hongy

@WongKinYiu could you add a license?

This is actually caused by a problem in the initialize population method. When running initialize population from a restore, it skips the process of setting the input shape, thus all...

@omalleyt12 gradient transformations may have unintended consequences when paired with moment based optimizers such as Adam. These optimizers usually take the first and second moment of the gradient to compute...

hmm I think this is my fault for using dictionaries to store tensors. I remember encountering similar issues with serializing tensors stored in dictionaries. The easy fix is listed by...

The most lazy option is to simply not support model.save(include_optimizer=True) and only support model.save(include_optimizer=False). Add the note to the documentation and on get config, print a warning that this optimizer...