search

microsoft / ProDA

Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation (CVPR 2021)
https://arxiv.org/abs/2101.10979
MIT License
286 stars 44 forks source link

About the mIoU metric #45

Open JunXieFront opened 2 years ago

JunXieFront commented 2 years ago

The warmup pretrained model was supposed to be 43.3 mIoU, but when I test on cityscapes valid dataset, I've got a really lower one.I'm using the runningSocre class in your Repo and my metric function with the same result. image I'm really confused with the result, could you tell me how to get the correct mIoU about the pretrained model?

JunXieFront commented 2 years ago

Maybe the version of PyTorch caused the unexpected result