search

RyanWangZf / MedCLIP

EMNLP'22 | MedCLIP: Contrastive Learning from Unpaired Medical Images and Texts
394 stars 41 forks source link

1 update + 1 issue #2

Closed zzachw closed 1 year ago

zzachw commented 2 years ago
  1. Update:

Better sentence split in dataset.py, which handles decimal points

  1. Issue

It seems there is some issue with the soft clip loss. It seems similarity score of -1 is better than 0? However, the softmax is doing the opposite.