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 problem for your DCGAN architecture #19

Open
RayGuo-C opened this issue Sep 23, 2021 · 1 comment
Open

A problem for your DCGAN architecture #19

RayGuo-C opened this issue Sep 23, 2021 · 1 comment

Comments

@RayGuo-C
Copy link

RayGuo-C commented Sep 23, 2021

Hi, - Your work is really interesting.
But I have found there is a problem for your DCGAN that I didn't understand.
You generate noise twice when train discriminator and generator for each iteration, like the blue lines in the following picture. In soumith code (includes some official DCGAN code), he only generate noise once: https://github.com/soumith/dcgan.torch. Could you please tell me the reason?

image

@RayGuo-C RayGuo-C changed the title A problem for your DAGAN architecture A problem for your DCGAN architecture Sep 23, 2021
@LynnHo
Copy link
Owner

LynnHo commented Sep 25, 2021

@RayGuo-C Because G and D training are separated,they don't need the same noise input.

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

2 participants