Closed jerryuhoo closed 2 years ago
Hey, it does not matter. There is the cross-entropy from logits calculation which is a numerically stable implementation of log softmax and negative log likelihood (see https://pytorch.org/docs/stable/generated/torch.nn.functional.cross_entropy.html#torch.nn.functional.cross_entropy): https://github.com/Tomiinek/Multilingual_Text_to_Speech/blob/5cddc8b0531e3102cf4fb3acb0d04d2713b5b3da/modules/classifier.py#L69
And we never do inference with the classifier.
https://github.com/Tomiinek/Multilingual_Text_to_Speech/blob/5cddc8b0531e3102cf4fb3acb0d04d2713b5b3da/modules/classifier.py#L47-L55
Hi, I saw there's a softmax layer after the hidden layer in your paper, but the code doesn't have it. Does the softmax layer matter?