google-research / big_vision

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.
Apache License 2.0
2.04k stars 140 forks source link

SigLIP and canonicalize #78

Open shkarupa-alex opened 7 months ago

shkarupa-alex commented 7 months ago

Сould you please clarify if canonicalization had been used during SigLIP training?

This demo https://github.com/google-research/big_vision/blob/main/big_vision/configs/proj/image_text/SigLIP_demo.ipynb does not use canonicalization.

But canonicalization used in this script https://github.com/google-research/big_vision/blob/main/big_vision/evaluators/proj/image_text/prompt_engineering.py