You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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.
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
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?
The text was updated successfully, but these errors were encountered: