Open qqwewewejekl opened 1 year ago
did you mean pretrain on imagenet and finetune on ade20k when you replace a new attention module?
Hi, @qqwewewejekl Yes. We set the same training protocol, hyperparameters, and model architecture configurations as Swin.
Thanks a lot.
did you mean pretrain on imagenet and finetune on ade20k when you replace a new attention module?