更新时间:2023-12-02 14:13:16
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)