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

Possible bug ? #33

Open
fratopa opened this issue Jul 24, 2024 · 2 comments
Open

Possible bug ? #33

fratopa opened this issue Jul 24, 2024 · 2 comments

Comments

@fratopa
Copy link

fratopa commented Jul 24, 2024

Hi, I think I found a small typo (or maybe I just missed something). In the file:
https://github.com/Parskatt/DeDoDe/blob/0928debd09de6e814c90647a639a7219437bf49a/DeDoDe/matchers/dual_softmax_matcher.py

I notice that "DualSoftMaxMatcher" returns batch_inds, shouldn't it return inds?

@Parskatt
Copy link
Owner

I think the impl is correct. The mnn may return different nums per batch so we need the batch ids to identitfy which pair the match comes from. In practice we typically use batchsize 1, where it doesnt matter.

@fratopa
Copy link
Author

fratopa commented Jul 24, 2024

When matching an image pair batch_inds appears to contain only zeros in a tensor as long as the number of matches, while inds contains the indices of the original keypoints and their batch id. This seems what one might want to receive from a matcher.

I'll double check tomorrow, I am probably missing something

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