HRNet-Semantic-Segmentation
HRNet-Semantic-Segmentation copied to clipboard
conf_mat calculation by GPU
the original conf_mat calculation method costs too much when transfer data back to cpu. And this makes v100 falls into some kind of stall, when GPU Mem is used more than 20GB. I added the the conf_mat calculation method by torch api using GPU. This imporves the efficiency in each testing or validating. Hope you can merge this into your official repo.