Why the shape between pretrianed weights and config is different?

Open xiguadong opened this issue 4 years ago • 3 comments

the output info as belows: Use load_from_local loader The model and loaded state dict do not match exactly

size mismatch for keypoint_head.final_layer.weight: copying a param with shape torch.Size([16, 30, 1, 1]) from checkpoint, the shape in current model is torch.Size([16, 40, 1, 1]).

Aug 04 '21 08:08 xiguadong

I meet the same error, how you solve this ?

Sep 15 '21 02:09 wangjing60755

I meet the same error, how you solve this ?

Sep 15 '21 02:09 wangjing60755

Does anayone solve it?

Sep 02 '22 08:09 s94210252000