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

关于DSDG的测试代码 #154

Open
xb9919 opened this issue Jul 5, 2022 · 0 comments
Open

关于DSDG的测试代码 #154

xb9919 opened this issue Jul 5, 2022 · 0 comments

Comments

@xb9919
Copy link

xb9919 commented Jul 5, 2022

你好,我对DSDG中测试代码(FaceX-Zoo/addition_module/DSDG/DUM/test.py)有点疑问,请问测试中计算score的时候,有用到norm的操作(score_norm = torch.sum(mu) / torch.sum(test_maps[:, frame_t, :, :])),针对这个我有两个疑惑:
1、假如是一个fake的样本,torch.sum(test_maps[:, frame_t, :, :]应该等于0?那是否需要加一个偏置项来避免除0的情况发生?
2、假如网络训练的很好的话,mu和test_maps[:, frame_t, :, :]应近似相等?那不论是对real还是fake的样本,score_norm应该都近似为1吧?怎么在计算指标的时候对他们进行区分呢

@xb9919 xb9919 changed the title 关于DSDG 关于DSDG的测试代码 Jul 5, 2022
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