{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Using TensorFlow backend.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Train on 18000 samples, validate on 42000 samples\n",
"Epoch 1/5\n",
"18000/18000 [==============================] - 2s 117us/step - loss: 1.1511 - acc: 0.7256 - val_loss: 0.6600 - val_acc: 0.8370\n",
"Epoch 2/5\n",
"18000/18000 [==============================] - 2s 85us/step - loss: 0.5191 - acc: 0.8667 - val_loss: 0.4786 - val_acc: 0.8724\n",
"Epoch 3/5\n",
"18000/18000 [==============================] - 2s 84us/step - loss: 0.4141 - acc: 0.8867 - val_loss: 0.4146 - val_acc: 0.8840\n",
"Epoch 4/5\n",
"18000/18000 [==============================] - 2s 87us/step - loss: 0.3684 - acc: 0.8959 - val_loss: 0.3815 - val_acc: 0.8926\n",
"Epoch 5/5\n",
"18000/18000 [==============================] - 2s 87us/step - loss: 0.3406 - acc: 0.9048 - val_loss: 0.3568 - val_acc: 0.8997\n",
"10000/10000 [==============================] - 0s 22us/step\n",
"\n",
"loss_and_metrics : [0.33103723052740097, 0.90649999999999997]\n"
]
}
],
"source": [
"# 0. 사용할 패키지 불러오기\n",
"from keras.utils import np_utils\n",
"from keras.datasets import mnist\n",
"from keras.models import Sequential\n",
"from keras.layers import Dense, Activation\n",
"import numpy as np\n",
"from numpy import argmax\n",
"\n",
"# 1. 데이터셋 생성하기\n",
"\n",
"# 훈련셋과 시험셋 불러오기\n",
"(x_train, y_train), (x_test, y_test) = mnist.load_data()\n",
"\n",
"# 데이터셋 전처리\n",
"x_train = x_train.reshape(60000, 784).astype('float32') / 255.0\n",
"x_test = x_test.reshape(10000, 784).astype('float32') / 255.0\n",
"\n",
"# 원핫인코딩 (one-hot encoding) 처리\n",
"y_train = np_utils.to_categorical(y_train)\n",
"y_test = np_utils.to_categorical(y_test)\n",
"\n",
"# 훈련셋과 검증셋 분리\n",
"x_val = x_train[:42000] # 데이터셋의 70%를 훈련셋/학습셋으로 사용\n",
"x_train = x_train[42000:] # 데이터셋의 30%를 검증셋으로 사용\n",
"y_val = y_train[:42000] # 데이터셋의 70%를 훈련셋/학습셋으로 사용\n",
"y_train = y_train[42000:] # 데이터셋의 30%를 검증셋으로 사용\n",
"\n",
"# 2. 모델 구성하기\n",
"model = Sequential()\n",
"model.add(Dense(units=64, input_dim=28*28, activation='relu'))\n",
"model.add(Dense(units=10, activation='softmax'))\n",
"\n",
"# 3. 모델 학습과정 설정하기\n",
"model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])\n",
"\n",
"# 4. 모델 학습시키기\n",
"model.fit(x_train, y_train, epochs=5, batch_size=32, validation_data=(x_val, y_val))\n",
"\n",
"# 5. 모델 평가하기\n",
"loss_and_metrics = model.evaluate(x_test, y_test, batch_size=32)\n",
"print('')\n",
"print('loss_and_metrics : ' + str(loss_and_metrics))\n",
"\n",
"# 6. 모델 저장하기\n",
"from keras.models import load_model\n",
"model.save('mnist_mlp_model.h5')"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"image/svg+xml": [
""
],
"text/plain": [
""
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from IPython.display import SVG\n",
"from keras.utils.vis_utils import model_to_dot\n",
"\n",
"%matplotlib inline\n",
"\n",
"SVG(model_to_dot(model, show_shapes=True).create(prog='dot', format='svg'))"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Train on 18000 samples, validate on 42000 samples\n",
"Epoch 1/5\n",
"18000/18000 [==============================] - 2s 103us/step - loss: 0.2618 - acc: 0.9269 - val_loss: 0.2936 - val_acc: 0.9162\n",
"Epoch 2/5\n",
"18000/18000 [==============================] - 2s 87us/step - loss: 0.2534 - acc: 0.9293 - val_loss: 0.2891 - val_acc: 0.9177\n",
"Epoch 3/5\n",
"18000/18000 [==============================] - 2s 88us/step - loss: 0.2460 - acc: 0.9312 - val_loss: 0.2817 - val_acc: 0.9201\n",
"Epoch 4/5\n",
"18000/18000 [==============================] - 2s 93us/step - loss: 0.2393 - acc: 0.9332 - val_loss: 0.2762 - val_acc: 0.9211\n",
"Epoch 5/5\n",
"18000/18000 [==============================] - 2s 86us/step - loss: 0.2327 - acc: 0.9354 - val_loss: 0.2700 - val_acc: 0.9231\n",
"10000/10000 [==============================] - 0s 22us/step\n",
"\n",
"loss_and_metrics : [0.25109204970002175, 0.92830000000000001]\n"
]
}
],
"source": [
"# 2. 모델 불러오기\n",
"from keras.models import load_model\n",
"model = load_model('mnist_mlp_model.h5')\n",
"\n",
"# 3. 모델 학습과정 설정하기\n",
"model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])\n",
"\n",
"# 4. 모델 학습시키기\n",
"model.fit(x_train, y_train, epochs=5, batch_size=32, validation_data=(x_val, y_val))\n",
"\n",
"# 5. 모델 평가하기\n",
"loss_and_metrics = model.evaluate(x_test, y_test, batch_size=32)\n",
"print('')\n",
"print('loss_and_metrics : ' + str(loss_and_metrics))\n",
"\n",
"# 6. 모델 저장하기\n",
"from keras.models import load_model\n",
"model.save('mnist_mlp_model.h5')"
]
},
{
"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": "3.5.4"
}
},
"nbformat": 4,
"nbformat_minor": 2
}