인공지능 과제1.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "043e0f4b",
   "metadata": {},
   "source": [
    "# 입력 데이터의 크기와 정확도의 상관관계\n",
    "\n",
    "# 입력 데이터의 크기는 50개 - 2,5000개 (2495씩 증가)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "e37bdcdd",
   "metadata": {},
   "outputs": [],
   "source": [
    "def handling_input_data_size(input):\n",
    "    \n",
    "    # IMDB Data set Load\n",
    "\n",
    "    from keras.datasets import imdb\n",
    "    input_words=input\n",
    "    (train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words=input_words)\n",
    "    \n",
    "    \n",
    "    # Encoding the integer sequences into a binary matrix\n",
    "    \n",
    "    import numpy as np\n",
    "    \n",
    "    def vectorize_sequences(sequences,dimension=input_words):\n",
    "        results = np.zeros((len(sequences), dimension))\n",
    "        for i, sequence in enumerate(sequences):\n",
    "            results[i,sequence] = 1.\n",
    "        return results\n",
    "    \n",
    "    x_train = vectorize_sequences(train_data)\n",
    "    x_test = vectorize_sequences(test_data)\n",
    "    \n",
    "    y_train = np.asarray(train_labels).astype('float32')\n",
    "    y_test = np.asarray(test_labels).astype('float32')\n",
    "    \n",
    "    \n",
    "    # Model definition\n",
    "    \n",
    "    from keras import models\n",
    "    from keras import layers\n",
    "    \n",
    "    model = models.Sequential()\n",
    "    model.add(layers.Dense(16, activation='relu', input_shape=(input_words,)))\n",
    "    model.add(layers.Dense(16, activation='relu'))\n",
    "    model.add(layers.Dense(1, activation='sigmoid'))\n",
    "    \n",
    "    \n",
    "    # Compiling the model\n",
    "    \n",
    "    model.compile(optimizer='rmsprop',\n",
    "                 loss='binary_crossentropy',\n",
    "                 metrics=['accuracy'])\n",
    "    \n",
    "    \n",
    "    # Configuring the optimizer\n",
    "    #from keras import optimizers -> AttributeError: module 'keras.optimizers' has no attribute 'RMSprop'\n",
    "    \n",
    "    from tensorflow.keras import optimizers\n",
    "    \n",
    "    model.compile(optimizer=optimizers.RMSprop(lr=0.001),\n",
    "                 loss='binary_crossentropy',\n",
    "                 metrics=['accuracy'])\n",
    "    \n",
    "    \n",
    "    # Using custom losses and metrics\n",
    "    \n",
    "    from keras import losses\n",
    "    from keras import metrics\n",
    "    \n",
    "    model.compile(optimizer=optimizers.RMSprop(lr=0.001),\n",
    "                 loss=losses.binary_crossentropy,\n",
    "                 metrics=[metrics.binary_accuracy])\n",
    "    \n",
    "    \n",
    "    # Setting aside a validation set\n",
    "    \n",
    "    x_val = x_train[:input_words]\n",
    "    partial_x_train = x_train[input_words:]\n",
    "    y_val = y_train[:input_words]\n",
    "    partial_y_train = y_train[input_words:]\n",
    "    \n",
    "    \n",
    "    # Training your model\n",
    "    \n",
    "    model.compile(optimizer='rmsprop',\n",
    "                 loss='binary_crossentropy',\n",
    "                 metrics=['acc'])\n",
    "    history = model.fit(partial_x_train,\n",
    "                       partial_y_train,\n",
    "                       epochs=20,\n",
    "                       batch_size=512,\n",
    "                       validation_data=(x_val,y_val))\n",
    "    \n",
    "    \n",
    "    # Plotting the training and validation loss\n",
    "    \n",
    "    #import matplotlib.pyplot as plt\n",
    "    #\n",
    "    #history_dict = history.history\n",
    "    #loss_values = history_dict['loss'] \n",
    "    #val_loss_values = history_dict['val_loss']\n",
    "    #\n",
    "    #epochs = range(1, len(loss_values) + 1)\n",
    "    #\n",
    "    #plt.plot(epochs, loss_values, 'bo', label='Training loss') \n",
    "    #plt.plot(epochs, val_loss_values, 'b', label='Validation loss')\n",
    "    #plt.title('Training and validation loss') \n",
    "    #plt.xlabel('Epochs')\n",
    "    #plt.ylabel('Loss') \n",
    "    #plt.legend()\n",
    "    #\n",
    "    #plt.show()\n",
    "    #\n",
    "    #\n",
    "    ## Plotting the training and validation accuracy\n",
    "    #\n",
    "    #plt.clf() # 생성한 그래프 초기화\n",
    "    #acc = history_dict['acc'] \n",
    "    #val_acc = history_dict['val_acc']\n",
    "    #plt.plot(epochs, acc, 'bo', label='Training acc') \n",
    "    #plt.plot(epochs, val_acc, 'b', label='Validation acc') \n",
    "    #plt.title('Training and validation accuracy') \n",
    "    #plt.xlabel('Epochs')\n",
    "    #plt.ylabel('Acc') \n",
    "    #plt.legend()\n",
    "    #plt.show()\n",
    "    \n",
    "    \n",
    "    # Retraining a model from scratch\n",
    "    \n",
    "    model = models.Sequential()\n",
    "    model.add(layers.Dense(16, activation='relu', input_shape=(input_words,))) \n",
    "    model.add(layers.Dense(16, activation='relu')) \n",
    "    model.add(layers.Dense(1, activation='sigmoid'))\n",
    "    \n",
    "    model.compile(optimizer='rmsprop',\n",
    "                  loss='binary_crossentropy',\n",
    "                  metrics=['accuracy'])\n",
    "    \n",
    "    model.fit(x_train, y_train, epochs=4, batch_size=512) \n",
    "    results = model.evaluate(x_test, y_test)\n",
    "    return results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "348fbcdb",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/20\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\jw101\\anaconda3\\lib\\site-packages\\keras\\optimizer_v2\\rmsprop.py:130: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.\n",
      "  super(RMSprop, self).__init__(name, **kwargs)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "49/49 [==============================] - 1s 4ms/step - loss: 0.6890 - acc: 0.5387 - val_loss: 0.6758 - val_acc: 0.6122\n",
      "Epoch 2/20\n",
      "49/49 [==============================] - 0s 2ms/step - loss: 0.6815 - acc: 0.5688 - val_loss: 0.6632 - val_acc: 0.6327\n",
      "Epoch 3/20\n",
      "49/49 [==============================] - 0s 1ms/step - loss: 0.6734 - acc: 0.5837 - val_loss: 0.6542 - val_acc: 0.6735\n",
      "Epoch 4/20\n",
      "49/49 [==============================] - 0s 1ms/step - loss: 0.6680 - acc: 0.5919 - val_loss: 0.6490 - val_acc: 0.6531\n",
      "Epoch 5/20\n",
      "49/49 [==============================] - 0s 1ms/step - loss: 0.6645 - acc: 0.5994 - val_loss: 0.6552 - val_acc: 0.5918\n",
      "Epoch 6/20\n",
      "49/49 [==============================] - 0s 2ms/step - loss: 0.6622 - acc: 0.6039 - val_loss: 0.6439 - val_acc: 0.6531\n",
      "Epoch 7/20\n",
      "49/49 [==============================] - 0s 2ms/step - loss: 0.6608 - acc: 0.6087 - val_loss: 0.6371 - val_acc: 0.6327\n",
      "Epoch 8/20\n",
      "49/49 [==============================] - 0s 1ms/step - loss: 0.6598 - acc: 0.6084 - val_loss: 0.6420 - val_acc: 0.6735\n",
      "Epoch 9/20\n",
      "49/49 [==============================] - 0s 1ms/step - loss: 0.6587 - acc: 0.6100 - val_loss: 0.6384 - val_acc: 0.6735\n",
      "Epoch 10/20\n",
      "49/49 [==============================] - 0s 1ms/step - loss: 0.6581 - acc: 0.6119 - val_loss: 0.6359 - val_acc: 0.6939\n",
      "Epoch 11/20\n",
      "49/49 [==============================] - 0s 1ms/step - loss: 0.6572 - acc: 0.6129 - val_loss: 0.6387 - val_acc: 0.6735\n",
      "Epoch 12/20\n",
      "49/49 [==============================] - 0s 1ms/step - loss: 0.6567 - acc: 0.6116 - val_loss: 0.6342 - val_acc: 0.6939\n",
      "Epoch 13/20\n",
      "49/49 [==============================] - 0s 1ms/step - loss: 0.6561 - acc: 0.6135 - val_loss: 0.6308 - val_acc: 0.6735\n",
      "Epoch 14/20\n",
      "49/49 [==============================] - 0s 1ms/step - loss: 0.6556 - acc: 0.6135 - val_loss: 0.6295 - val_acc: 0.6327\n",
      "Epoch 15/20\n",
      "49/49 [==============================] - 0s 1ms/step - loss: 0.6549 - acc: 0.6161 - val_loss: 0.6343 - val_acc: 0.6735\n",
      "Epoch 16/20\n",
      "49/49 [==============================] - 0s 1ms/step - loss: 0.6543 - acc: 0.6143 - val_loss: 0.6292 - val_acc: 0.6939\n",
      "Epoch 17/20\n",
      "49/49 [==============================] - 0s 1ms/step - loss: 0.6538 - acc: 0.6145 - val_loss: 0.6284 - val_acc: 0.6735\n",
      "Epoch 18/20\n",
      "49/49 [==============================] - 0s 1ms/step - loss: 0.6531 - acc: 0.6165 - val_loss: 0.6287 - val_acc: 0.6122\n",
      "Epoch 19/20\n",
      "49/49 [==============================] - 0s 1ms/step - loss: 0.6526 - acc: 0.6177 - val_loss: 0.6291 - val_acc: 0.6939\n",
      "Epoch 20/20\n",
      "49/49 [==============================] - 0s 1ms/step - loss: 0.6519 - acc: 0.6208 - val_loss: 0.6220 - val_acc: 0.6531\n",
      "Epoch 1/4\n",
      "49/49 [==============================] - 0s 1ms/step - loss: 0.6967 - accuracy: 0.5302\n",
      "Epoch 2/4\n",
      "49/49 [==============================] - 0s 1ms/step - loss: 0.6782 - accuracy: 0.5718\n",
      "Epoch 3/4\n",
      "49/49 [==============================] - 0s 928us/step - loss: 0.6721 - accuracy: 0.5857\n",
      "Epoch 4/4\n",
      "49/49 [==============================] - 0s 937us/step - loss: 0.6674 - accuracy: 0.5961\n",
      "782/782 [==============================] - 1s 726us/step - loss: 0.6700 - accuracy: 0.5886\n",
      "Epoch 1/20\n",
      "44/44 [==============================] - 1s 6ms/step - loss: 0.4895 - acc: 0.7838 - val_loss: 0.3652 - val_acc: 0.8593\n",
      "Epoch 2/20\n",
      "44/44 [==============================] - 0s 4ms/step - loss: 0.3155 - acc: 0.8778 - val_loss: 0.3140 - val_acc: 0.8750\n",
      "Epoch 3/20\n",
      "44/44 [==============================] - 0s 4ms/step - loss: 0.2710 - acc: 0.8917 - val_loss: 0.3063 - val_acc: 0.8730\n",
      "Epoch 4/20\n",
      "44/44 [==============================] - 0s 4ms/step - loss: 0.2500 - acc: 0.9003 - val_loss: 0.3119 - val_acc: 0.8699\n",
      "Epoch 5/20\n",
      "44/44 [==============================] - 0s 4ms/step - loss: 0.2344 - acc: 0.9092 - val_loss: 0.3163 - val_acc: 0.8719\n",
      "Epoch 6/20\n",
      "44/44 [==============================] - 0s 4ms/step - loss: 0.2291 - acc: 0.9088 - val_loss: 0.3123 - val_acc: 0.8781\n",
      "Epoch 7/20\n",
      "44/44 [==============================] - 0s 4ms/step - loss: 0.2189 - acc: 0.9134 - val_loss: 0.3180 - val_acc: 0.8774\n",
      "Epoch 8/20\n",
      "44/44 [==============================] - 0s 4ms/step - loss: 0.2134 - acc: 0.9157 - val_loss: 0.3216 - val_acc: 0.8813\n",
      "Epoch 9/20\n",
      "44/44 [==============================] - 0s 4ms/step - loss: 0.2106 - acc: 0.9169 - val_loss: 0.3381 - val_acc: 0.8726\n",
      "Epoch 10/20\n",
      "44/44 [==============================] - 0s 4ms/step - loss: 0.2044 - acc: 0.9192 - val_loss: 0.3314 - val_acc: 0.8789\n",
      "Epoch 11/20\n",
      "44/44 [==============================] - 0s 4ms/step - loss: 0.1993 - acc: 0.9202 - val_loss: 0.3372 - val_acc: 0.8781\n",
      "Epoch 12/20\n",
      "44/44 [==============================] - 0s 4ms/step - loss: 0.1919 - acc: 0.9236 - val_loss: 0.3802 - val_acc: 0.8628\n",
      "Epoch 13/20\n",
      "44/44 [==============================] - 0s 4ms/step - loss: 0.1876 - acc: 0.9268 - val_loss: 0.3467 - val_acc: 0.8722\n",
      "Epoch 14/20\n",
      "44/44 [==============================] - 0s 4ms/step - loss: 0.1811 - acc: 0.9282 - val_loss: 0.3489 - val_acc: 0.8738\n",
      "Epoch 15/20\n",
      "44/44 [==============================] - 0s 4ms/step - loss: 0.1722 - acc: 0.9338 - val_loss: 0.3552 - val_acc: 0.8734\n",
      "Epoch 16/20\n",
      "44/44 [==============================] - 0s 4ms/step - loss: 0.1657 - acc: 0.9370 - val_loss: 0.3797 - val_acc: 0.8719\n",
      "Epoch 17/20\n",
      "44/44 [==============================] - 0s 4ms/step - loss: 0.1589 - acc: 0.9397 - val_loss: 0.3736 - val_acc: 0.8719\n",
      "Epoch 18/20\n",
      "44/44 [==============================] - 0s 4ms/step - loss: 0.1507 - acc: 0.9428 - val_loss: 0.3712 - val_acc: 0.8683\n",
      "Epoch 19/20\n",
      "44/44 [==============================] - 0s 4ms/step - loss: 0.1447 - acc: 0.9461 - val_loss: 0.4066 - val_acc: 0.8656\n",
      "Epoch 20/20\n",
      "44/44 [==============================] - 0s 4ms/step - loss: 0.1351 - acc: 0.9495 - val_loss: 0.3851 - val_acc: 0.8687\n",
      "Epoch 1/4\n",
      "49/49 [==============================] - 1s 3ms/step - loss: 0.5215 - accuracy: 0.7751\n",
      "Epoch 2/4\n",
      "49/49 [==============================] - 0s 3ms/step - loss: 0.3233 - accuracy: 0.8778\n",
      "Epoch 3/4\n",
      "49/49 [==============================] - 0s 3ms/step - loss: 0.2720 - accuracy: 0.8922\n",
      "Epoch 4/4\n",
      "49/49 [==============================] - 0s 3ms/step - loss: 0.2523 - accuracy: 0.9010\n",
      "782/782 [==============================] - 1s 780us/step - loss: 0.2944 - accuracy: 0.8781\n",
      "Epoch 1/20\n",
      "39/39 [==============================] - 1s 11ms/step - loss: 0.4794 - acc: 0.7951 - val_loss: 0.3555 - val_acc: 0.8700\n",
      "Epoch 2/20\n",
      "39/39 [==============================] - 0s 6ms/step - loss: 0.2940 - acc: 0.8959 - val_loss: 0.2941 - val_acc: 0.8821\n",
      "Epoch 3/20\n",
      "39/39 [==============================] - 0s 6ms/step - loss: 0.2372 - acc: 0.9127 - val_loss: 0.3016 - val_acc: 0.8801\n",
      "Epoch 4/20\n",
      "39/39 [==============================] - 0s 6ms/step - loss: 0.2086 - acc: 0.9217 - val_loss: 0.2789 - val_acc: 0.8883\n",
      "Epoch 5/20\n",
      "39/39 [==============================] - 0s 6ms/step - loss: 0.1899 - acc: 0.9297 - val_loss: 0.2882 - val_acc: 0.8877\n",
      "Epoch 6/20\n",
      "39/39 [==============================] - 0s 7ms/step - loss: 0.1748 - acc: 0.9358 - val_loss: 0.3127 - val_acc: 0.8829\n",
      "Epoch 7/20\n",
      "39/39 [==============================] - 0s 8ms/step - loss: 0.1629 - acc: 0.9392 - val_loss: 0.3102 - val_acc: 0.8859\n",
      "Epoch 8/20\n",
      "39/39 [==============================] - 0s 8ms/step - loss: 0.1559 - acc: 0.9414 - val_loss: 0.3214 - val_acc: 0.8833\n",
      "Epoch 9/20\n",
      "39/39 [==============================] - 0s 7ms/step - loss: 0.1479 - acc: 0.9446 - val_loss: 0.3299 - val_acc: 0.8793\n",
      "Epoch 10/20\n",
      "39/39 [==============================] - 0s 7ms/step - loss: 0.1353 - acc: 0.9502 - val_loss: 0.3862 - val_acc: 0.8700\n",
      "Epoch 11/20\n",
      "39/39 [==============================] - 0s 8ms/step - loss: 0.1352 - acc: 0.9486 - val_loss: 0.3561 - val_acc: 0.8754\n",
      "Epoch 12/20\n",
      "39/39 [==============================] - 0s 8ms/step - loss: 0.1244 - acc: 0.9538 - val_loss: 0.3706 - val_acc: 0.8742\n",
      "Epoch 13/20\n",
      "39/39 [==============================] - 0s 7ms/step - loss: 0.1183 - acc: 0.9567 - val_loss: 0.4148 - val_acc: 0.8643\n",
      "Epoch 14/20\n",
      "39/39 [==============================] - 0s 8ms/step - loss: 0.1132 - acc: 0.9583 - val_loss: 0.4223 - val_acc: 0.8698\n",
      "Epoch 15/20\n",
      "39/39 [==============================] - 0s 8ms/step - loss: 0.1089 - acc: 0.9601 - val_loss: 0.4181 - val_acc: 0.8710\n",
      "Epoch 16/20\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "39/39 [==============================] - 0s 8ms/step - loss: 0.1024 - acc: 0.9635 - val_loss: 0.4298 - val_acc: 0.8712\n",
      "Epoch 17/20\n",
      "39/39 [==============================] - 0s 8ms/step - loss: 0.0974 - acc: 0.9654 - val_loss: 0.4491 - val_acc: 0.8651\n",
      "Epoch 18/20\n",
      "39/39 [==============================] - 0s 7ms/step - loss: 0.0897 - acc: 0.9688 - val_loss: 0.4842 - val_acc: 0.8643\n",
      "Epoch 19/20\n",
      "39/39 [==============================] - 0s 7ms/step - loss: 0.0831 - acc: 0.9705 - val_loss: 0.4722 - val_acc: 0.8688\n",
      "Epoch 20/20\n",
      "39/39 [==============================] - 0s 6ms/step - loss: 0.0804 - acc: 0.9720 - val_loss: 0.4905 - val_acc: 0.8653\n",
      "Epoch 1/4\n",
      "49/49 [==============================] - 1s 5ms/step - loss: 0.4479 - accuracy: 0.8158\n",
      "Epoch 2/4\n",
      "49/49 [==============================] - 0s 5ms/step - loss: 0.2805 - accuracy: 0.8982\n",
      "Epoch 3/4\n",
      "49/49 [==============================] - 0s 5ms/step - loss: 0.2330 - accuracy: 0.9121\n",
      "Epoch 4/4\n",
      "49/49 [==============================] - 0s 5ms/step - loss: 0.2078 - accuracy: 0.9214\n",
      "782/782 [==============================] - 1s 809us/step - loss: 0.3108 - accuracy: 0.8759\n",
      "Epoch 1/20\n",
      "35/35 [==============================] - 1s 14ms/step - loss: 0.4918 - acc: 0.7935 - val_loss: 0.3643 - val_acc: 0.8714\n",
      "Epoch 2/20\n",
      "35/35 [==============================] - 0s 8ms/step - loss: 0.2916 - acc: 0.8993 - val_loss: 0.2907 - val_acc: 0.8889\n",
      "Epoch 3/20\n",
      "35/35 [==============================] - 0s 8ms/step - loss: 0.2224 - acc: 0.9221 - val_loss: 0.3128 - val_acc: 0.8754\n",
      "Epoch 4/20\n",
      "35/35 [==============================] - 0s 8ms/step - loss: 0.1868 - acc: 0.9345 - val_loss: 0.3204 - val_acc: 0.8730\n",
      "Epoch 5/20\n",
      "35/35 [==============================] - 0s 8ms/step - loss: 0.1603 - acc: 0.9456 - val_loss: 0.2809 - val_acc: 0.8888\n",
      "Epoch 6/20\n",
      "35/35 [==============================] - 0s 8ms/step - loss: 0.1378 - acc: 0.9528 - val_loss: 0.2937 - val_acc: 0.8892\n",
      "Epoch 7/20\n",
      "35/35 [==============================] - 0s 8ms/step - loss: 0.1195 - acc: 0.9600 - val_loss: 0.3621 - val_acc: 0.8686\n",
      "Epoch 8/20\n",
      "35/35 [==============================] - 0s 8ms/step - loss: 0.1016 - acc: 0.9672 - val_loss: 0.3335 - val_acc: 0.8825\n",
      "Epoch 9/20\n",
      "35/35 [==============================] - 0s 8ms/step - loss: 0.0890 - acc: 0.9714 - val_loss: 0.3523 - val_acc: 0.8807\n",
      "Epoch 10/20\n",
      "35/35 [==============================] - 0s 8ms/step - loss: 0.0789 - acc: 0.9751 - val_loss: 0.3768 - val_acc: 0.8783\n",
      "Epoch 11/20\n",
      "35/35 [==============================] - 0s 8ms/step - loss: 0.0663 - acc: 0.9791 - val_loss: 0.3925 - val_acc: 0.8762\n",
      "Epoch 12/20\n",
      "35/35 [==============================] - 0s 8ms/step - loss: 0.0605 - acc: 0.9816 - val_loss: 0.4232 - val_acc: 0.8719\n",
      "Epoch 13/20\n",
      "35/35 [==============================] - 0s 8ms/step - loss: 0.0476 - acc: 0.9876 - val_loss: 0.4430 - val_acc: 0.8714\n",
      "Epoch 14/20\n",
      "35/35 [==============================] - 0s 8ms/step - loss: 0.0451 - acc: 0.9871 - val_loss: 0.4735 - val_acc: 0.8690\n",
      "Epoch 15/20\n",
      "35/35 [==============================] - 0s 8ms/step - loss: 0.0339 - acc: 0.9923 - val_loss: 0.4945 - val_acc: 0.8720\n",
      "Epoch 16/20\n",
      "35/35 [==============================] - 0s 8ms/step - loss: 0.0308 - acc: 0.9932 - val_loss: 0.5186 - val_acc: 0.8701\n",
      "Epoch 17/20\n",
      "35/35 [==============================] - 0s 9ms/step - loss: 0.0250 - acc: 0.9942 - val_loss: 0.5605 - val_acc: 0.8669\n",
      "Epoch 18/20\n",
      "35/35 [==============================] - 0s 10ms/step - loss: 0.0202 - acc: 0.9962 - val_loss: 0.5789 - val_acc: 0.8651\n",
      "Epoch 19/20\n",
      "35/35 [==============================] - 0s 9ms/step - loss: 0.0171 - acc: 0.9965 - val_loss: 0.6073 - val_acc: 0.8633\n",
      "Epoch 20/20\n",
      "35/35 [==============================] - 0s 8ms/step - loss: 0.0170 - acc: 0.9963 - val_loss: 0.6322 - val_acc: 0.8638\n",
      "Epoch 1/4\n",
      "49/49 [==============================] - 1s 6ms/step - loss: 0.4842 - accuracy: 0.7919\n",
      "Epoch 2/4\n",
      "49/49 [==============================] - 0s 6ms/step - loss: 0.2853 - accuracy: 0.9020\n",
      "Epoch 3/4\n",
      "49/49 [==============================] - 0s 6ms/step - loss: 0.2235 - accuracy: 0.9205\n",
      "Epoch 4/4\n",
      "49/49 [==============================] - 0s 6ms/step - loss: 0.1888 - accuracy: 0.9323\n",
      "782/782 [==============================] - 1s 870us/step - loss: 0.2880 - accuracy: 0.8838\n",
      "Epoch 1/20\n",
      "30/30 [==============================] - 1s 26ms/step - loss: 0.4929 - acc: 0.7883 - val_loss: 0.3744 - val_acc: 0.8637\n",
      "Epoch 2/20\n",
      "30/30 [==============================] - 0s 13ms/step - loss: 0.2863 - acc: 0.9043 - val_loss: 0.3065 - val_acc: 0.8774\n",
      "Epoch 3/20\n",
      "30/30 [==============================] - 0s 12ms/step - loss: 0.2130 - acc: 0.9255 - val_loss: 0.2747 - val_acc: 0.8907\n",
      "Epoch 4/20\n",
      "30/30 [==============================] - 0s 12ms/step - loss: 0.1618 - acc: 0.9466 - val_loss: 0.2773 - val_acc: 0.8879\n",
      "Epoch 5/20\n",
      "30/30 [==============================] - 0s 14ms/step - loss: 0.1377 - acc: 0.9546 - val_loss: 0.2875 - val_acc: 0.8879\n",
      "Epoch 6/20\n",
      "30/30 [==============================] - 0s 12ms/step - loss: 0.1148 - acc: 0.9641 - val_loss: 0.3057 - val_acc: 0.8820\n",
      "Epoch 7/20\n",
      "30/30 [==============================] - 0s 12ms/step - loss: 0.0943 - acc: 0.9723 - val_loss: 0.3237 - val_acc: 0.8795\n",
      "Epoch 8/20\n",
      "30/30 [==============================] - 0s 12ms/step - loss: 0.0808 - acc: 0.9757 - val_loss: 0.3385 - val_acc: 0.8791\n",
      "Epoch 9/20\n",
      "30/30 [==============================] - 0s 12ms/step - loss: 0.0644 - acc: 0.9833 - val_loss: 0.3839 - val_acc: 0.8723\n",
      "Epoch 10/20\n",
      "30/30 [==============================] - 0s 13ms/step - loss: 0.0571 - acc: 0.9854 - val_loss: 0.3869 - val_acc: 0.8746\n",
      "Epoch 11/20\n",
      "30/30 [==============================] - 0s 12ms/step - loss: 0.0463 - acc: 0.9874 - val_loss: 0.4237 - val_acc: 0.8693\n",
      "Epoch 12/20\n",
      "30/30 [==============================] - 0s 11ms/step - loss: 0.0382 - acc: 0.9908 - val_loss: 0.4439 - val_acc: 0.8750\n",
      "Epoch 13/20\n",
      "30/30 [==============================] - 0s 11ms/step - loss: 0.0302 - acc: 0.9945 - val_loss: 0.4747 - val_acc: 0.8741\n",
      "Epoch 14/20\n",
      "30/30 [==============================] - 0s 11ms/step - loss: 0.0245 - acc: 0.9955 - val_loss: 0.5226 - val_acc: 0.8637\n",
      "Epoch 15/20\n",
      "30/30 [==============================] - 0s 13ms/step - loss: 0.0212 - acc: 0.9963 - val_loss: 0.5404 - val_acc: 0.8711\n",
      "Epoch 16/20\n",
      "30/30 [==============================] - 0s 12ms/step - loss: 0.0166 - acc: 0.9972 - val_loss: 0.5791 - val_acc: 0.8674\n",
      "Epoch 17/20\n",
      "30/30 [==============================] - 0s 12ms/step - loss: 0.0095 - acc: 0.9995 - val_loss: 0.6160 - val_acc: 0.8642\n",
      "Epoch 18/20\n",
      "30/30 [==============================] - 0s 12ms/step - loss: 0.0103 - acc: 0.9992 - val_loss: 0.6499 - val_acc: 0.8669\n",
      "Epoch 19/20\n",
      "30/30 [==============================] - 0s 13ms/step - loss: 0.0116 - acc: 0.9979 - val_loss: 0.6802 - val_acc: 0.8646\n",
      "Epoch 20/20\n",
      "30/30 [==============================] - 0s 11ms/step - loss: 0.0047 - acc: 0.9997 - val_loss: 0.7422 - val_acc: 0.8649\n",
      "Epoch 1/4\n",
      "49/49 [==============================] - 1s 12ms/step - loss: 0.4725 - accuracy: 0.8220\n",
      "Epoch 2/4\n",
      "49/49 [==============================] - 0s 8ms/step - loss: 0.2732 - accuracy: 0.9073\n",
      "Epoch 3/4\n",
      "49/49 [==============================] - 0s 9ms/step - loss: 0.2082 - accuracy: 0.9246\n",
      "Epoch 4/4\n",
      "49/49 [==============================] - 0s 8ms/step - loss: 0.1711 - accuracy: 0.9405\n",
      "782/782 [==============================] - 1s 1ms/step - loss: 0.2859 - accuracy: 0.8870\n",
      "Epoch 1/20\n",
      "25/25 [==============================] - 1s 33ms/step - loss: 0.5416 - acc: 0.7714 - val_loss: 0.4336 - val_acc: 0.8490\n",
      "Epoch 2/20\n",
      "25/25 [==============================] - 0s 16ms/step - loss: 0.3358 - acc: 0.9015 - val_loss: 0.3340 - val_acc: 0.8824\n",
      "Epoch 3/20\n",
