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

how to start train cycleGAN with checkpoints? #275

Closed
Wanger-SJTU opened this issue May 18, 2018 · 2 comments
Closed

how to start train cycleGAN with checkpoints? #275

Wanger-SJTU opened this issue May 18, 2018 · 2 comments

Comments

@Wanger-SJTU
Copy link

I trained CycleGAN with my own dataset, but got interupted. and I have latest_net_D_A.pth , latest_net_D_B.pth latest_net_G_A.pth and latest_net_G_B.pth files in checkpoints/AtoB/ directory.
How could I restarted the training process, with the checkpoint files

@happsky
Copy link

happsky commented May 21, 2018

Try --continue_train.

@junyanz
Copy link
Owner

junyanz commented May 23, 2018

Also, use epoch_count. See this issue for more details.

@junyanz junyanz closed this as completed May 23, 2018
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

3 participants