深度学习笔记——分类模型（一）LeNet-5

# -*- coding: utf-8 -*-
import datetime
from keras.datasets import mnist
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import *

def main():
    (x_train, y_train), (x_test, y_test) = mnist.load_data()

    x_train = x_train.reshape(x_train.shape[0], 28, 28, 1).astype('float32')
    x_test = x_test.reshape(x_test.shape[0], 28, 28, 1).astype('float32')

    x_train = x_train / 255
    x_test = x_test / 255
    # one hot encode outputs
    y_train = np_utils.to_categorical(y_train)
    y_test = np_utils.to_categorical(y_test)
    num_classes = y_test.shape[1]

    # LeNet-5
    model = Sequential()
    model.add(Conv2D(6, kernel_size=(5, 5), padding='same', activation='relu', input_shape=(28, 28, 1)))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Conv2D(16, kernel_size=(5, 5), padding='same', activation='relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Flatten())
    model.add(Dense(120, activation='relu'))
    model.add(Dense(84, activation='relu'))

    model.add(Dense(num_classes, activation='softmax'))
    model.summary()
    # Compile model
    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
    model.fit(x_train, y_train, validation_data=(x_test, y_test), epochs=10, batch_size=256, verbose=2)
    return 0

if __name__ == '__main__':
    tic = datetime.datetime.now()
    main()
    toc = datetime.datetime.now()
    print("\nThis model took ", (toc - tic))