keras CNN端到端的MNIST训练数字识别

     使用keras建立简单的CNN进行数字识别，代码如下，具体步骤带注释：

import numpy as np
from keras.datasets import  mnist

# 引入Keras的卷积模块， 包括Dropout, Conv2D 和 MaxPooling2D
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers.convolutional import Conv2D, MaxPooling2D

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

#预览数据
print(X_train[0].shape)
print(y_train)

# 数据格式成四维张量
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')

# 数据归一化

X_train /= 255
X_train /= 255

# 对y值进行One Hot 编码
def tran_y(y):
    y_ohe = np.zeros(10)
    y_ohe[y] = 1
    return y_ohe

y_train_ohe = np.array([tran_y(y_train[i]) for i in range(len(y_train))])
y_test_ohe = np.array([tran_y(y_test[i]) for i in range(len(y_test))])

# 搭建卷积神经网络

model = Sequential()

# 添加一层卷积层，构造64个过滤器，每个过滤器3*3*1，过滤器挪动步长为1，图的四周补上一圈0，并用relu作为激活函数
model.add(Conv2D(filters=64, kernel_size=(3, 3), strides=(1, 1),
                 padding='same', input_shape=(28, 28, 1), activation='relu'))

# 添加一层 MaxPooling, 在2*2的格子中选取最大值
model.add(MaxPooling2D(pool_size=(2, 2)))

# 设立Dropout层。 讲Dropout的概率设置为0.5
model.add(Dropout(0.5))

# 重复构造， 搭建深度网络
model.add(Conv2D(filters=128, kernel_size=(3, 3), strides=(1, 1),
                 padding='same', input_shape=(28, 28, 1), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))

model.add(Conv2D(filters=256, kernel_size=(3, 3), strides=(1, 1),
                 padding='same', input_shape=(28, 28, 1), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))

# 将当前的层点展平
model.add(Flatten())

# 构造全连接神经网络
model.add(Dense(128, activation='relu'))
model.add(Dense(64, activation='relu'))
model.add(Dense(32, activation='relu'))
model.add(Dense(10, activation='softmax'))

# 定义损失函数， 一般定义为交叉熵（Cross Entropy）
model.compile(loss='categorical_crossentropy', optimizer='Adam', metrics=['accuracy'])

# 放入样本，进行训练
model.fit(X_train, y_train_ohe, validation_data=(X_test, y_test_ohe), epochs=20, batch_size=128)

# 在测试集上评价模型的准确度
scores = model.evaluate(X_test, y_test_ohe, verbose=0)