python学习——绘制loss、acc学习曲线

两种方式

1.直接画

# model.fit返回acc和loss的日志
hist=model.fit(train_data, train_label,
          batch_size=64,
          epochs=2,
          validation_split=0.2,
          shuffle=True)


# verbose = 0 为不在标准输出流输出日志信息,verbose = 1 为输出进度条记录,verbose = 2 为每个epoch输出一行记录

# 创建一个绘图窗口
plt.figure()

acc = hist.history['acc']
val_acc = hist.history['val_acc']
loss = hist.history['loss']
val_loss = hist.history['val_loss']

epochs = range(len(acc))

plt.plot(epochs, acc, 'bo', label='Training acc') # 'bo'为画蓝色圆点,不连线
plt.plot(epochs, val_acc, 'b', label='Validation acc') 
plt.title('Training and validation accuracy')
plt.legend() # 绘制图例,默认在右上角

plt.figure()

plt.plot(epochs, loss, 'bo', label='Training loss')
plt.plot(epochs, val_loss, 'b', label='Validation loss')
plt.title('Training and validation loss')
plt.legend()

plt.show()

参考:

Keras绘制Loss,Accuracy值变化曲线

方法二:

参考:

keras画acc和loss曲线图

使用keras绘制实时的loss与acc曲线

你可能感兴趣的:(python,小问题)