keras中的History对象

keras中的fit_generator和fit函数均返回History对象，那么History怎么用呢？事实上History对象已经记录了运行输出。在了解之前，我们甚至自己定义回调函数记录损失和准确率等。

相关keras源码位于网址：

class History(Callback):
    """Callback that records events into a `History` object.
    This callback is automatically applied to
    every Keras model. The `History` object
    gets returned by the `fit` method of models.
    """

    def on_train_begin(self, logs=None):
        self.epoch = []
        self.history = {}

    def on_epoch_end(self, epoch, logs=None):
        logs = logs or {}
        self.epoch.append(epoch)
        for k, v in logs.items():
            self.history.setdefault(k, []).append(v)

可以看出History类对象包含两个属性，分别为epoch和history，epoch为训练轮数。

根据compile参数metrics，history包含不同的内容。比如，当某一次metrics=['accuracy']时，运行如下部分代码我们可以看出，history字典类型，包含val_loss,val_acc,loss,acc四个key值。

####省略若干
history = model.fit_generator(
      mp.train_flow,
      steps_per_epoch=32,
      epochs=3,
      validation_data=mp.test_flow,
      validation_steps=32)
print(history.history)
print(history.epoch)

print(history.history['val_loss'])

{‘val_loss’: [0.4231100323200226, 0.3713115310668945, 0.3836631367206573], ‘val_acc’: [0.815, 0.84, 0.83], ‘loss’: [0.8348453622311354, 0.5010451343324449, 0.4296100065112114], ‘acc’: [0.630859375, 0.7509920634920635, 0.783203125]}
[0, 1, 2]
[0.4231100323200226, 0.3713115310668945, 0.3836631367206573]