Keras自定义丢失未正确计算

时间:2018-01-28 19:08:55

标签: python tensorflow machine-learning deep-learning keras

我试图在Keras中使用自定义丢失功能。我的实现看起来像:

class LossFunction:
    ...

    def loss(self, y_true, y_pred):
        ...
        localization_loss = self._localization_loss()
        confidence_loss = self._object_confidence_loss()
        category_loss = self._category_loss()

        self.loc_loss = localization_loss
        self.obj_conf_loss = confidence_loss
        self.category_loss = category_loss

        tot_loss = localization_loss + confidence_loss + category_loss
        self.tot_loss = tot_loss
        return tot_loss

然后我定义自定义指标来查看存储的张量,如:

class MetricContainer:
    def __init__(self, loss_obj):
        self.loss = loss_obj

    def local_loss(self, y_true, y_pred):
        return self.loss.loc_loss

    def confidence_loss(self, y_true, y_pred):
        return self.loss.obj_conf_loss

    def category_loss(self, y_true, y_pred):
        return self.loss.category_loss

    def tot_loss(self, y_true, y_pred):
        return self.loss.tot_loss

然后我用这个命令编译我的模型:

model.compile('adam', 
              loss=loss_obj.loss,
              metrics=[metric_container.local_loss, 
                       metric_container.confidence_loss, 
                       metric_container.category_loss, 
                       metric_container.tot_loss])

当我训练模型时(在一个非常小的训练集上)我输出如下:

Epoch 1/2
1/2 [==============>...............] - ETA: 76s - loss: 482.6910 - category_loss: 28.1100 - confidence_loss: 439.9192 - local_loss: 13.1180 - tot_loss: 481.1472 
2/2 [==============================] - 96s - loss: 324.6292 - category_loss: 18.1967 - confidence_loss: 296.0593 - local_loss: 8.8204 - tot_loss: 323.0764 - val_loss: 408.1170 - val_category_loss: 0.0000e+00 - val_confidence_loss: 400.0000 - val_local_loss: 6.5036 - val_tot_loss: 406.5036

由于某些原因tot_lossloss不匹配,即使我应该为它们使用相同的值。

知道为什么会这样吗?返回后,Keras会做些什么来修改损失吗?

1 个答案:

答案 0 :(得分:2)

您的损失等于所选损失函数和正则化项的总和。因此,如果您使用任何类型的正则化 - 它会通过添加正则化术语来影响您的损失。