如何使用自定义优化器加载保存了keras的模型 [英] How do I load a keras saved model with custom Optimizer

问题描述

我已经使用自定义优化器编译并训练了keras模型.我保存了模型，但是当我尝试加载模型时，它抛出错误，指出ValueError: Unknown optimizer: MyOptimizer.我试图将MyOptimizer作为自定义对象传递，例如:models.load_model('myModel.h5', custom_objects={'optimizer':MyOptimizer})，但仍然会引发错误.如何使用自定义对象将模型加载为keras模型?

I have compiled and trained a keras model with a custom optimizer. I saved the model but when I try to load the model, it throws an error stating ValueError: Unknown optimizer: MyOptimizer. I tried to pass MyOptimizer as a custom object something like : models.load_model('myModel.h5', custom_objects={'optimizer':MyOptimizer}) and it still throws an error. How do I load the model a keras model with custom Objects?

推荐答案

我遇到了同样的问题:)

I ran into the same problem :)

我通过向模型加载models.load_model('myModel.h5', compile=False)使它起作用.

I made it work by loading the model with models.load_model('myModel.h5', compile=False).

来自keras 源代码:

如果在保存的模型中找到优化器，则该模型已经编译.否则，该模型将无法编译，并且将显示警告.当compile设置为False时，将省略编译而不会发出任何警告.

If an optimizer was found as part of the saved model, the model is already compiled. Otherwise, the model is uncompiled and a warning will be displayed. When compile is set to False, the compilation is omitted without any warning.

加载未编译的模型后，我可以使用自定义优化器再次对其进行编译.

After the uncompiled model is loaded, I can compile it again with my custom optimizer.

这篇关于如何使用自定义优化器加载保存了keras的模型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IT屋！