Skip to content

About the inference speed of using FullGrad for cam visualization #553

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

Open
kasteric opened this issue Feb 5, 2025 · 1 comment
Open

Comments

@kasteric
Copy link

kasteric commented Feb 5, 2025

I was using FullGrad for cam visualization and found that it was much slower compared with ScoreCAM or GradCAM, and when using FullGrad for visualizations, there were warnings like Warning: target_layers is ignored in FullGrad. All bias layers will be used instead. Was it normal that using FullGrad was slow because it considered all layers? Or did I wrongly use the FullGrad?

@jacobgil
Copy link
Owner

Yes exactly, it is slower because it considered all layers.

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