【DL--14】Keras案例学习-- CNN做手写字符分类（mnist_cnn ）

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])