Haochen-Wang409 / U2PL

[CVPR'22 & IJCV'24] Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels & Using Unreliable Pseudo-Labels for Label-Efficient Semantic Segmentation
Apache License 2.0
437 stars 61 forks source link

hello ! Execuce I want train my model with one GPU ,how can I modefiy code #123

Closed yjq767579182 closed 1 year ago

Haochen-Wang409 commented 1 year ago

No modification is needed. Just run bash train.sh 1 <port>.

yjq767579182 commented 1 year ago

oh!Thanks very much! But I have another question, I want to ask about eval.py and infer.py. Will eval.py generate a visual evaluation index file, and will infer.py generate a visual segmentation file.I hope my little question didn't bother you, looking forward to your answer.

Haochen-Wang409 commented 1 year ago

infer.py will save segmentation maps and colorized maps. For details, see https://github.com/Haochen-Wang409/U2PL/blob/main/infer.py#L130-L134

yjq767579182 commented 1 year ago

Thanks a lot and all the best