google-deepmind / google-deepmind/magiclens

why use AttenTokenPoolingLayer at the end of the model?

Open
#7 2 comments 0 reactions 0 assignees View on GitHub
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

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.