ws.send(JSON.stringify(properties));\n", + "};\n", + "\n", + "mpl.figure.prototype.send_draw_message = function () {\n", + " if (!this.waiting) {\n", + " this.waiting = true;\n", + " this.ws.send(JSON.stringify({ type: 'draw', figure_id: this.id }));\n", + " }\n", + "};\n", + "\n", + "mpl.figure.prototype.handle_save = function (fig, _msg) {\n", + " var format_dropdown = fig.format_dropdown;\n", + " var format = format_dropdown.options[format_dropdown.selectedIndex].value;\n", + " fig.ondownload(fig, format);\n", + "};\n", + "\n", + "mpl.figure.prototype.handle_resize = function (fig, msg) {\n", + " var size = msg['size'];\n", + " if (size[0] !== fig.canvas.width || size[1] !== fig.canvas.height) {\n", + " fig._resize_canvas(size[0], size[1], msg['forward']);\n", + " fig.send_message('refresh', {});\n", + " }\n", + "};\n", + "\n", + "mpl.figure.prototype.handle_rubberband = function (fig, msg) {\n", + " var x0 = msg['x0'] / fig.ratio;\n", + " var y0 = (fig.canvas.height - msg['y0']) / fig.ratio;\n", + " var x1 = msg['x1'] / fig.ratio;\n", + " var y1 = (fig.canvas.height - msg['y1']) / fig.ratio;\n", + " x0 = Math.floor(x0) + 0.5;\n", + " y0 = Math.floor(y0) + 0.5;\n", + " x1 = Math.floor(x1) + 0.5;\n", + " y1 = Math.floor(y1) + 0.5;\n", + " var min_x = Math.min(x0, x1);\n", + " var min_y = Math.min(y0, y1);\n", + " var width = Math.abs(x1 - x0);\n", + " var height = Math.abs(y1 - y0);\n", + "\n", + " fig.rubberband_context.clearRect(\n", + " 0,\n", + " 0,\n", + " fig.canvas.width / fig.ratio,\n", + " fig.canvas.height / fig.ratio\n", + " );\n", + "\n", + " fig.rubberband_context.strokeRect(min_x, min_y, width, height);\n", + "};\n", + "\n", + "mpl.figure.prototype.handle_figure_label = function (fig, msg) {\n", + " // Updates the figure title.\n", + " fig.header.textContent = msg['label'];\n", + "};\n", + "\n", + "mpl.figure.prototype.handle_cursor = function (fig, msg) {\n", + " fig.rubberband_canvas.style.cursor = msg['cursor'];\n", + "};\n", + "\n", + "mpl.figure.prototype.handle_message = function (fig, msg) {\n", + " fig.message.textContent = msg['message'];\n", + "};\n", + "\n", + "mpl.figure.prototype.handle_draw = function (fig, _msg) {\n", + " // Request the server to send over a new figure.\n", + " fig.send_draw_message();\n", + "};\n", + "\n", + "mpl.figure.prototype.handle_image_mode = function (fig, msg) {\n", + " fig.image_mode = msg['mode'];\n", + "};\n", + "\n", + "mpl.figure.prototype.handle_history_buttons = function (fig, msg) {\n", + " for (var key in msg) {\n", + " if (!(key in fig.buttons)) {\n", + " continue;\n", + " }\n", + " fig.buttons[key].disabled = !msg[key];\n", + " fig.buttons[key].setAttribute('aria-disabled', !msg[key]);\n", + " }\n", + "};\n", + "\n", + "mpl.figure.prototype.handle_navigate_mode = function (fig, msg) {\n", + " if (msg['mode'] === 'PAN') {\n", + " fig.buttons['Pan'].classList.add('active');\n", + " fig.buttons['Zoom'].classList.remove('active');\n", + " } else if (msg['mode'] === 'ZOOM') {\n", + " fig.buttons['Pan'].classList.remove('active');\n", + " fig.buttons['Zoom'].classList.add('active');\n", + " } else {\n", + " fig.buttons['Pan'].classList.remove('active');\n", + " fig.buttons['Zoom'].classList.remove('active');\n", + " }\n", + "};\n", + "\n", + "mpl.figure.prototype.updated_canvas_event = function () {\n", + " // Called whenever the canvas gets updated.\n", + " this.send_message('ack', {});\n", + "};\n", + "\n", + "// A function to construct a web socket function for onmessage handling.\n", + "// Called in the figure constructor.\n", + "mpl.figure.prototype._make_on_message_function = function (fig) {\n", + " return function socket_on_message(evt) {\n", + " if (evt.data instanceof Blob) {\n", + " var img = evt.data;\n", + " if (img.type !== 'image/png') {\n", + " /* FIXME: We get \"Resource interpreted as Image but\n", + " * transferred with MIME type text/plain:\" errors on\n", + " * Chrome. But how to set the MIME type? It doesn't seem\n", + " * to be part of the websocket stream */\n", + " img.type = 'image/png';\n", + " }\n", + "\n", + " /* Free the memory for the previous frames */\n", + " if (fig.imageObj.src) {\n", + " (window.URL || window.webkitURL).revokeObjectURL(\n", + " fig.imageObj.src\n", + " );\n", + " }\n", + "\n", + " fig.imageObj.src = (window.URL || window.webkitURL).createObjectURL(\n", + " img\n", + " );\n", + " fig.updated_canvas_event();\n", + " fig.waiting = false;\n", + " return;\n", + " } else if (\n", + " typeof evt.data === 'string' &&\n", + " evt.data.slice(0, 21) === 'data:image/png;base64'\n", + " ) {\n", + " fig.imageObj.src = evt.data;\n", + " fig.updated_canvas_event();\n", + " fig.waiting = false;\n", + " return;\n", + " }\n", + "\n", + " var msg = JSON.parse(evt.data);\n", + " var msg_type = msg['type'];\n", + "\n", + " // Call the \"handle_{type}\" callback, which takes\n", + " // the figure and JSON message as its only arguments.\n", + " try {\n", + " var callback = fig['handle_' + msg_type];\n", + " } catch (e) {\n", + " console.log(\n", + " \"No handler for the '\" + msg_type + \"' message type: \",\n", + " msg\n", + " );\n", + " return;\n", + " }\n", + "\n", + " if (callback) {\n", + " try {\n", + " // console.log(\"Handling '\" + msg_type + \"' message: \", msg);\n", + " callback(fig, msg);\n", + " } catch (e) {\n", + " console.log(\n", + " \"Exception inside the 'handler_\" + msg_type + \"' callback:\",\n", + " e,\n", + " e.stack,\n", + " msg\n", + " );\n", + " }\n", + " }\n", + " };\n", + "};\n", + "\n", + "// from https://stackoverflow.com/questions/1114465/getting-mouse-location-in-canvas\n", + "mpl.findpos = function (e) {\n", + " //this section is from http://www.quirksmode.org/js/events_properties.html\n", + " var targ;\n", + " if (!e) {\n", + " e = window.event;\n", + " }\n", + " if (e.target) {\n", + " targ = e.target;\n", + " } else if (e.srcElement) {\n", + " targ = e.srcElement;\n", + " }\n", + " if (targ.nodeType === 3) {\n", + " // defeat Safari bug\n", + " targ = targ.parentNode;\n", + " }\n", + "\n", + " // pageX,Y are the mouse positions relative to the document\n", + " var boundingRect = targ.getBoundingClientRect();\n", + " var x = e.pageX - (boundingRect.left + document.body.scrollLeft);\n", + " var y = e.pageY - (boundingRect.top + document.body.scrollTop);\n", + "\n", + " return { x: x, y: y };\n", + "};\n", + "\n", + "/*\n", + " * return a copy of an object with only non-object keys\n", + " * we need this to avoid circular references\n", + " * https://stackoverflow.com/a/24161582/3208463\n", + " */\n", + "function simpleKeys(original) {\n", + " return Object.keys(original).reduce(function (obj, key) {\n", + " if (typeof original[key] !== 'object') {\n", + " obj[key] = original[key];\n", + " }\n", + " return obj;\n", + " }, {});\n", + "}\n", + "\n", + "mpl.figure.prototype.mouse_event = function (event, name) {\n", + " var canvas_pos = mpl.findpos(event);\n", + "\n", + " if (name === 'button_press') {\n", + " this.canvas.focus();\n", + " this.canvas_div.focus();\n", + " }\n", + "\n", + " var x = canvas_pos.x * this.ratio;\n", + " var y = canvas_pos.y * this.ratio;\n", + "\n", + " this.send_message(name, {\n", + " x: x,\n", + " y: y,\n", + " button: event.button,\n", + " step: event.step,\n", + " guiEvent: simpleKeys(event),\n", + " });\n", + "\n", + " /* This prevents the web browser from automatically changing to\n", + " * the text insertion cursor when the button is pressed. We want\n", + " * to control all of the cursor setting manually through the\n", + " * 'cursor' event from matplotlib */\n", + " event.preventDefault();\n", + " return false;\n", + "};\n", + "\n", + "mpl.figure.prototype._key_event_extra = function (_event, _name) {\n", + " // Handle any extra behaviour associated with a key event\n", + "};\n", + "\n", + "mpl.figure.prototype.key_event = function (event, name) {\n", + " // Prevent repeat events\n", + " if (name === 'key_press') {\n", + " if (event.key === this._key) {\n", + " return;\n", + " } else {\n", + " this._key = event.key;\n", + " }\n", + " }\n", + " if (name === 'key_release') {\n", + " this._key = null;\n", + " }\n", + "\n", + " var value = '';\n", + " if (event.ctrlKey && event.key !== 'Control') {\n", + " value += 'ctrl+';\n", + " }\n", + " else if (event.altKey && event.key !== 'Alt') {\n", + " value += 'alt+';\n", + " }\n", + " else if (event.shiftKey && event.key !