      "25/25 [==============================] - 0s 17ms/step - loss: 0.2430 - acc: 0.9279 - val_loss: 0.3125 - val_acc: 0.8770\n",
      "Epoch 4/20\n",
      "25/25 [==============================] - 0s 17ms/step - loss: 0.1832 - acc: 0.9469 - val_loss: 0.2900 - val_acc: 0.8863\n",
      "Epoch 5/20\n",
      "25/25 [==============================] - 0s 17ms/step - loss: 0.1480 - acc: 0.9564 - val_loss: 0.3014 - val_acc: 0.8810\n",
      "Epoch 6/20\n",
      "25/25 [==============================] - 0s 18ms/step - loss: 0.1149 - acc: 0.9695 - val_loss: 0.2925 - val_acc: 0.8857\n",
      "Epoch 7/20\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "25/25 [==============================] - 0s 19ms/step - loss: 0.0936 - acc: 0.9751 - val_loss: 0.3042 - val_acc: 0.8837\n",
      "Epoch 8/20\n",
      "25/25 [==============================] - 0s 18ms/step - loss: 0.0730 - acc: 0.9828 - val_loss: 0.3221 - val_acc: 0.8800\n",
      "Epoch 9/20\n",
      "25/25 [==============================] - 0s 18ms/step - loss: 0.0588 - acc: 0.9880 - val_loss: 0.3437 - val_acc: 0.8794\n",
      "Epoch 10/20\n",
      "25/25 [==============================] - 1s 24ms/step - loss: 0.0459 - acc: 0.9909 - val_loss: 0.3758 - val_acc: 0.8769\n",
      "Epoch 11/20\n",
      "25/25 [==============================] - 1s 21ms/step - loss: 0.0355 - acc: 0.9941 - val_loss: 0.3913 - val_acc: 0.8766\n",
      "Epoch 12/20\n",
      "25/25 [==============================] - 0s 17ms/step - loss: 0.0286 - acc: 0.9954 - val_loss: 0.4213 - val_acc: 0.8747\n",
      "Epoch 13/20\n",
      "25/25 [==============================] - 0s 17ms/step - loss: 0.0212 - acc: 0.9968 - val_loss: 0.4573 - val_acc: 0.8724\n",
      "Epoch 14/20\n",
      "25/25 [==============================] - 0s 17ms/step - loss: 0.0152 - acc: 0.9983 - val_loss: 0.4820 - val_acc: 0.8720\n",
      "Epoch 15/20\n",
      "25/25 [==============================] - 0s 17ms/step - loss: 0.0130 - acc: 0.9986 - val_loss: 0.5101 - val_acc: 0.8712\n",
      "Epoch 16/20\n",
      "25/25 [==============================] - 0s 17ms/step - loss: 0.0093 - acc: 0.9990 - val_loss: 0.5462 - val_acc: 0.8697\n",
      "Epoch 17/20\n",
      "25/25 [==============================] - 1s 21ms/step - loss: 0.0064 - acc: 0.9998 - val_loss: 0.5854 - val_acc: 0.8690\n",
      "Epoch 18/20\n",
      "25/25 [==============================] - 0s 16ms/step - loss: 0.0046 - acc: 0.9999 - val_loss: 0.6867 - val_acc: 0.8537\n",
      "Epoch 19/20\n",
      "25/25 [==============================] - 0s 19ms/step - loss: 0.0034 - acc: 0.9999 - val_loss: 0.6714 - val_acc: 0.8644\n",
      "Epoch 20/20\n",
      "25/25 [==============================] - 0s 15ms/step - loss: 0.0023 - acc: 0.9999 - val_loss: 0.7088 - val_acc: 0.8671\n",
      "Epoch 1/4\n",
      "49/49 [==============================] - 1s 9ms/step - loss: 0.4800 - accuracy: 0.8227\n",
      "Epoch 2/4\n",
      "49/49 [==============================] - 1s 12ms/step - loss: 0.2640 - accuracy: 0.9120\n",
      "Epoch 3/4\n",
      "49/49 [==============================] - 0s 10ms/step - loss: 0.1976 - accuracy: 0.9328\n",
      "Epoch 4/4\n",
      "49/49 [==============================] - 0s 9ms/step - loss: 0.1616 - accuracy: 0.9441\n",
      "782/782 [==============================] - 1s 1ms/step - loss: 0.3036 - accuracy: 0.8790\n",
      "Epoch 1/20\n",
      "20/20 [==============================] - 1s 56ms/step - loss: 0.5482 - acc: 0.7406 - val_loss: 0.4159 - val_acc: 0.8656\n",
      "Epoch 2/20\n",
      "20/20 [==============================] - 0s 26ms/step - loss: 0.3279 - acc: 0.9059 - val_loss: 0.3340 - val_acc: 0.8841\n",
      "Epoch 3/20\n",
      "20/20 [==============================] - 0s 24ms/step - loss: 0.2331 - acc: 0.9398 - val_loss: 0.3165 - val_acc: 0.8767\n",
      "Epoch 4/20\n",
      "20/20 [==============================] - 0s 25ms/step - loss: 0.1802 - acc: 0.9518 - val_loss: 0.2970 - val_acc: 0.8836\n",
      "Epoch 5/20\n",
      "20/20 [==============================] - 0s 25ms/step - loss: 0.1314 - acc: 0.9708 - val_loss: 0.2943 - val_acc: 0.8822\n",
      "Epoch 6/20\n",
      "20/20 [==============================] - 1s 26ms/step - loss: 0.1029 - acc: 0.9770 - val_loss: 0.2953 - val_acc: 0.8835\n",
      "Epoch 7/20\n",
      "20/20 [==============================] - 0s 24ms/step - loss: 0.0787 - acc: 0.9848 - val_loss: 0.3065 - val_acc: 0.8816\n",
      "Epoch 8/20\n",
      "20/20 [==============================] - 1s 26ms/step - loss: 0.0558 - acc: 0.9915 - val_loss: 0.3222 - val_acc: 0.8806\n",
      "Epoch 9/20\n",
      "20/20 [==============================] - 0s 25ms/step - loss: 0.0458 - acc: 0.9927 - val_loss: 0.3388 - val_acc: 0.8783\n",
      "Epoch 10/20\n",
      "20/20 [==============================] - 1s 26ms/step - loss: 0.0293 - acc: 0.9965 - val_loss: 0.3673 - val_acc: 0.8752\n",
      "Epoch 11/20\n",
      "20/20 [==============================] - 0s 25ms/step - loss: 0.0226 - acc: 0.9973 - val_loss: 0.3967 - val_acc: 0.8740\n",
      "Epoch 12/20\n",
      "20/20 [==============================] - 0s 24ms/step - loss: 0.0174 - acc: 0.9980 - val_loss: 0.4429 - val_acc: 0.8690\n",
      "Epoch 13/20\n",
      "20/20 [==============================] - 0s 24ms/step - loss: 0.0099 - acc: 0.9995 - val_loss: 0.4419 - val_acc: 0.8730\n",
      "Epoch 14/20\n",
      "20/20 [==============================] - 0s 25ms/step - loss: 0.0072 - acc: 0.9997 - val_loss: 0.4796 - val_acc: 0.8700\n",
      "Epoch 15/20\n",
      "20/20 [==============================] - 0s 25ms/step - loss: 0.0051 - acc: 0.9998 - val_loss: 0.6304 - val_acc: 0.8536\n",
      "Epoch 16/20\n",
      "20/20 [==============================] - 0s 25ms/step - loss: 0.0034 - acc: 0.9999 - val_loss: 0.5529 - val_acc: 0.8688\n",
      "Epoch 17/20\n",
      "20/20 [==============================] - 1s 26ms/step - loss: 0.0022 - acc: 0.9999 - val_loss: 0.6786 - val_acc: 0.8580\n",
      "Epoch 18/20\n",
      "20/20 [==============================] - 1s 27ms/step - loss: 0.0017 - acc: 1.0000 - val_loss: 0.6263 - val_acc: 0.8688\n",
