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

about D_real、D_fake、l_d_fake、l_d_real in tb_logger #21

Open
liqian2018 opened this issue May 21, 2021 · 0 comments
Open

about D_real、D_fake、l_d_fake、l_d_real in tb_logger #21

liqian2018 opened this issue May 21, 2021 · 0 comments

Comments

@liqian2018
Copy link

截图_2021-05-21_17-44-35
截图_2021-05-21_17-44-57

I’m not sure that the D_real and D_fake respectly corresponds to which part of the formula fo Lgan. Should they each gradually become larger or smaller? Can you help me see my picture if the training state is correct? i guess D_real represent E[C(Xr)] and D_fake represent E[C(Xf)]?and l_d_real represents log(D(Xr, Xf)) and l_d_fake represents the log(1-D(Xf, Xr)) ?

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