keras打印train_loss,val_loss,train_acc,val_acc

1.添加網絡結構

model.add(...)
model.add(...)
...

2.模型編譯

model.compile(loss='...'，omeptimizer='...'，metrics=['accuracy'])

3.模型訓練

history = model.fit(x_train,y_train,batchsize=64,epoch=epochs,validation=(x_test,y_test))

4.打印結果

plt.plot(history.epoch, history.history['loss'], label='train loss+error')
plt.plot(history.epoch, history.history['val_loss'], label='val_error')
plt.plot(history.epoch, history.history['acc'],label='train_acc')
plt.plot(history.epoch, history.history['val_acc'], label = 'val_acc')
plt.legend()