CNN识别手写字符集
from keras.layers import MaxPooling2D
卷积层1
model = Sequential()
model.add(Conv2D(filters=16, kernel_size=3, strides=3, activation='relu', input_shape=(84, 84, 1)))
池化层1
model.add(MaxPooling2D(pool_size=2, strides=2))
卷积层2
model.add(Conv2D(filters=32, kernel_size=3, padding='same', activation='relu'))
池化层2
model.add(MaxPooling2D(pool_size=2, strides=2))
展平上述池化层，隐藏层神经元128个，输出10分类。
from keras.layers import MaxPooling2D,Flatten
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dense(10, activation='softmax'))
model.summary()