如果我加载保存到tf保存的模型文件中的模型,则会出现以下问题。 (keras 2.0)
SystemError: unknown opcode
我发现这与模型中的lambda层有关。
https://github.com/keras-team/keras/issues/9595
有人提出了节省架构和重量的解决方案。
Keep the code around and just save the weights. As you said:
save the architecture as code, and the weights in an h5. This will be compatible across versions
但是我该怎么做?
如何立即保存带有lambda层的模型?
谢谢!