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

Overriden value of alpha is being used where? #8

Open
Saranga7 opened this issue Sep 11, 2024 · 0 comments
Open

Overriden value of alpha is being used where? #8

Saranga7 opened this issue Sep 11, 2024 · 0 comments

Comments

@Saranga7
Copy link

In the code prompt provided in the README:

python train.py k=100 generator=stylegan2 generator.feature_layer=conv1 hparams.batch_size=8 generator.class_name=ffhq model=nonlinear model.alpha=1

I am confused as to where is this model.alpha being used as you define:

model: torch.nn.Module = instantiate(cfg.model, k=cfg.k).to(device)

Is instantiate responsible for overriding the value of alpha? Otherwise the default value of alpha = 0.1 is used for all runs despite the user setting a different alpha.

PS : I'm new to Hydra, I apologize in advance if this is a dumb question

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

1 participant