transformers
d447c460 - Speed up TF token classification postprocessing by converting complete tensors to numpy (#19976)

Commit

3 years ago

Speed up TF token classification postprocessing by converting complete tensors to numpy (#19976) * Speed up TF postprocessing by converting to numpy before * Fix bug that was triggered when offset_mapping was None Co-authored-by: Patrick Deutschmann <patrick.deutschmann@dedalus.com>

References

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

#19976 - Speed up TF token classification postprocessing by converting complete tensors to numpy

#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

#62 - Add initial DEIMv2 model implementation

#65 - Fix RTDetrV2 sine position embedding ordering