HRNet / HRNet-Semantic-Segmentation

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

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Unable to achieve the result on the README...

lzy-learning opened this issue · comments

I train the model HRNet-W48+OCR with the configuration seg_hrnet_ocr_w48_473x473_sgd_lr7e-3_wd5e-4_bs_40_epoch150, but finally only get 52% mIoU on the dataset LIP. How to deal with it? Or are there any train tips not mentioned in README?