== 'Shift') {\n", + " value += 'shift+';\n", + " }\n", + "\n", + " value += 'k' + event.key;\n", + "\n", + " this._key_event_extra(event, name);\n", + "\n", + " this.send_message(name, { key: value, guiEvent: simpleKeys(event) });\n", + " return false;\n", + "};\n", + "\n", + "mpl.figure.prototype.toolbar_button_onclick = function (name) {\n", + " if (name === 'download') {\n", + " this.handle_save(this, null);\n", + " } else {\n", + " this.send_message('toolbar_button', { name: name });\n", + " }\n", + "};\n", + "\n", + "mpl.figure.prototype.toolbar_button_onmouseover = function (tooltip) {\n", + " this.message.textContent = tooltip;\n", + "};\n", + "\n", + "///////////////// REMAINING CONTENT GENERATED BY embed_js.py /////////////////\n", + "// prettier-ignore\n", + "var _JSXTOOLS_RESIZE_OBSERVER=function(A){var t,i=new WeakMap,n=new WeakMap,a=new WeakMap,r=new WeakMap,o=new Set;function s(e){if(!(this instanceof s))throw new TypeError(\"Constructor requires 'new' operator\");i.set(this,e)}function h(){throw new TypeError(\"Function is not a constructor\")}function c(e,t,i,n){e=0 in arguments?Number(arguments[0]):0,t=1 in arguments?Number(arguments[1]):0,i=2 in arguments?Number(arguments[2]):0,n=3 in arguments?Number(arguments[3]):0,this.right=(this.x=this.left=e)+(this.width=i),this.bottom=(this.y=this.top=t)+(this.height=n),Object.freeze(this)}function d(){t=requestAnimationFrame(d);var s=new WeakMap,p=new Set;o.forEach((function(t){r.get(t).forEach((function(i){var r=t instanceof window.SVGElement,o=a.get(t),d=r?0:parseFloat(o.paddingTop),f=r?0:parseFloat(o.paddingRight),l=r?0:parseFloat(o.paddingBottom),u=r?0:parseFloat(o.paddingLeft),g=r?0:parseFloat(o.borderTopWidth),m=r?0:parseFloat(o.borderRightWidth),w=r?0:parseFloat(o.borderBottomWidth),b=u+f,F=d+l,v=(r?0:parseFloat(o.borderLeftWidth))+m,W=g+w,y=r?0:t.offsetHeight-W-t.clientHeight,E=r?0:t.offsetWidth-v-t.clientWidth,R=b+v,z=F+W,M=r?t.width:parseFloat(o.width)-R-E,O=r?t.height:parseFloat(o.height)-z-y;if(n.has(t)){var k=n.get(t);if(k[0]===M&&k[1]===O)return}n.set(t,[M,O]);var S=Object.create(h.prototype);S.target=t,S.contentRect=new c(u,d,M,O),s.has(i)||(s.set(i,[]),p.add(i)),s.get(i).push(S)}))})),p.forEach((function(e){i.get(e).call(e,s.get(e),e)}))}return s.prototype.observe=function(i){if(i instanceof window.Element){r.has(i)||(r.set(i,new Set),o.add(i),a.set(i,window.getComputedStyle(i)));var n=r.get(i);n.has(this)||n.add(this),cancelAnimationFrame(t),t=requestAnimationFrame(d)}},s.prototype.unobserve=function(i){if(i instanceof window.Element&&r.has(i)){var n=r.get(i);n.has(this)&&(n.delete(this),n.size||(r.delete(i),o.delete(i))),n.size||r.delete(i),o.size||cancelAnimationFrame(t)}},A.DOMRectReadOnly=c,A.ResizeObserver=s,A.ResizeObserverEntry=h,A}; // eslint-disable-line\n", + "mpl.toolbar_items = [[\"Home\", \"Reset original view\", \"fa fa-home icon-home\", \"home\"], [\"Back\", \"Back to previous view\", \"fa fa-arrow-left icon-arrow-left\", \"back\"], [\"Forward\", \"Forward to next view\", \"fa fa-arrow-right icon-arrow-right\", \"forward\"], [\"\", \"\", \"\", \"\"], [\"Pan\", \"Left button pans, Right button zooms\\nx/y fixes axis, CTRL fixes aspect\", \"fa fa-arrows icon-move\", \"pan\"], [\"Zoom\", \"Zoom to rectangle\\nx/y fixes axis\", \"fa fa-square-o icon-check-empty\", \"zoom\"], [\"\", \"\", \"\", \"\"], [\"Download\", \"Download plot\", \"fa fa-floppy-o icon-save\", \"download\"]];\n", + "\n", + "mpl.extensions = [\"eps\", \"jpeg\", \"pgf\", \"pdf\", \"png\", \"ps\", \"raw\", \"svg\", \"tif\"];\n", + "\n", + "mpl.default_extension = \"png\";/* global mpl */\n", + "\n", + "var comm_websocket_adapter = function (comm) {\n", + " // Create a \"websocket\"-like object which calls the given IPython comm\n", + " // object with the appropriate methods. Currently this is a non binary\n", + " // socket, so there is still some room for performance tuning.\n", + " var ws = {};\n", + "\n", + " ws.binaryType = comm.kernel.ws.binaryType;\n", + " ws.readyState = comm.kernel.ws.readyState;\n", + " function updateReadyState(_event) {\n", + " if (comm.kernel.ws) {\n", + " ws.readyState = comm.kernel.ws.readyState;\n", + " } else {\n", + " ws.readyState = 3; // Closed state.