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

"Tip-Adapter/main.py" use test features to eval #11

Open
fikry102 opened this issue Nov 15, 2022 · 3 comments
Open

"Tip-Adapter/main.py" use test features to eval #11

fikry102 opened this issue Nov 15, 2022 · 3 comments

Comments

@fikry102
Copy link

It seems odd to use test features to eval.
see

# Eval

Could authors give some explanation?

@ZrrSkywalker
Copy link
Collaborator

Thanks for your interest.
Here in line 111, we conduct inference on the test set after every epoch's training.

@waleedgondal
Copy link

I agree with @fikry102, best 'adapter' selection is done using test features. Shouldn't validation features be used for model selection?

@ZrrSkywalker
Copy link
Collaborator

@waleedgondal Thanks for pointing out. Sorry for this mistake. The model selection after every-epoch training should be rectified by using validation set. By our experiments, this would not affect the final performance on the test set.

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