IoU for semantic segmentation implementation in python/caffe per class

Question

Is there any recommendable per class IoU(intersection over union) per pixel accuracy(different from bounding box) implementation.I am using caffe and managed to get the mean IoU but i am having difficulty in doing IoU for per class accuracy.I would appreciate a lot if someone could point out a good implementation in any language

Answer 1

so far this the only close semantic segmentation with multiple pixel label i ve seen so far here