up-detr
up-detr copied to clipboard
Evaluation problem
I have the opposite situation.
RuntimeError: Error(s) in loading state_dict for UPDETR: size mismatch for class_embed.weight: copying a param with shape torch.Size([3, 256]) from checkpoint, the shape in current model is torch.Size([92, 256]). size mismatch for class_embed.bias: copying a param with shape torch.Size([3]) from checkpoint, the shape in current model is torch.Size([92]).
How to fix it?
Originally posted by @liuchengying758650786 in https://github.com/dddzg/up-detr/issues/13#issuecomment-2011164443