Improve DETR models (#19644)

Commit

3 years ago

Improve DETR models (#19644) * Improve DETR models * Fix Deformable DETR loss and matcher * Fixup * Fix integration tests * Improve variable names * Apply suggestion * Fix copies * Fix DeformableDetrLoss * Make Conditional DETR copy from Deformable DETR * Copy from deformable detr's hungarian matcher * Fix bug

References

#19449 - [WIP] Fix weights initialization of several vision models

#19644 - Improve DETR models

#27720 - Add common processor tests

#29969 - [SigLIP] Add fast tokenizer

#32831 - [Docs] Update resources

#33111 - [Backbone] Remove out_features everywhere

#33174 - [Zero-shot image classification pipeline] Remove tokenizer_kwargs

#39821 - Support MetaCLIP 2

#59 - Fix attention mask handling in EoMT-DINOv3 converter

#41212 - Add EoMT with DINOv3 backbone

#62 - Add initial DEIMv2 model implementation

Author

NielsRogge

Parents

072dfdae

transformers 90071fe4 - Improve DETR models (#19644)

transformers
90071fe4 - Improve DETR models (#19644)