Skip to content
New issue

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

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

Already on GitHub? # 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
# for free to join this conversation on GitHub. Already have an account? # to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant