SHI-Labs / Self-Similarity-Grouping

Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification (ICCV 2019, Oral)
187 stars 43 forks source link

There might be a bug in line 195 of SSG-master/reid/trainers.py #28

Open LiangY1994 opened 4 years ago

LiangY1994 commented 4 years ago

To my understanding, should it be "loss += loss_tri" instead of "loss + loss_tri"?