lightly-ai/lightly

Add multi-modal loss

Open

#264 opened on 2021年3月29日

GitHub で見る
 (5 comments) (0 reactions) (0 assignees)Python (337 forks)auto 404
featuregood first issue

Repository metrics

Stars
 (3,775 stars)
PR merge metrics
 (PR metrics pending)

説明

Add multi-modal loss

As discussed in #249, adding the loss function as described in CLIP would enable users to work with multi-modal datasets.

The pseudo-code (from the paper) is: grafik

コントリビューターガイド