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.

Sign up for GitHub

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

Jump to bottom

Abour pre-trained network #2

Open
zinuok opened this issue Oct 25, 2021 · 0 comments
Open

Abour pre-trained network #2

zinuok opened this issue Oct 25, 2021 · 0 comments

Comments

@zinuok
Copy link

zinuok commented Oct 25, 2021 •
edited
Loading

Really thanks for your great works!
Currently, I'm trying to use your pre-trained network CelebA (64x64) for fine-tuning.
Regarding this, I have two questions about resuming from the pre-trained network.

  • Q1. Does the uploaded pre-trained pickle contain the best performance of your network for CelebA? Approximately how many epochs did it run?
  • Q2. Even if I have tried to resume from pre-trained network by using --resume [path to the pre-trained pickle file], it seems the network starts from the initial state of knowing nothing. Is there any other specific command for fine-tuning?
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@zinuok