Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

a mistake has been found #3

Open
ForawardStar opened this issue Jan 8, 2021 · 0 comments
Open

a mistake has been found #3

ForawardStar opened this issue Jan 8, 2021 · 0 comments

Comments

@ForawardStar
Copy link

ForawardStar commented Jan 8, 2021

Hello! very great project, it gives me a lot help. But I think I found a mistake in model.py, line291, which is 'mupp, logvarpp = self.encoder(xp.detach())'. I suppose that 'xp' should not be detached when updating the parameters of decoder, since it would stop the gradient of backpropagation to decoder, or the generator. Does someone found the same mistake? Thanks, I have given a star.

@ForawardStar ForawardStar changed the title a question about stop gradient a mistake is found Jan 8, 2021
@ForawardStar ForawardStar changed the title a mistake is found a mistake has been found Jan 8, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant