数据下载地址:http://yann.lecun.com/exdb/mnist/
'''Trains a simple convnet on the MNIST dataset.
Gets to 99.25% test accuracy after 12 epochs
(there is still a lot of margin for parameter tuning).
16 seconds per epoch on a GRID K520 GPU.
'''
from __future__ import print_function
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K
batch_size = 128
num_classes = 10
epochs = 12
# input image dimensions
img_rows, img_cols = 28, 28
# the data, shuffled and split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()
if K.image_data_format() == 'channels_first':
x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
input_shape = (1, img_rows, img_cols)
else:
x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
input_shape = (img_rows, img_cols, 1)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')
# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
# 卷积层,对二维输入进行滑动窗卷积
# 当使用该层为第一层时,应提供input_shape参数,在tf模式中,通道维位于第三个位置
# border_mode:边界模式,为"valid","same"或"full",即图像外的边缘点是补0
# 还是补成相同像素,或者是补1
model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
activation='relu',
input_shape=input_shape))
# 卷积层,激活函数是ReLu
model.add(Conv2D(64, (3, 3), activation='relu'))
# 池化层,选用Maxpooling,给定pool_size,dropout比例为0.25
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
# Flatten层,把多维输入进行一维化,常用在卷积层到全连接层的过渡
model.add(Flatten())
# 包含128个神经元的全连接层,激活函数为ReLu,dropout比例为0.5
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
# 包含10个神经元的输出层,激活函数为Softmax
model.add(Dense(num_classes, activation='softmax'))
# 配置模型的学习过程
model.compile(loss=keras.losses.categorical_crossentropy,
optimizer=keras.optimizers.Adadelta(),
metrics=['accuracy'])
# 训练模型
model.fit(x_train, y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(x_test, y_test))
# 按batch计算在某些输入数据上模型的误差
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])