while freeze the stylegan? #10

Closed
opened 2026-01-29 21:36:27 +00:00 by claunia · 1 comment
Owner

Originally created by @zhangyunming on GitHub (Jun 23, 2021).

hi nice work !

one question: why set fix_decoder: true. will fintune the param have a better result?

Originally created by @zhangyunming on GitHub (Jun 23, 2021). hi nice work ! one question: why set fix_decoder: true. will fintune the param have a better result?
Author
Owner

@xinntao commented on GitHub (Jun 23, 2021):

As this work focuses on using the pre-trained StyleGAN, so we freeze it.
We can also finetune it (may with a smaller learning rate). It probably improves a bit.

@xinntao commented on GitHub (Jun 23, 2021): As this work focuses on using the pre-trained StyleGAN, so we freeze it. We can also finetune it (may with a smaller learning rate). It probably improves a bit.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: TencentARC/GFPGAN#10