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

Can’t replicate the relation between feature norm and image quality #156

Open
QiqLiang opened this issue Aug 16, 2024 · 0 comments
Open

Comments

@QiqLiang
Copy link

Hi, I used your model r50 and r101 to show the feature norm of the images of my own datasets, but i didn’t see any law between feature norm and image quality, why does it happen? Is it because my dataset and your training set are in different domains that causes domain gap?

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