waner1998

Thank you for your wonderful work, However, I print the parameters of the net from your code, and compare the parameter from the paper of page 8, its much more...

I use crossformer++ on cifar10(32*32) and cifar100(32) and tiny-imagenet(64*64), however, the acc drop to 1/num_classes after about 8 epoches. 

Questions about FEDER

2

Hi. In FEDER, there is a loss about the edge ( loss_edge = dice_loss(preds[6], edges)*0.125 + dice_loss(preds[7], edges)*0.25 + dice_loss(preds[8], edges)*0.5 ). However, not all datasets contain data about edge...

wrong checkpoint

2

Thank you for your wonderful work. 'Encoder. SAM2-UNet applys the Hiera [38] backbone pretrained by SAM2.' However, I download the checkpoint from 'https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_large.pt' in 'https://github.com/facebookresearch/sam2/tree/main/checkpoints', but failed to init the...