\n", + " }\n", + " }\n", + " comm.kernel.ws.addEventListener('open', updateReadyState);\n", + " comm.kernel.ws.addEventListener('close', updateReadyState);\n", + " comm.kernel.ws.addEventListener('error', updateReadyState);\n", + "\n", + " ws.close = function () {\n", + " comm.close();\n", + " };\n", + " ws.send = function (m) {\n", + " //console.log('sending', m);\n", + " comm.send(m);\n", + " };\n", + " // Register the callback with on_msg.\n", + " comm.on_msg(function (msg) {\n", + " //console.log('receiving', msg['content']['data'], msg);\n", + " var data = msg['content']['data'];\n", + " if (data['blob'] !== undefined) {\n", + " data = {\n", + " data: new Blob(msg['buffers'], { type: data['blob'] }),\n", + " };\n", + " }\n", + " // Pass the mpl event to the overridden (by mpl) onmessage function.\n", + " ws.onmessage(data);\n", + " });\n", + " return ws;\n", + "};\n", + "\n", + "mpl.mpl_figure_comm = function (comm, msg) {\n", + " // This is the function which gets called when the mpl process\n", + " // starts-up an IPython Comm through the \"matplotlib\" channel.\n", + "\n", + " var id = msg.content.data.id;\n", + " // Get hold of the div created by the display call when the Comm\n", + " // socket was opened in Python.\n", + " var element = document.getElementById(id);\n", + " var ws_proxy = comm_websocket_adapter(comm);\n", + "\n", + " function ondownload(figure, _format) {\n", + " window.open(figure.canvas.toDataURL());\n", + " }\n", + "\n", + " var fig = new mpl.figure(id, ws_proxy, ondownload, element);\n", + "\n", + " // Call onopen now - mpl needs it, as it is assuming we've passed it a real\n", + " // web socket which is closed, not our websocket->open comm proxy.\n", + " ws_proxy.onopen();\n", + "\n", + " fig.parent_element = element;\n", + " fig.cell_info = mpl.find_output_cell(\"<div id='\" + id + \"'></div>\");\n", + " if (!fig.cell_info) {\n", + " console.error('Failed to find cell for figure', id, fig);\n", + " return;\n", + " }\n", + " fig.cell_info[0].output_area.element.on(\n", + " 'cleared',\n", + " { fig: fig },\n", + " fig._remove_fig_handler\n", + " );\n", + "};\n", + "\n", + "mpl.figure.prototype.handle_close = function (fig, msg) {\n", + " var width = fig.canvas.width / fig.ratio;\n", + " fig.cell_info[0].output_area.element.off(\n", + " 'cleared',\n", + " fig._remove_fig_handler\n", + " );\n", + " fig.resizeObserverInstance.unobserve(fig.canvas_div);\n", + "\n", + " // Update the output cell to use the data from the current canvas.\n", + " fig.push_to_output();\n", + " var dataURL = fig.canvas.toDataURL();\n", + " // Re-enable the keyboard manager in IPython - without this line, in FF,\n", + " // the notebook keyboard shortcuts fail.\n", + " IPython.keyboard_manager.enable();\n", + " fig.parent_element.innerHTML =\n", + " '<img src=\"' + dataURL + '\" width=\"' + width + '\">';\n", + " fig.close_ws(fig, msg);\n", + "};\n", + "\n", + "mpl.figure.prototype.close_ws = function (fig, msg) {\n", + " fig.send_message('closing', msg);\n", + " // fig.ws.close()\n", + "};\n", + "\n", + "mpl.figure.prototype.push_to_output = function (_remove_interactive) {\n", + " // Turn the data on the canvas into data in the output cell.\n", + " var width = this.canvas.width / this.ratio;\n", + " var dataURL = this.canvas.toDataURL();\n", + " this.cell_info[1]['text/html'] =\n", + " '<img src=\"' + dataURL + '\" width=\"' + width + '\">';\n", + "};\n", + "\n", + "mpl.figure.prototype.updated_canvas_event = function () {\n", + " // Tell IPython that the notebook contents must change.\n", + " IPython.notebook.set_dirty(true);\n", + " this.send_message('ack', {});\n", + " var fig = this;\n", + " // Wait a second, then push the new image to the DOM so\n", + " // that it is saved nicely (might be nice to debounce this).