      "Epoch 19/20\n",
      "20/20 [==============================] - 1s 26ms/step - loss: 9.1288e-04 - acc: 1.0000 - val_loss: 0.6684 - val_acc: 0.8662\n",
      "Epoch 20/20\n",
      "20/20 [==============================] - 1s 28ms/step - loss: 5.4706e-04 - acc: 1.0000 - val_loss: 0.7216 - val_acc: 0.8660\n",
      "Epoch 1/4\n",
      "49/49 [==============================] - 1s 13ms/step - loss: 0.4513 - accuracy: 0.8294\n",
      "Epoch 2/4\n",
      "49/49 [==============================] - 1s 14ms/step - loss: 0.2424 - accuracy: 0.9189\n",
      "Epoch 3/4\n",
      "49/49 [==============================] - 1s 16ms/step - loss: 0.1795 - accuracy: 0.9391\n",
      "Epoch 4/4\n",
      "49/49 [==============================] - 1s 13ms/step - loss: 0.1444 - accuracy: 0.9520\n",
      "782/782 [==============================] - 1s 2ms/step - loss: 0.2990 - accuracy: 0.8837\n",
      "Epoch 1/20\n",
      "15/15 [==============================] - 2s 90ms/step - loss: 0.6085 - acc: 0.6944 - val_loss: 0.4993 - val_acc: 0.8219\n",
      "Epoch 2/20\n",
      "15/15 [==============================] - 1s 37ms/step - loss: 0.3983 - acc: 0.9009 - val_loss: 0.4113 - val_acc: 0.8608\n",
      "Epoch 3/20\n",
      "15/15 [==============================] - 1s 37ms/step - loss: 0.2894 - acc: 0.9368 - val_loss: 0.3475 - val_acc: 0.8791\n",
      "Epoch 4/20\n",
      "15/15 [==============================] - 1s 35ms/step - loss: 0.2095 - acc: 0.9597 - val_loss: 0.3175 - val_acc: 0.8794\n",
      "Epoch 5/20\n",
      "15/15 [==============================] - 1s 38ms/step - loss: 0.1588 - acc: 0.9698 - val_loss: 0.2967 - val_acc: 0.8853\n",
      "Epoch 6/20\n",
      "15/15 [==============================] - 1s 46ms/step - loss: 0.1212 - acc: 0.9773 - val_loss: 0.2955 - val_acc: 0.8817\n",
      "Epoch 7/20\n",
      "15/15 [==============================] - 1s 39ms/step - loss: 0.0892 - acc: 0.9868 - val_loss: 0.3005 - val_acc: 0.8807\n",
      "Epoch 8/20\n",
      "15/15 [==============================] - 1s 36ms/step - loss: 0.0687 - acc: 0.9917 - val_loss: 0.3065 - val_acc: 0.8804\n",
      "Epoch 9/20\n",
      "15/15 [==============================] - 1s 38ms/step - loss: 0.0520 - acc: 0.9944 - val_loss: 0.3204 - val_acc: 0.8785\n",
      "Epoch 10/20\n",
      "15/15 [==============================] - 1s 40ms/step - loss: 0.0377 - acc: 0.9973 - val_loss: 0.3249 - val_acc: 0.8784\n",
      "Epoch 11/20\n",
      "15/15 [==============================] - 1s 36ms/step - loss: 0.0279 - acc: 0.9979 - val_loss: 0.3957 - val_acc: 0.8660\n",
      "Epoch 12/20\n",
      "15/15 [==============================] - 1s 38ms/step - loss: 0.0210 - acc: 0.9987 - val_loss: 0.3970 - val_acc: 0.8700\n",
      "Epoch 13/20\n",
      "15/15 [==============================] - 1s 38ms/step - loss: 0.0144 - acc: 0.9991 - val_loss: 0.4130 - val_acc: 0.8714\n",
      "Epoch 14/20\n",
      "15/15 [==============================] - 1s 35ms/step - loss: 0.0101 - acc: 0.9995 - val_loss: 0.4722 - val_acc: 0.8629\n",
      "Epoch 15/20\n",
      "15/15 [==============================] - 1s 40ms/step - loss: 0.0068 - acc: 0.9999 - val_loss: 0.4377 - val_acc: 0.8728\n",
      "Epoch 16/20\n",
      "15/15 [==============================] - 1s 38ms/step - loss: 0.0045 - acc: 1.0000 - val_loss: 0.5691 - val_acc: 0.8561\n",
      "Epoch 17/20\n",
      "15/15 [==============================] - 1s 37ms/step - loss: 0.0031 - acc: 1.0000 - val_loss: 0.4953 - val_acc: 0.8705\n",
      "Epoch 18/20\n",
      "15/15 [==============================] - 1s 36ms/step - loss: 0.0021 - acc: 1.0000 - val_loss: 0.5436 - val_acc: 0.8687\n",
      "Epoch 19/20\n",
      "15/15 [==============================] - 1s 38ms/step - loss: 0.0013 - acc: 1.0000 - val_loss: 0.5861 - val_acc: 0.8679\n",
      "Epoch 20/20\n",
      "15/15 [==============================] - 1s 35ms/step - loss: 7.9152e-04 - acc: 1.0000 - val_loss: 0.6122 - val_acc: 0.8675\n",
      "Epoch 1/4\n",
      "49/49 [==============================] - 1s 13ms/step - loss: 0.5192 - accuracy: 0.7888\n",
      "Epoch 2/4\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "49/49 [==============================] - 1s 13ms/step - loss: 0.3000 - accuracy: 0.9133\n",
      "Epoch 3/4\n",
      "49/49 [==============================] - 1s 15ms/step - loss: 0.2009 - accuracy: 0.9389\n",
      "Epoch 4/4\n",
      "49/49 [==============================] - 1s 13ms/step - loss: 0.1501 - accuracy: 0.9534\n",
      "782/782 [==============================] - 2s 2ms/step - loss: 0.2952 - accuracy: 0.8842\n",
      "Epoch 1/20\n",
      "10/10 [==============================] - 2s 180ms/step - loss: 0.6373 - acc: 0.6526 - val_loss: 0.5472 - val_acc: 0.8347\n",
      "Epoch 2/20\n",
      "10/10 [==============================] - 1s 68ms/step - loss: 0.4622 - acc: 0.8888 - val_loss: 0.4637 - val_acc: 0.8557\n",
      "Epoch 3/20\n",
      "10/10 [==============================] - 1s 65ms/step - loss: 0.3459 - acc: 0.9333 - val_loss: 0.4030 - val_acc: 0.8628\n",
      "Epoch 4/20\n",
      "10/10 [==============================] - 1s 64ms/step - loss: 0.2730 - acc: 0.9475 - val_loss: 0.3606 - val_acc: 0.8751\n",
      "Epoch 5/20\n",
      "10/10 [==============================] - 1s 63ms/step - loss: 0.2133 - acc: 0.9629 - val_loss: 0.3354 - val_acc: 0.8768\n",
      "Epoch 6/20\n",
      "10/10 [==============================] - 1s 63ms/step - loss: 0.1594 - acc: 0.9794 - val_loss: 0.3222 - val_acc: 0.8744\n",
      "Epoch 7/20\n",
      "10/10 [==============================] - 1s 60ms/step - loss: 0.1255 - acc: 0.9870 - val_loss: 0.3083 - val_acc: 0.8781\n",
      "Epoch 8/20\n",
      "10/10 [==============================] - 1s 64ms/step - loss: 0.0951 - acc: 0.9920 - val_loss: 0.3252 - val_acc: 0.8669\n",
      "Epoch 9/20\n",
      "10/10 [==============================] - 1s 64ms/step - loss: 0.0749 - acc: 0.9938 - val_loss: 0.3146 - val_acc: 0.8705\n",
      "Epoch 10/20\n",
      "10/10 [==============================] - 1s 63ms/step - loss: 0.0555 - acc: 0.9966 - val_loss: 0.3182 - val_acc: 0.8703\n",
