Contrastive-Predictive-Coding-PyTorch the self.softmax() don't update the paras in the CDCK2?

the self.softmax() don't update the paras in the CDCK2?

Open super-wcg opened this issue 5 years ago • 1 comments

I don't understand how to update the self.softmax() when training, because the acc don't backward. How does it work?

Jun 17 '20 04:06 super-wcg

@jefflai108

Jun 17 '20 04:06 super-wcg