TencentARC/GFPGAN
1
0
Fork 0
mirror of https://github.com/TencentARC/GFPGAN.git synced 2026-02-04 08:14:41 +00:00
Code Issues 476 Packages Projects Releases 8 Wiki Activity

About the convergence curve of the training loss function #99

New Issue
Open
opened 2026-01-29 21:41:48 +00:00 by claunia · 0 comments
claunia commented 2026-01-29 21:41:48 +00:00
Owner
Copy Link

Originally created by @NNNNAI on GitHub (Nov 4, 2021).

Hi xintao.
I have try to retrain the gfpganv1, but I noticed that the loss function about gan fluctuated significantly in the early stages of training as shown shown in the red box below.Could you give me a copy of the tensorboard file when you trained gfpganv1 so that I can compare the difference between the model I trained and yours？Thanks for your attention, have a nice day!~
1635997159
1635997159(1)

Originally created by @NNNNAI on GitHub (Nov 4, 2021). Hi xintao. I have try to retrain the gfpganv1, but I noticed that the loss function about gan fluctuated significantly in the early stages of training as shown shown in the red box below.Could you give me a copy of the tensorboard file when you trained gfpganv1 so that I can compare the difference between the model I trained and yours？Thanks for your attention, have a nice day!~ ![1635997159](https://user-images.githubusercontent.com/30747212/140254120-4b7d3893-7682-4cef-b318-6f12289d89b1.jpg) ![1635997159(1)](https://user-images.githubusercontent.com/30747212/140254129-087fac94-8d5a-4629-a6d5-3ad8b94692e4.jpg)
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#99
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?