search

Haochen-Wang409 / U2PL

[CVPR'22] Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels
Apache License 2.0
426 stars 59 forks source link

Contrastive loss is 0 #142

Closed tanveer6715 closed 1 year ago

tanveer6715 commented 1 year ago

Hi, Thanks for your great work. I have implemented U2PL method on my own dataset which have only 2 classes. I have attached my config file and training log . It can be seen that during all iteration the contrastive loss is 0 throughout training. Is it normal?

config.txt seg_20230902_171430.txt

tanveer6715 commented 1 year ago

I am closing this issue as I used 3 as low rank which is quite high for 2 classes.