\n", + " setTimeout(function () {\n", + " fig.push_to_output();\n", + " }, 1000);\n", + "};\n", + "\n", + "mpl.figure.prototype._init_toolbar = function () {\n", + " var fig = this;\n", + "\n", + " var toolbar = document.createElement('div');\n", + " toolbar.classList = 'btn-toolbar';\n", + " this.root.appendChild(toolbar);\n", + "\n", + " function on_click_closure(name) {\n", + " return function (_event) {\n", + " return fig.toolbar_button_onclick(name);\n", + " };\n", + " }\n", + "\n", + " function on_mouseover_closure(tooltip) {\n", + " return function (event) {\n", + " if (!event.currentTarget.disabled) {\n", + " return fig.toolbar_button_onmouseover(tooltip);\n", + " }\n", + " };\n", + " }\n", + "\n", + " fig.buttons = {};\n", + " var buttonGroup = document.createElement('div');\n", + " buttonGroup.classList = 'btn-group';\n", + " var button;\n", + " for (var toolbar_ind in mpl.toolbar_items) {\n", + " var name = mpl.toolbar_items[toolbar_ind][0];\n", + " var tooltip = mpl.toolbar_items[toolbar_ind][1];\n", + " var image = mpl.toolbar_items[toolbar_ind][2];\n", + " var method_name = mpl.toolbar_items[toolbar_ind][3];\n", + "\n", + " if (!name) {\n", + " /* Instead of a spacer, we start a new button group. */\n", + " if (buttonGroup.hasChildNodes()) {\n", + " toolbar.appendChild(buttonGroup);\n", + " }\n", + " buttonGroup = document.createElement('div');\n", + " buttonGroup.classList = 'btn-group';\n", + " continue;\n", + " }\n", + "\n", + " button = fig.buttons[name] = document.createElement('button');\n", + " button.classList = 'btn btn-default';\n", + " button.href = '#';\n", + " button.title = name;\n", + " button.innerHTML = '<i class=\"fa ' + image + ' fa-lg\"></i>';\n", + " button.addEventListener('click', on_click_closure(method_name));\n", + " button.addEventListener('mouseover', on_mouseover_closure(tooltip));\n", + " buttonGroup.appendChild(button);\n", + " }\n", + "\n", + " if (buttonGroup.hasChildNodes()) {\n", + " toolbar.appendChild(buttonGroup);\n", + " }\n", + "\n", + " // Add the status bar.\n", + " var status_bar = document.createElement('span');\n", + " status_bar.classList = 'mpl-message pull-right';\n", + " toolbar.appendChild(status_bar);\n", + " this.message = status_bar;\n", + "\n", + " // Add the close button to the window.\n", + " var buttongrp = document.createElement('div');\n", + " buttongrp.classList = 'btn-group inline pull-right';\n", + " button = document.createElement('button');\n", + " button.classList = 'btn btn-mini btn-primary';\n", + " button.href = '#';\n", + " button.title = 'Stop Interaction';\n", + " button.innerHTML = '<i class=\"fa fa-power-off icon-remove icon-large\"></i>';\n", + " button.addEventListener('click', function (_evt) {\n", + " fig.handle_close(fig, {});\n", + " });\n", + " button.addEventListener(\n", + " 'mouseover',\n", + " on_mouseover_closure('Stop Interaction')\n", + " );\n", + " buttongrp.appendChild(button);\n", + " var titlebar = this.root.querySelector('.ui-dialog-titlebar');\n", + " titlebar.insertBefore(buttongrp, titlebar.firstChild);\n", + "};\n", + "\n", + "mpl.figure.prototype._remove_fig_handler = function (event) {\n", + " var fig = event.data.fig;\n", + " if (event.target !== this) {\n", + " // Ignore bubbled events from children.\n", + " return;\n", + " }\n", + " fig.close_ws(fig, {});\n", + "};\n", + "\n", + "mpl.figure.prototype._root_extra_style = function (el) {\n", + " el.style.boxSizing = 'content-box'; // override notebook setting of border-box.\n", + "};\n", + "\n", + "mpl.figure.prototype._canvas_extra_style = function (el) {\n", + " // this is important to make the div 'focusable\n", + " el.setAttribute('tabindex', 0);\n", + " // reach out to IPython and tell the keyboard manager to turn it's self\n", + " // off when our div gets focus\n", + "\n", + " // location in version 3\n", + " if (IPython.notebook.keyboard_manager) {\n", + " IPython.notebook.keyboard_manager.register_events(el);\n", + " } else {\n", + " // location in version 2\n", + " IPython.keyboard_manager.register_events(el);\n", + " }\n", + "};\n", + "\n", + "mpl.figure.prototype._key_event_extra = function (event, _name) {\n", + " // Check for shift+enter\n", + " if (event.shiftKey && event.which === 13) {\n", + " this.canvas_div.blur();\n", + " // select the cell after this one\n", + " var index = IPython.notebook.find_cell_index(this.cell_info[0]);\n", + " IPython.notebook.select(index + 1);\n", + " }\n", + "};\n", + "\n", + "mpl.figure.prototype.handle_save = function (fig, _msg) {\n", + " fig.ondownload(fig, null);\n", + "};\n", + "\n", + "mpl.find_output_cell = function (html_output) {\n", + " // Return the cell and output element which can be found *uniquely* in the notebook.\n", + " // Note - this is a bit hacky, but it is done because the \"notebook_saving.Notebook\"\n", + " // IPython event is triggered only after the cells have been serialised, which for\n", + " // our purposes (turning an active figure into a static one), is too late.