Closed Serge-weihao closed 5 years ago
May I ask what code did you change? It seems that you didn't set the ignore label in the loss function.
May I ask what code did you change? It seems that you didn't set the ignore label in the loss function.
ignore label is setted in your train.py, which is 255, and the problem seems to be caused by tensor type.
I replace 1-valid_mask with ~valid_mask, and the code for trainning cityscapes can run now.
And I want to know the mIoU of 69.57% is from val set or test set?
This result were trained on the training set and tested on the val set.
I got this error in ProbOhemCrossEntropy2d, when trainning on cityscapes.