      "Epoch 11/20\n",
      "10/10 [==============================] - 1s 65ms/step - loss: 0.0418 - acc: 0.9984 - val_loss: 0.3215 - val_acc: 0.8708\n",
      "Epoch 12/20\n",
      "10/10 [==============================] - 1s 64ms/step - loss: 0.0319 - acc: 0.9986 - val_loss: 0.3293 - val_acc: 0.8710\n",
      "Epoch 13/20\n",
      "10/10 [==============================] - 1s 60ms/step - loss: 0.0232 - acc: 0.9994 - val_loss: 0.3382 - val_acc: 0.8707\n",
      "Epoch 14/20\n",
      "10/10 [==============================] - 1s 65ms/step - loss: 0.0170 - acc: 0.9996 - val_loss: 0.3605 - val_acc: 0.8681\n",
      "Epoch 15/20\n",
      "10/10 [==============================] - 1s 65ms/step - loss: 0.0124 - acc: 0.9998 - val_loss: 0.3644 - val_acc: 0.8698\n",
      "Epoch 16/20\n",
      "10/10 [==============================] - 1s 64ms/step - loss: 0.0087 - acc: 1.0000 - val_loss: 0.3872 - val_acc: 0.8672\n",
      "Epoch 17/20\n",
      "10/10 [==============================] - 1s 59ms/step - loss: 0.0066 - acc: 1.0000 - val_loss: 0.4299 - val_acc: 0.8619\n",
      "Epoch 18/20\n",
      "10/10 [==============================] - 1s 66ms/step - loss: 0.0046 - acc: 1.0000 - val_loss: 0.4192 - val_acc: 0.8683\n",
      "Epoch 19/20\n",
      "10/10 [==============================] - 1s 64ms/step - loss: 0.0032 - acc: 1.0000 - val_loss: 0.4415 - val_acc: 0.8661\n",
      "Epoch 20/20\n",
      "10/10 [==============================] - 1s 57ms/step - loss: 0.0022 - acc: 1.0000 - val_loss: 0.4649 - val_acc: 0.8649\n",
      "Epoch 1/4\n",
      "49/49 [==============================] - 1s 15ms/step - loss: 0.4569 - accuracy: 0.8140\n",
      "Epoch 2/4\n",
      "49/49 [==============================] - 1s 16ms/step - loss: 0.2401 - accuracy: 0.9195\n",
      "Epoch 3/4\n",
      "49/49 [==============================] - 1s 15ms/step - loss: 0.1721 - accuracy: 0.9422\n",
      "Epoch 4/4\n",
      "49/49 [==============================] - 1s 15ms/step - loss: 0.1308 - accuracy: 0.9578\n",
      "782/782 [==============================] - 2s 2ms/step - loss: 0.3335 - accuracy: 0.8712\n",
      "Epoch 1/20\n",
      "5/5 [==============================] - 3s 567ms/step - loss: 0.6676 - acc: 0.5172 - val_loss: 0.6480 - val_acc: 0.8022\n",
      "Epoch 2/20\n",
      "5/5 [==============================] - 1s 180ms/step - loss: 0.5660 - acc: 0.7752 - val_loss: 0.5786 - val_acc: 0.6458\n",
      "Epoch 3/20\n",
      "5/5 [==============================] - 1s 171ms/step - loss: 0.4245 - acc: 0.8922 - val_loss: 0.4866 - val_acc: 0.8444\n",
      "Epoch 4/20\n",
      "5/5 [==============================] - 1s 173ms/step - loss: 0.3491 - acc: 0.9415 - val_loss: 0.4778 - val_acc: 0.7865\n",
      "Epoch 5/20\n",
      "5/5 [==============================] - 1s 170ms/step - loss: 0.2666 - acc: 0.9748 - val_loss: 0.4207 - val_acc: 0.8501\n",
      "Epoch 6/20\n",
      "5/5 [==============================] - 1s 171ms/step - loss: 0.2169 - acc: 0.9868 - val_loss: 0.4305 - val_acc: 0.8144\n",
      "Epoch 7/20\n",
      "5/5 [==============================] - 1s 170ms/step - loss: 0.1811 - acc: 0.9884 - val_loss: 0.3791 - val_acc: 0.8603\n",
      "Epoch 8/20\n",
      "5/5 [==============================] - 1s 167ms/step - loss: 0.1465 - acc: 0.9936 - val_loss: 0.4048 - val_acc: 0.8242\n",
      "Epoch 9/20\n",
      "5/5 [==============================] - 1s 164ms/step - loss: 0.1164 - acc: 0.9968 - val_loss: 0.3558 - val_acc: 0.8603\n",
      "Epoch 10/20\n",
      "5/5 [==============================] - 1s 162ms/step - loss: 0.0957 - acc: 0.9964 - val_loss: 0.3596 - val_acc: 0.8495\n",
      "Epoch 11/20\n",
      "5/5 [==============================] - 1s 163ms/step - loss: 0.0758 - acc: 0.9992 - val_loss: 0.3450 - val_acc: 0.8580\n",
      "Epoch 12/20\n",
      "5/5 [==============================] - 1s 161ms/step - loss: 0.0643 - acc: 0.9992 - val_loss: 0.3915 - val_acc: 0.8277\n",
      "Epoch 13/20\n",
      "5/5 [==============================] - 1s 163ms/step - loss: 0.0515 - acc: 0.9992 - val_loss: 0.3408 - val_acc: 0.8580\n",
      "Epoch 14/20\n",
      "5/5 [==============================] - 1s 163ms/step - loss: 0.0401 - acc: 0.9996 - val_loss: 0.3560 - val_acc: 0.8476\n",
      "Epoch 15/20\n",
      "5/5 [==============================] - 1s 169ms/step - loss: 0.0328 - acc: 0.9996 - val_loss: 0.3435 - val_acc: 0.8560\n",
      "Epoch 16/20\n",
      "5/5 [==============================] - 1s 162ms/step - loss: 0.0268 - acc: 1.0000 - val_loss: 0.3858 - val_acc: 0.8359\n",
      "Epoch 17/20\n",
      "5/5 [==============================] - 1s 161ms/step - loss: 0.0226 - acc: 1.0000 - val_loss: 0.3499 - val_acc: 0.8559\n",
      "Epoch 18/20\n",
      "5/5 [==============================] - 1s 162ms/step - loss: 0.0174 - acc: 1.0000 - val_loss: 0.3629 - val_acc: 0.8496\n",
      "Epoch 19/20\n",
      "5/5 [==============================] - 1s 160ms/step - loss: 0.0141 - acc: 1.0000 - val_loss: 0.3736 - val_acc: 0.8465\n",
      "Epoch 20/20\n",
      "5/5 [==============================] - 1s 148ms/step - loss: 0.0114 - acc: 1.0000 - val_loss: 0.3716 - val_acc: 0.8506\n",
      "Epoch 1/4\n",
      "49/49 [==============================] - 1s 20ms/step - loss: 0.4369 - accuracy: 0.8322\n",
      "Epoch 2/4\n",
      "49/49 [==============================] - 1s 20ms/step - loss: 0.2300 - accuracy: 0.9236\n",
      "Epoch 3/4\n",
      "49/49 [==============================] - 1s 19ms/step - loss: 0.1627 - accuracy: 0.9450\n",
      "Epoch 4/4\n",
      "49/49 [==============================] - 1s 18ms/step - loss: 0.1246 - accuracy: 0.9590\n",
      "782/782 [==============================] - 2s 2ms/step - loss: 0.3043 - accuracy: 0.8815\n",
      "Epoch 1/20\n",
      "1/1 [==============================] - 3s 3s/step - loss: 0.6847 - acc: 1.0000 - val_loss: 0.6963 - val_acc: 0.5015\n",
      "Epoch 2/20\n",
      "1/1 [==============================] - 1s 842ms/step - loss: 0.5676 - acc: 1.0000 - val_loss: 0.6992 - val_acc: 0.5001\n",
      "Epoch 3/20\n",
