train-DeepLab
train-DeepLab copied to clipboard
Pascal VOC mIOU should ignore `void` labels
Hello,
At training, the void label in Pascal VOC is mapped to the background class 0. However, for evaluation purposes, it would make sense to ignore pixels corresponding void pixels in the ground-truth, as this is standard for Pascal VOC evaluation. If I'm not mistaken, this step was not done here. I opened a similar issue on this tensorflow implementation.
@bermanmaxim I really find this problem. How do you update the mIOU code?
You can just zero the prediction mask at the locations where the void pixels are before computing the mIoU.