model.load_state_dict(sam_checkpoint, strict=False)

[xiaozhen228]

RuntimeError: Error(s) in loading state_dict for SAM: size mismatch for image_encoder.pos_embed: copying a param with shape torch.Size([1, 64, 64, 1024]) from checkpoint, the shape in current model is torch.Size([1, 64, 64, 1280]).

Why I have such problem when I plan to load the weights? May be the code has some problems?

[Jack-bo1220]

same question

[tianrun-chen]

Have you use the original implementation or have you changed the input size?

[Jack-bo1220]

I have identified the potential cause of this error: using mismatched parameters and pre training models (such as using vit-l parameters and calling vit-h pretraining model). I have resolved it, thank you for your reply.