microsoft / CvT

This is an official implementation of CvT: Introducing Convolutions to Vision Transformers.
MIT License
533 stars 120 forks source link

Question about the class token #15

Open Andy1621 opened 2 years ago

Andy1621 commented 2 years ago

Good job! My question is that why to use different class tokens for each stage but only the final class token is used for classification? https://github.com/microsoft/CvT/blob/34d1af94c95442b19fb9470e0c9dd5ee11be2024/lib/models/cls_cvt.py#L607