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

Question about sc_model.py (bs_per_gpu) #6

Closed
1211sh opened this issue Sep 8, 2021 · 2 comments
Closed

Question about sc_model.py (bs_per_gpu) #6

1211sh opened this issue Sep 8, 2021 · 2 comments

Comments

@1211sh
Copy link

1211sh commented Sep 8, 2021

image

Hi,
I am wondering how the multi-gpu process works in the line 102 and 103.
Line 102 : self.real_A = self.real_A[:bs_per_gpu]

I think self.real_A[:bs_per_gpu] is just simply removing a part of self.real_A, not working as spliting data for multi-gpu.

Is it a typo? or am I wrong?

@o0t1ng0o
Copy link

@1211sh
I think that row 102-103 can be deleted?

@lyndonzheng
Copy link
Owner

Hi @1211sh, this code is used for initializing the feature extractor networks and auxiliary optimizers, instead of the multi-gpu training. The code is based on the CUT.

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

3 participants