Vim
Vim copied to clipboard
What I need to tweak VIm's code if my input Images' resolution is 512*512 not 224.
RuntimeError: Error(s) in loading state_dict for VisionMamba: size mismatch for pos_embed: copying a param with shape torch.Size([1, 197, 768]) from checkpoint, the shape in current model is torch.Size([1, 1025, 768]). If I need to retrain the weight for vim_base?