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.

Sign up for GitHub

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

Jump to bottom

Correctness Issues. #10

Open
tongche opened this issue Jul 4, 2017 · 1 comment
Open

Correctness Issues. #10

tongche opened this issue Jul 4, 2017 · 1 comment
Labels
question

Comments

@tongche
Copy link

tongche commented Jul 4, 2017

Hi. In this implementation, is batch normalization used in the discriminator? I think in WGAN paper, it is mentioned that you should not use BN in discriminators, right?

In discriminators it seems that the biases term in all convolutional layers are set fixed, and to zero. I don't think this is mentioned in the paper either.
@shekkizh
Copy link
Owner

shekkizh commented Jul 4, 2017

The authors by discarding BN were trying to prove that WGAN formulation is much more stable - You are welcome to comment it out.

I don't remember whether it was mentioned in the paper but the code that was released with the model did have the bias term removed.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
question
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@tongche @shekkizh