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

Problem of retrieving a saved model of natural variation #1

Closed
themanchangechina opened this issue Dec 14, 2020 · 2 comments
Closed

Comments

@themanchangechina
Copy link

themanchangechina commented Dec 14, 2020

Excuse me, I download a pre-trained models of natural variation(svhn-brightness.pt) from your library, it is a .pt file.
I want to know how to write the command G = MUNITModelOfNatVar(args.model_path, reverse=False).cuda() to get the model?
I see G = MUNITModelOfNatVar(fname, reverse=reverse, args=args).cuda() in the load.py, how should I add the args?

@arobey1
Copy link
Owner

arobey1 commented Dec 14, 2020

See commit f49bd05

You can now use

G = MUNITModelOfNatVar(fname, reverse=reverse, config=config)

where config is a path pointing to the .yaml configuration file for MUNIT. The relevant file for svhn-brightness.pt should be ./core/models/munit/munit.yaml

@themanchangechina
Copy link
Author

OK, thanks~

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

2 participants