from keras.datasets import mnist
from keras import models
from keras import layers
from keras.utils import to_categorical
import matplotlib.pyplot as plt
#导入数据
(train_x,train_y),(test_x,test_y) = mnist.load_data()
#每个神经元表示一个像素，所以把3维数据转换成2维数据
train_x = train_x.reshape(60000,28*28)
train_x = train_x.astype(‘float32‘) /255
test_x = test_x.reshape(10000,28*28)
test_x = test_x.astype(‘float32‘) /255
#把数据中类别用向量表示，以便使用交叉熵,6---->[0,0,0,0,0,0,1,0,0,0]
train_y = to_categorical(train_y)
test_y = to_categorical(test_y)
#定义网络结构
network = models.Sequential()
#Dense表示全连接
network.add(layers.Dense(512,activation="relu",input_shape=(28*28,)))
network.add(layers.Dense(10,activation="softmax"))

#定义损失函数、优化器、监控指标
network.compile(optimizer="rmsprop",loss="categorical_crossentropy",metrics=[‘accuracy‘])
#训练模型
history = network.fit(train_x,train_y,batch_size=128,epochs=11,validation_data=(test_x,test_y))

history_dict = history.history
loss = history_dict[‘loss‘]
val_loss = history_dict[‘val_loss‘]
acc = history_dict[‘acc‘]
val_acc = history_dict[‘val_acc‘]

epochs = range(1,11)
#loss的图
plt.subplot(121)
plt.plot(epochs,loss,‘g‘,label = ‘Training loss‘)
plt.plot(epochs,val_loss,‘b‘,label = ‘Validation loss‘)
plt.xlabel(‘Epochs‘)
plt.ylabel(‘Loss‘)
#显示图例
plt.legend()

plt.subplot(122)
plt.plot(epochs,acc,‘g‘,label = ‘Training accuracy‘)
plt.plot(epochs,val_acc,‘b‘,label = ‘Validation accuracy‘)
plt.xlabel(‘Epochs‘)
plt.ylabel(‘accuracy‘)
plt.legend()
plt.show()