from keras.datasets import mnist
from keras.layers import Dense, Flatten, Conv2D, MaxPooling2D, Dropout
from keras.models import Sequential
from keras.optimizers import RMSprop
from keras.utils import np_utils

img_rows, img_cols = 28, 28

(X_train, y_train), (X_test, y_test) = mnist.load_data()

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') / 255.
X_test = X_test.astype('float32') / 255.

Y_train = np_utils.to_categorical(y_train, 10)
Y_test = np_utils.to_categorical(y_test, 10)

model = Sequential()

model.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=input_shape))
model.add(MaxPooling2D())
model.add(Dropout(0.2))

model.add(Conv2D(64, kernel_size=(3, 3), activation='relu'))
model.add(MaxPooling2D())
model.add(Dropout(0.2))

model.add(Conv2D(128, kernel_size=(3, 3), activation='relu'))
model.add(MaxPooling2D())
model.add(Flatten())
model.add(Dropout(0.2))

model.add(Dense(625, activation='relu'))
model.add(Dropout(0.5))

model.add(Dense(10, activation='softmax'))

opt = RMSprop()
model.compile(optimizer=opt, loss='categorical_crossentropy', metrics=['accuracy'])
model.summary()

history = model.fit(X_train, Y_train, nb_epoch=10, batch_size=128, shuffle=True, verbose=2,
                    validation_data=(X_test, Y_test))


_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_1 (Conv2D)            (None, 26, 26, 32)        320       
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 13, 13, 32)        0         
_________________________________________________________________
dropout_1 (Dropout)          (None, 13, 13, 32)        0         
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 11, 11, 64)        18496     
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 5, 5, 64)          0         
_________________________________________________________________
dropout_2 (Dropout)          (None, 5, 5, 64)          0         
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 3, 3, 128)         73856     
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 1, 1, 128)         0         
_________________________________________________________________
flatten_1 (Flatten)          (None, 128)               0         
_________________________________________________________________
dropout_3 (Dropout)          (None, 128)               0         
_________________________________________________________________
dense_1 (Dense)              (None, 625)               80625     
_________________________________________________________________
dropout_4 (Dropout)          (None, 625)               0         
_________________________________________________________________
dense_2 (Dense)              (None, 10)                6260      
=================================================================
Total params: 179,557
Trainable params: 179,557
Non-trainable params: 0

卷积深度神经网络在深度神经网络的基础上，加入了卷积层和池化层。网络的第一层是二维卷积层

Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=input_shape)

这一层的卷积核的数目为32，也就是输出的维度。卷积的空间维度是3_3,也就是用一个3_3的框框去做卷积，采用relu激活函数。 接下来用了MaxPooling2D 这个二维的池化层，主要用来降维和特征提取。

在连续做了3次CNN之后，使用了一个Flatten层。这个层会把多维数据压扁成一维数据，但是不会影响数据总量也就是batch的大小，从summery里面来看，就是把(None, 1, 1, 128) 压扁成了(None, 128) 。

最后，在fit的时候我们看到了一个新的参数shuffle=True，这个参数其实是默认开启的，不写也可以，指定为True，会在每次训练的时候让训练集随机打乱