ProDA
ProDA copied to clipboard
About the mIoU metric
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.
I'm really confused with the result, could you tell me how to get the correct mIoU about the pretrained model?
Maybe the version of PyTorch caused the unexpected result