google-deepmind / google-deepmind/magiclens
why use AttenTokenPoolingLayer at the end of the model?
Open
- Dominant language
- Python
- Stars
- 211
- Forks
- 15
- PR merge metrics
- No merged PRs in 30d
Description
hi why use a query token at the end of model to learn about the embedding? have try to add the beginning of the multimodal_encoder? or just simply to use average-pooling operation?
thanks.
Contributor guide
Assessment
This issue has not been assessed yet.