\n", + " var cells = IPython.notebook.get_cells();\n", + " var ncells = cells.length;\n", + " for (var i = 0; i < ncells; i++) {\n", + " var cell = cells[i];\n", + " if (cell.cell_type === 'code') {\n", + " for (var j = 0; j < cell.output_area.outputs.length; j++) {\n", + " var data = cell.output_area.outputs[j];\n", + " if (data.data) {\n", + " // IPython >= 3 moved mimebundle to data attribute of output\n", + " data = data.data;\n", + " }\n", + " if (data['text/html'] === html_output) {\n", + " return [cell, data, j];\n", + " }\n", + " }\n", + " }\n", + " }\n", + "};\n", + "\n", + "// Register the function which deals with the matplotlib target/channel.\n", + "// The kernel may be null if the page has been refreshed.\n", + "if (IPython.notebook.kernel !== null) {\n", + " IPython.notebook.kernel.comm_manager.register_target(\n", + " 'matplotlib',\n", + " mpl.mpl_figure_comm\n", + " );\n", + "}\n" + ], + "text/plain": [ + "<IPython.core.display.Javascript object>" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "<img src=\"data:image/png;base64,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\" width=\"640\">" + ], + "text/plain": [ + "<IPython.core.display.HTML object>" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "learning_rate = 0.01\n", + "epochs = 500\n", + "batch_size = 1000\n", + "validation_split = 0.2\n", + "\n", + "# Establish the model's topography.\n", + "my_model = create_model(learning_rate)\n", + "# Train the model on the normalized training set.\n", + "epochs, hist = train_model(my_model, train_df, np.array(mydata_lable), \n", + " epochs, batch_size, validation_split)\n", + "\n", + "# Plot a graph of the metric vs. epochs.\n", + "list_of_metrics_to_plot = ['accuracy', 'val_accuracy']\n", + "plot_curve(epochs, hist, list_of_metrics_to_plot)\n", + "\n", + "\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 67, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "<div>\n", + "<style scoped>\n", + " .dataframe tbody tr th:only-of-type {\n", + " vertical-align: middle;\n", + " }\n", + "\n", + " .dataframe tbody tr th {\n", + " vertical-align: top;\n", + " }\n", + "\n", + " .dataframe thead th {\n", + " text-align: right;\n", + " }\n", + "</style>\n", + "<table border=\"1\" class=\"dataframe\">\n", + " <thead>\n", + " <tr style=\"text-align: right;\">\n", + " <th></th>\n", + " <th>loss</th>\n", + " <th>accuracy</th>\n", + " <th>val_loss</th>\n", + " <th>val_accuracy</th>\n", + " </tr>\n", + " </thead>\n", + " <tbody>\n", + " <tr>\n", + " <th>0</th>\n", + " <td>11.004742</td>\n", + " <td>0.079911</td>\n", + " <td>11.425354</td>\n", + " <td>0.149733</td>\n", + " </tr>\n", + " <tr>\n", + " <th>1</th>\n", + " <td>6.618367</td>\n", + " <td>0.195982</td>\n", + " <td>5.508847</td>\n", + " <td>0.199643</td>\n", + " </tr>\n", + " <tr>\n", + " <th>2</th>\n", + " <td>3.557698</td>\n", + " <td>0.344643</td>\n", + " <td>3.907562</td>\n", + " <td>0.176471</td>\n", + " </tr>\n", + " <tr>\n", + " <th>3</th>\n", + " <td>2.740256</td>\n", + " <td>0.362946</td>\n", + " <td>3.747744</td>\n", + " <td>0.258467</td>\n", + " </tr>\n", + " <tr>\n", + " <th>4</th>\n", + " <td>2.119701</td>\n", + " <td>0.490625</td>\n", + " <td>3.717331</td>\n", + " <td>0.279857</td>\n", + " </tr>\n", + " <tr>\n", + " <th>5</th>\n", + " <td>1.627006</td>\n", + " <td>0.599554</td>\n", + " <td>3.453233</td>\n", + " <td>0.376114</td>\n", + " </tr>\n", + " <tr>\n", + " <th>6</th>\n", + " <td>1.215506</td>\n", + " <td>0.697768</td>\n", + " <td>3.377179</td>\n", + " <td>0.393939</td>\n", + " </tr>\n", + " <tr>\n", + " <th>7</th>\n", + " <td>0.882748</td>\n", + " <td>0.788393</td>\n", + " <td>3.353643</td>\n", + " <td>0.506239</td>\n", + " </tr>\n", + " <tr>\n", + " <th>8</th>\n", + " <td>0.671532</td>\n", + " <td>0.845982</td>\n", + " <td>3.494065</td>\n", + " <td>0.543672</td>\n", + " </tr>\n", + " <tr>\n", + " <th>9</th>\n", + " <td>0.502864</td>\n", + " <td>0.880357</td>\n", + " <td>3.594764</td>\n", + " <td>0.586453</td>\n", + " </tr>\n", + " <tr>\n", + " <th>10</th>\n", + " <td>0.423036</td>\n", + " <td>0.887500</td>\n", + " <td>3.665407</td>\n", + " <td>0.645276</td>\n", + " </tr>\n", + " <tr>\n", + " <th>11</th>\n", + " <td>0.332413</td>\n", + " <td>0.913839</td>\n", + " <td>3.578811</td>\n", + " <td>0.672014</td>\n", + " </tr>\n", + " <tr>\n", + " <th>12</th>\n", + " <td>0.282103</td>\n", + " <td>0.928571</td>\n", + " <td>3.630975</td>\n", + " <td>0.682709</td>\n", + " </tr>\n", + " <tr>\n", + " <th>13</th>\n", + " <td>0.244660</td>\n", + " <td>0.930804</td>\n", + " <td>3.658487</td>\n", + " <td>0.700535</td>\n", + " </tr>\n", + " <tr>\n", + " <th>14</th>\n", + " <td>0.210043</td>\n", + " <td>0.944196</td>\n", + " <td>3.646290</td>\n", + " <td>0.736185</td>\n", + " </tr>\n", + " <tr>\n", + " <th>15</th>\n", + " <td>0.183707</td>\n", + " <td>0.954018</td>\n", + " <td>3.646698</td>\n", + " <td>0.754011</td>\n", + " </tr>\n", + " <tr>\n", + " <th>16</th>\n", + " <td>0.157131</td>\n", + " <td>0.960268</td>\n", + " <td>3.742814</td>\n", + " <td>0.773619</td>\n", + " </tr>\n", + " <tr>\n", + " <th>17</th>\n", + " <td>0.146922</td>\n", + " <td>0.970089</td>\n", + " <td>3.793929</td>\n", + " <td>0.741533</td>\n", + " </tr>\n", + " <tr>\n", + " <th>18</th>\n", + " <td>0.124116</td>\n", + " <td>0.972321</td>\n", + " <td>3.775696</td>\n", + " <td>0.752228</td>\n", + " </tr>\n", + " <tr>\n", + " <th>19</th>\n", + " <td>0.120120</td>\n", + " <td>0.970982</td>\n", + " <td>3.833987</td>\n", + " <td>0.784314</td>\n", + " </tr>\n", + " <tr>\n", + " <th>20</th>\n", + " <td>0.104548</td>\n", + " <td>0.979018</td>\n", + " <td>3.796654</td>\n", + " <td>0.787879</td>\n", + " </tr>\n", + " <tr>\n", + " <th>21</th>\n", + " <td>0.092513</td>\n", + " <td>0.977679</td>\n", + " <td>3.842330</td>\n", + " <td>0.795009</td>\n", + " </tr>\n", + " <tr>\n", + " <th>22</th>\n", + " <td>0.092888</td>\n", + " <td>0.978571</td>\n", + " <td>3.855977</td>\n", + " <td>0.802139</td>\n", + " </tr>\n", + " <tr>\n", + " <th>23</th>\n", + " <td>0.085674</td>\n", + " <td>0.983482</td>\n", + " <td>3.843676</td>\n", + " <td>0.811052</td>\n", + " </tr>\n", + " <tr>\n", + " <th>24</th>\n", + " <td>0.073889</td>\n", + " <td>0.987946</td>\n", + " <td>3.855924</td>\n", + " <td>0.798574</td>\n", + " </tr>\n", + " <tr>\n", + " <th>25</th>\n", + " <td>0.070386</td>\n", + " <td>0.986607</td>\n", + " <td>3.903577</td>\n", + " <td>0.811052</td>\n", + " </tr>\n", + " <tr>\n", + " <th>26</th>\n", + " <td>0.070243</td>\n", + " <td>0.984375</td>\n", + " <td>4.010518</td>\n", + " <td>0.789661</td>\n", + " </tr>\n", + " <tr>\n", + " <th>27</th>\n", + " <td>0.063253</td>\n", + " <td>0.988393</td>\n", + " <td>3.933264</td>\n", + " <td>0.811052</td>\n", + " </tr>\n", + " <tr>\n", + " <th>28</th>\n", + " <td>0.051594</td>\n", + " <td>0.994196</td>\n", + " <td>3.966866</td>\n", + " <td>0.795009</td>\n", + " </tr>\n", + " <tr>\n", + " <th>29</th>\n", + " <td>0.055196</td>\n", + " <td>0.987500</td>\n", + " <td>4.035394</td>\n", + " <td>0.802139</td>\n", + " </tr>\n", + " <tr>\n", + " <th>30</th>\n", + " <td>0.050213</td>\n", + " <td>0.990179</td>\n", + " <td>4.022369</td>\n", + " <td>0.809269</td>\n", + " </tr>\n", + " <tr>\n", + " <th>31</th>\n", + " <td>0.047225</td>\n", + " <td>0.991518</td>\n", + " <td>4.027649</td>\n", + " <td>0.814617</td>\n", + " </tr>\n", + " <tr>\n", + " <th>32</th>\n", + " <td>0.041895</td>\n", + " <td>0.993750</td>\n", + " <td>4.088426</td>\n", + " <td>0.802139</td>\n", + " </tr>\n", + " <tr>\n", + " <th>33</th>\n", + " <td>0.043031</td>\n", + " <td>0.991071</td>\n", + " <td>4.114517</td>\n", + " <td>0.803922</td>\n", + " </tr>\n", + " <tr>\n", + " <th>34</th>\n", + " <td>0.038416</td>\n", + " <td>0.995536</td>\n", + " <td>4.096894</td>\n", + " <td>0.807487</td>\n", + " </tr>\n", + " <tr>\n", + " <th>35</th>\n", + " <td>0.040092</td>\n", + " <td>0.991071</td>\n", + " <td>4.111500</td>\n", + " <td>0.812834</td>\n", + " </tr>\n", + " <tr>\n", + " <th>36</th>\n", + " <td>0.032241</td>\n", + " <td>0.994643</td>\n", + " <td>4.167528</td>\n", + " <td>0.798574</td>\n", + " </tr>\n", + " <tr>\n", + " <th>37</th>\n", + " <td>0.035291</td>\n", + " <td>0.994643</td>\n", + " <td>4.172002</td>\n", + " <td>0.816399</td>\n", + " </tr>\n", + " <tr>\n", + " <th>38</th>\n", + " <td>0.029142</td>\n", + " <td>0.995089</td>\n", + " <td>4.188559</td>\n", + " <td>0.819964</td>\n", + " </tr>\n", + " <tr>\n", + " <th>39</th>\n", + " <td>0.026098</td>\n", + " <td>0.998214</td>\n", + " <td>4.240377</td>\n", + " <td>0.802139</td>\n", + " </tr>\n", + " <tr>\n", + " <th>40</th>\n", + " <td>0.025485</td>\n", + " <td>0.997768</td>\n", + " <td>4.210416</td>\n", + " <td>0.809269</td>\n", + " </tr>\n", + " <tr>\n", + " <th>41</th>\n", + " <td>0.029039</td>\n", + " <td>0.994643</td>\n", + " <td>4.245789</td>\n", + " <td>0.811052</td>\n", + " </tr>\n", + " <tr>\n", + " <th>42</th>\n", + " <td>0.038559</td>\n", + " <td>0.991518</td>\n", + " <td>4.417270</td>\n", + " <td>0.786096</td>\n", + " </tr>\n", + " <tr>\n", + " <th>43</th>\n", + " <td>0.043408</td>\n", + " <td>0.991071</td>\n", + " <td>4.400871</td>\n", + " <td>0.768271</td>\n", + " </tr>\n", + " <tr>\n", + " <th>44</th>\n", + " <td>0.042944</td>\n", + " <td>0.990625</td>\n", + " <td>4.206236</td>\n", + " <td>0.823529</td>\n", + " </tr>\n", + " <tr>\n", + " <th>45</th>\n", + " <td>0.028191</td>\n", + " <td>0.995089</td>\n", + " <td>4.211978</td>\n", + " <td>0.825312</td>\n", + " </tr>\n", + " <tr>\n", + " <th>46</th>\n", + " <td>0.021191</td>\n", + " <td>0.997768</td>\n", + " <td>4.303451</td>\n", + " <td>0.805704</td>\n", + " </tr>\n", + " <tr>\n", + " <th>47</th>\n", + " <td>0.020631</td>\n", + " <td>0.996875</td>\n", + " <td>4.236072</td>\n", + " <td>0.807487</td>\n", + " </tr>\n", + " <tr>\n", + " <th>48</th>\n", + " <td>0.022236</td>\n", + " <td>0.996875</td>\n", + " <td>4.252170</td>\n", + " <td>0.821747</td>\n", + " </tr>\n", + " <tr>\n", + " <th>49</th>\n", + " <td>0.022179</td>\n", + " <td>0.996875</td>\n", + " <td>4.329636</td>\n", + " <td>0.814617</td>\n", + " </tr>\n", + " </tbody>\n", + "</table>\n", + "</div>" + ], + "text/plain": [ + " loss accuracy val_loss val_accuracy\n", + "0 11.004742 0.079911 11.425354 0.149733\n", + "1 6.618367 0.195982 5.508847 0.199643\n", + "2 3.557698 0.344643 3.907562 0.176471\n", + "3 2.740256 0.362946 3.747744 0.258467\n", + "4 2.119701 0.490625 3.717331 0.279857\n", + "5 1.627006 0.599554 3.453233 0.376114\n", + "6 1.215506 0.697768 3.377179 0.393939\n", + "7 0.882748 0.788393 3.353643 0.506239\n", + "8 0.671532 0.845982 3.494065 0.543672\n", + "9 0.502864 0.880357 3.594764 0.586453\n", + "10 0.423036 0.887500 3.665407 0.645276\n", + "11 0.332413 0.913839 3.578811 0.672014\n", + "12 0.282103 0.928571 3.630975 0.682709\n", + "13 0.244660 0.930804 3.658487 0.700535\n", + "14 0.210043 0.944196 3.646290 0.736185\n", + "15 0.183707 0.954018 3.646698 0.754011\n", + "16 0.157131 0.960268 3.742814 0.773619\n", + "17 0.146922 0.970089 3.793929 0.741533\n", + "18 0.124116 0.972321 3.775696 0.752228\n", + "19 0.120120 0.970982 3.833987 0.784314\n", + "20 0.104548 0.979018 3.796654 0.787879\n", + "21 0.092513 0.977679 3.842330 0.795009\n", + "22 0.092888 0.978571 3.855977 0.802139\n", + "23 0.085674 0.983482 3.843676 0.811052\n", + "24 0.073889 0.987946 3.855924 0.798574\n", + "25 0.070386 0.986607 3.903577 0.811052\n", + "26 0.070243 0.984375 4.010518 0.789661\n", + "27 0.063253 0.988393 3.933264 0.811052\n", + "28 0.051594 0.994196 3.966866 0.795009\n", + "29 0.055196 0.987500 4.035394 0.802139\n", + "30 0.050213 0.990179 4.022369 0.809269\n", + "31 0.047225 0.991518 4.027649 0.814617\n", + "32 0.041895 0.993750 4.088426 0.802139\n", + "33 0.043031 0.991071 4.114517 0.803922\n", + "34 0.038416 0.995536 4.096894 0.807487\n", + "35 0.040092 0.991071 4.111500 0.812834\n", + "36 0.032241 0.994643 4.167528 0.798574\n", + "37 0.035291 0.994643 4.172002 0.816399\n", + "38 0.029142 0.995089 4.188559 0.819964\n", + "39 0.026098 0.998214 4.240377 0.802139\n", + "40 0.025485 0.997768 4.210416 0.809269\n", + "41 0.029039 0.994643 4.245789 0.811052\n", + "42 0.038559 0.991518 4.417270 0.786096\n", + "43 0.043408 0.991071 4.400871 0.768271\n", + "44 0.042944 0.990625 4.206236 0.823529\n", + "45 0.028191 0.995089 4.211978 0.825312\n", + "46 0.021191 0.997768 4.303451 0.805704\n", + "47 0.020631 0.996875 4.236072 0.807487\n", + "48 0.022236 0.996875 4.252170 0.821747\n", + "49 0.022179 0.996875 4.329636 0.814617" + ] + }, + "execution_count": 67, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "hist\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.8.10" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +}