Got error in videopose.py. size mismatch for conv_out.bias
kathanvyas opened this issue · 1 comments
running in vscode with a conda enviornment that is setup with all dependencies. I have followed instructions as mentioned in readme.md. Downloaded all weights and requirements. I changed the directory for video file and have changed nothing else. can someone help me with this? I am not training anything. just planning to get 3D pose out of a video (so testing)
So this is the error i am getting:
self.class.name, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for FastPose:
size mismatch for conv_out.weight: copying a param with shape torch.Size([33, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([17, 128, 3, 3]).
size mismatch for conv_out.bias: copying a param with shape torch.Size([33]) from checkpoint, the shape in current model
is torch.Size([17]).
Please show the complete Runtime Error stack.
From the message you provided, the bug is the mismatch between the needed weight shape and the actual weight shape from the downloaded checkpoint. It may be caused by the PyTorch version. Updating/downgrading the version to 1.0 may help.