慕课网视频中的代码---3-4 Minst手写体识别

 慕课网视频地址：https://www.imooc.com/video/17905

import matplotlib.pyplot as plt
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense
from keras.optimizers import SGD

# 加载数据源
(x_train, y_train), (x_test, y_test) = mnist.load_data()
print(x_train.shape,y_train.shape)
print(x_test.shape,y_test.shape)
# 打印第一张图片及对应的数据 是5
im = plt.imshow(x_train[0])
print(y_train[0])
plt.show()

# 我们使用的是多层感知机，没有在空间中识别矩阵阵变的算法  将图片摊平 变成一维的向量
x_train = x_train.reshape(60000,784)
x_test = x_test.reshape(10000,784)

print(x_train.shape)

# 将数据变成0-1之间的好处：加速收敛，减少脏数据的影响
x_train = x_train/255
x_test = x_test/255

# 神经网络的输出是多个层，所以要将y标签要变成独热编码(one-hot) 比如：3 就变成[0,0,1,0,0,0,0,0,0,0]
y_train = keras.utils.to_categorical(y_train,10)
y_test = keras.utils.to_categorical(y_test,10)

model = Sequential()
model.add(Dense(512,activation='relu',input_shape = (784,)))
model.add(Dense(256,activation='relu'))
model.add(Dense(10,activation='softmax')) # 将输出值 控制在0-1之间
# 打印模型的结构
model.summary()
# 编译
model.compile(optimizer=SGD(),loss='categorical_crossentropy',metrics=['accuracy'])
model.fit(x_train,y_train,batch_size=64,epochs=5,validation_data=(x_test,y_test))

 结果：