RuntimeError: Error(s) in loading state_dict for Generator: size mismatch for pixelwise_flow_predictor.hourglass.encoder.down_blocks.0.conv.weight: copying a param with shape torch.Size([128, 44, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 84, 3, 3]).

[G-force78]

RuntimeError: Error(s) in loading state_dict for Generator:
size mismatch for pixelwise_flow_predictor.hourglass.encoder.down_blocks.0.conv.weight: copying a param with shape torch.Size([128, 44, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 84, 3, 3]).
size mismatch for pixelwise_flow_predictor.mask.weight: copying a param with shape torch.Size([11, 108, 7, 7]) from checkpoint, the shape in current model is torch.Size([21, 148, 7, 7]).
size mismatch for pixelwise_flow_predictor.mask.bias: copying a param with shape torch.Size([11]) from checkpoint, the shape in current model is torch.Size([21]).
size mismatch for pixelwise_flow_predictor.occlusion.weight: copying a param with shape torch.Size([1, 108, 7, 7]) from checkpoint, the shape in current model is torch.Size([1, 148, 7, 7]).

[hacker009-sudo]

@G-force78 , did you get any solution?

[G-force78]

@G-force78 , did you get any solution?

I think it was likely somethingh to do with my config file, but Ive had so many problems with it I cant quite remember at which stage and attempt the error occurred! Its beyond my skill level so I have given up on all of it.

[hacker009-sudo]

@G-force78 , Still not got the solution :(

[SatyaDewangan05]

Check which .pth file are you using, I was using ted-youtube384.pth and ted384.yaml then I was getting this error. When I used ted384.pth and ted384.yaml then there was no error.

Just check the checkpoint file and yaml file, they should be same.