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
Why don't the track queries get updated for two_stage? #61
Comments
TrackFormer is not implemented to work with the two-stage approach of Deformable DETR. In my opinion, the two-stage approach is a step back from the end-to-end unified solution of DETR. Hence, we never tried to combine two-stage with our track query approach. |
Ah ok. I see. Thanks for the quick response! Following up with another question, does TrackFormer work with num_feature_levels greater than 1. It makes sense why you chose 1 feature level however I would like to try more feature levels. Although I could run MultiScaleDeformableAttention with multiple feature levels on Trackformer, I noticed the MultiScaleDeformableAttention package was differenent from the Deformable DETR paper. Is it ok to use your MultiScaleDeformableAttention package for multiple feature levels or should I revert back to the Deformable DETR's MultiScaleDeformableAttention package. |
TrackFormer already works with multiple feature levels. All our trainings/evaluations (except the MOTS20 models) run the The underlying MultiScaleDeformableAttention backend should not make a big difference. |
Great! Thanks a lot! |
trackformer/src/trackformer/models/deformable_transformer.py
Lines 180 to 230 in d62d810
I am confused why the track queries don't get updated for the two-stage.
Also, nice work by the way!
The text was updated successfully, but these errors were encountered: