lightly-ai/lightly

Add multi-modal loss

开放

#264 创建于 2021年3月29日

 (5 条评论) (0 个反应) (0 位负责人)Python (337 个派生)auto 404
featuregood first issue

仓库指标

星标
 (3,775 个星标)
PR 合并指标
 (平均合并 8天) (30 天内合并 34 个 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

贡献者指南