search

Zhengxinyang / LAS-Diffusion

MIT License
225 stars 16 forks source link

which vit model is right #18

Closed 1910183821 closed 2 months ago

1910183821 commented 3 months ago

RuntimeError: Error(s) in loading state_dict for VisionTransformer: size mismatch for head.weight: copying a param with shape torch.Size([1000, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1280]). size mismatch for head.bias: copying a param with shape torch.Size([1000]) from checkpoint, the shape in current model is torch.Size([1024]).

CRISZJ commented 3 months ago

RuntimeError: Error(s) in loading state_dict for VisionTransformer: size mismatch for head.weight: copying a param with shape torch.Size([1000, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1280]). size mismatch for head.bias: copying a param with shape torch.Size([1000]) from checkpoint, the shape in current model is torch.Size([1024]).

have you solved the problem?

CRISZJ commented 3 months ago

I've used this https://huggingface.co/timm/vit_huge_patch14_clip_224.laion2b_ft_in1k/tree/main model. and it works!

1910183821 commented 2 months ago

I've used this https://huggingface.co/timm/vit_huge_patch14_clip_224.laion2b_ft_in1k/tree/main model. and it works! That's what I used to report the error