Closed VoVAllen closed 5 years ago
As you say, the implementation is strictly mirrored from the paper, if you take a closer look you will see that the implementation is correct.
Sorry for the mistake. I realized it's right. Thanks! Another minor problem I found is Dropout. Due to pytorch features, you need to explicit call model.eval() in valuation and test period to turn the Dropout into right mode to get right forward result.
Fixed the dropout issue I didn't see any typo that you mentioned
可能是我看错了……应该没有typo……
Also I see you might also need to add model.eval() at valuation period
The EMD loss still seems to be wrong, my opinion is the sum operation should be inside of torch.abs
Should be the L2 distance between CDF of two distributions but not between the PDF of two distributions
And there's some typo in the naming such as emb and emd