Closed lc82111 closed 7 years ago
I would like see a clear definition of Wasserstein loss that gets rid of "y_true" or "y_pred", because these remind me conventional entropy loss.
Thanks for letting me know. I may change that when I port the code to Keras 2
I would like see a clear definition of Wasserstein loss that gets rid of "y_true" or "y_pred", because these remind me conventional entropy loss.