TencentARC/GFPGAN
1
0
Fork 0
mirror of https://github.com/TencentARC/GFPGAN.git synced 2026-07-09 02:06:30 +00:00
Code Issues 476 Packages Projects Releases 8 Wiki Activity

Questions about the discriminator code #120

New Issue
Open
opened 2026-01-29 21:42:58 +00:00 by claunia · 0 comments
claunia commented 2026-01-29 21:42:58 +00:00
Owner
Copy Link

Originally created by @FeiiYin on GitHub (Dec 15, 2021).

Thanks for the impressive work!
I have several questions about the discriminator code of the training process.

The discriminator loss for the Generator part is like

l_g_gan = self.cri_gan(fake_g_pred, target_is_real=True, is_disc=False)

While the discriminator part is like

l_d = self.cri_gan(real_d_pred, target_is_real=True, is_disc=True) + self.cri_gan(fake_d_pred, target_is_real=False, is_disc=True)

Why the target_is_real option differs for fake images at two stages?

Thanks in advance!

Originally created by @FeiiYin on GitHub (Dec 15, 2021). Thanks for the impressive work! I have several questions about the discriminator code of the training process. The discriminator loss for the Generator part is like ``` l_g_gan = self.cri_gan(fake_g_pred, target_is_real=True, is_disc=False) ``` While the discriminator part is like ``` l_d = self.cri_gan(real_d_pred, target_is_real=True, is_disc=True) + self.cri_gan(fake_d_pred, target_is_real=False, is_disc=True) ``` Why the `target_is_real` option differs for fake images at two stages? Thanks in advance!
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
pull-request
Mirrored from GitHub Pull Request
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
claunia
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: TencentARC/GFPGAN#120
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?