lightly-ai/lightly

Add multi-modal loss

開放

#264 建立於 2021年3月29日

 (5 則留言) (0 個反應) (0 位負責人)Python (337 個分叉)auto 404
featuregood first issue

倉庫指標

星標
 (3,775 顆星)
PR 合併指標
 (平均合併 8天) (30 天內合併 34 個 PR)

描述

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

貢獻者指南