haoyuying

if we want to train this model(hrnet32_ocr128) and achieve excellent result like yours, can we achieve this by run 'python3 train.py models/sbd/hrnet32_ocr128.py --gpus=0,1 --workers=4 --exp-name=first-try' without changing any hyper parameters?

segmentation

1

the program is broken when the program excutes "y_s,offset,filter = model(torch.stack((X0, X1),dim = 0))", I have pointed out align_corners "temps = [nn.Upsample(scale_factor=4, mode='bilinear',align_corners=False)(temp) for temp in temps]", however it does...

the program is broken when the program excutes "y_s,offset,filter = model(torch.stack((X0, X1),dim = 0))", I have pointed out align_corners "temps = [nn.Upsample(scale_factor=4, mode='bilinear',align_corners=False)(temp) for temp in temps]", however it does...