Keras-历时相关的损失函数

问题描述

我正在使用Keras框架，我想实现一个与历时有关的损失函数(即，每个时期的损失函数都不相同)

I'm working with the Keras framework and I would like to implement an epoch dependent loss function (i.e the loss function isn't the same at each epoch)

您将如何做?您能否添加示例，例如基于 keras VAE教程?

How would you do that ? Can you add an example, for instance based on the keras VAE tutorial ?

谢谢您的帮助

推荐答案

这可以通过重新编译网络来完成.保存的权重不会因重新编译而改变.所以本质上是这样的:

This can be accomplished by recompiling the network. The weights are saved not changed by the recompilation. So in essence something like this:

for epoch in range(nb_epoch):
     loss_function = loss_for_epoch(epoch)
     model.compile(optimizer, loss_function, metrics)
     model.fit(X, y, nb_epoch=1)

这篇关于Keras-历时相关的损失函数的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！