The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919
the weight download from 'hrnet48_imagenet' and 'hrnet48_cityscapes' have the same name（hrnetv2_w48_imagenet_pretrained.pth）.
so, whether they are two different files but have the same name?
thank you!
the weight download from 'hrnet48_imagenet' and 'hrnet48_cityscapes' have the same name（hrnetv2_w48_imagenet_pretrained.pth）. so, whether they are two different files but have the same name? thank you!