      "1/1 [==============================] - 1s 759ms/step - loss: 0.4604 - acc: 1.0000 - val_loss: 0.7019 - val_acc: 0.5002\n",
      "Epoch 4/20\n",
      "1/1 [==============================] - 1s 762ms/step - loss: 0.3887 - acc: 1.0000 - val_loss: 0.7051 - val_acc: 0.5001\n",
      "Epoch 5/20\n",
      "1/1 [==============================] - 1s 783ms/step - loss: 0.3351 - acc: 1.0000 - val_loss: 0.7082 - val_acc: 0.5000\n",
      "Epoch 6/20\n",
      "1/1 [==============================] - 1s 799ms/step - loss: 0.2986 - acc: 1.0000 - val_loss: 0.7117 - val_acc: 0.5000\n",
      "Epoch 7/20\n",
      "1/1 [==============================] - 1s 776ms/step - loss: 0.2633 - acc: 1.0000 - val_loss: 0.7147 - val_acc: 0.5000\n",
      "Epoch 8/20\n",
      "1/1 [==============================] - 1s 731ms/step - loss: 0.2385 - acc: 1.0000 - val_loss: 0.7186 - val_acc: 0.5000\n",
      "Epoch 9/20\n",
      "1/1 [==============================] - 1s 730ms/step - loss: 0.2131 - acc: 1.0000 - val_loss: 0.7221 - val_acc: 0.5000\n",
      "Epoch 10/20\n",
      "1/1 [==============================] - 1s 732ms/step - loss: 0.1923 - acc: 1.0000 - val_loss: 0.7258 - val_acc: 0.5000\n",
      "Epoch 11/20\n",
      "1/1 [==============================] - 1s 752ms/step - loss: 0.1742 - acc: 1.0000 - val_loss: 0.7292 - val_acc: 0.5000\n",
      "Epoch 12/20\n",
      "1/1 [==============================] - 1s 731ms/step - loss: 0.1591 - acc: 1.0000 - val_loss: 0.7330 - val_acc: 0.5000\n",
      "Epoch 13/20\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1/1 [==============================] - 1s 725ms/step - loss: 0.1448 - acc: 1.0000 - val_loss: 0.7368 - val_acc: 0.5000\n",
      "Epoch 14/20\n",
      "1/1 [==============================] - 1s 733ms/step - loss: 0.1321 - acc: 1.0000 - val_loss: 0.7407 - val_acc: 0.5000\n",
      "Epoch 15/20\n",
      "1/1 [==============================] - 1s 730ms/step - loss: 0.1207 - acc: 1.0000 - val_loss: 0.7447 - val_acc: 0.5000\n",
      "Epoch 16/20\n",
      "1/1 [==============================] - 1s 744ms/step - loss: 0.1107 - acc: 1.0000 - val_loss: 0.7484 - val_acc: 0.5000\n",
      "Epoch 17/20\n",
      "1/1 [==============================] - 1s 724ms/step - loss: 0.1019 - acc: 1.0000 - val_loss: 0.7525 - val_acc: 0.5000\n",
      "Epoch 18/20\n",
      "1/1 [==============================] - 1s 722ms/step - loss: 0.0936 - acc: 1.0000 - val_loss: 0.7566 - val_acc: 0.5000\n",
      "Epoch 19/20\n",
      "1/1 [==============================] - 1s 727ms/step - loss: 0.0861 - acc: 1.0000 - val_loss: 0.7607 - val_acc: 0.5000\n",
      "Epoch 20/20\n",
      "1/1 [==============================] - 1s 733ms/step - loss: 0.0794 - acc: 1.0000 - val_loss: 0.7647 - val_acc: 0.5000\n",
      "Epoch 1/4\n",
      "49/49 [==============================] - 2s 22ms/step - loss: 0.4456 - accuracy: 0.8332\n",
      "Epoch 2/4\n",
      "49/49 [==============================] - 1s 22ms/step - loss: 0.2349 - accuracy: 0.9212\n",
      "Epoch 3/4\n",
      "49/49 [==============================] - 1s 22ms/step - loss: 0.1668 - accuracy: 0.9445\n",
      "Epoch 4/4\n",
      "49/49 [==============================] - 1s 21ms/step - loss: 0.1270 - accuracy: 0.9585\n",
      "782/782 [==============================] - 2s 2ms/step - loss: 0.2962 - accuracy: 0.8854\n",
      "[0.670025646686554, 0.29440852999687195, 0.3107953369617462, 0.2880347967147827, 0.285887748003006, 0.3035995364189148, 0.2990269064903259, 0.29524073004722595, 0.3334537446498871, 0.3042912185192108, 0.296213835477829]\n",
      "[0.5885999798774719, 0.8781200051307678, 0.8758800029754639, 0.8837599754333496, 0.8870000243186951, 0.8790000081062317, 0.8837199807167053, 0.8841999769210815, 0.8712400197982788, 0.8814799785614014, 0.8854399919509888]\n"
     ]
    }
   ],
   "source": [
    "x_list = []\n",
    "y_list = []\n",
    "j = 49\n",
    "for i in range(11):\n",
    "    \n",
    "    x_Accuracy, y_Accuracy = handling_input_data_size(j)\n",
    "    x_list.append(x_Accuracy)\n",
    "    y_list.append(y_Accuracy)\n",
    "    j+= 2495\n",
    "\n",
    "print(x_list)\n",
    "print(y_list)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "0424f353",
   "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>데이터 개수</th>\n",
       "      <th>50</th>\n",
       "      <th>2545</th>\n",
       "      <th>5040</th>\n",
       "      <th>7535</th>\n",
       "      <th>10030</th>\n",
       "      <th>12525</th>\n",
       "      <th>15020</th>\n",
       "      <th>17515</th>\n",
       "      <th>20010</th>\n",
       "      <th>22505</th>\n",
       "      <th>25000</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>정확도</th>\n",
       "      <td>0.5886</td>\n",
       "      <td>0.87812</td>\n",
       "      <td>0.87588</td>\n",
       "      <td>0.88376</td>\n",
       "      <td>0.887</td>\n",
       "      <td>0.879</td>\n",
       "      <td>0.88372</td>\n",
       "      <td>0.8842</td>\n",
       "      <td>0.87124</td>\n",
       "      <td>0.88148</td>\n",
       "      <td>0.88544</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "데이터 개수   50       2545     5040     7535   10030  12525    15020   17515  \\\n",
       "정확도     0.5886  0.87812  0.87588  0.88376  0.887  0.879  0.88372  0.8842   \n",
       "\n",
       "데이터 개수    20010    22505    25000  \n",
       "정확도     0.87124  0.88148  0.88544  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "data = [y_list]\n",
    "columns = list(range(50,25001,2495))\n",
    "index = ['정확도']\n",
    "\n",
    "df = pd.DataFrame(data,columns = columns, index = index)\n",
    "df.columns.name = '데이터 개수'\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "091e02bc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "\n",
    "x = df.columns\n",
    "y = df.values[0]\n",
    "plt.figure(figsize=(8,4))\n",
    "plt.plot(x,y)\n",
    "plt.xticks(list(range(50,27494,2495)))\n",
    "plt.grid(True,axis='x')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d620b54f",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}