Unable to achieve the result on the README...
lzy-learning opened this issue · comments
lzy-learning commented
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?