pretrain encode checkpoint mismatch model

[ZipperDeng]

Hi, thank you very much for this gorgeous project! I am testing the performance of Encoder task, but i meet a problem when loading the Pretrained Encoder(MoDi_encoder_f7c850_079999.pt) following readme. the error is below:

        size mismatch for convs.3.convs.1.1.mask: copying a param with shape torch.Size([128, 64, 4, 10, 3]) from checkpoint, the shape in current model is torch.Size([128, 64, 5, 10, 3]).
        size mismatch for convs.3.convs.1.1.scale: copying a param with shape torch.Size([1, 1, 4, 1, 1]) from checkpoint, the shape in current model is torch.Size([1, 1, 5, 1, 1]).
        size mismatch for convs.3.convs.1.1.mask: copying a param with shape torch.Size([128, 64, 4, 10, 3]) from checkpoint, the shape in current model is torch.Size([128, 64, 5, 10, 3]).
        size mismatch for convs.3.convs.1.1.scale: copying a param with shape torch.Size([1, 1, 4, 1, 1]) from checkpoint, the shape in current model is torch.Size([1, 1, 5, 1, 1]).
        size mismatch for convs.3.skip.1.weight: copying a param with shape torch.Size([128, 64, 4, 10, 1]) from checkpoint, the shape in current model is torch.Size([128, 64, 5, 10, 1]).
        size mismatch for convs.3.skip.1.mask: copying a param with shape torch.Size([128, 64, 4, 10, 1]) from checkpoint, the shape in current model is torch.Size([128, 64, 5, 10, 1]).
        size mismatch for convs.3.skip.1.scale: copying a param with shape torch.Size([1, 1, 4, 1, 1]) from checkpoint, the shape in current model is torch.Size([1, 1, 5, 1, 1]).
        size mismatch for convs.4.convs.0.0.weight: copying a param with shape torch.Size([128, 128, 4, 4, 3]) from checkpoint, the shape in current model is torch.Size([128, 128, 5, 5, 3]).
        size mismatch for convs.4.convs.0.0.mask: copying a param with shape torch.Size([128, 128, 4, 4, 3]) from checkpoint, the shape in current model is torch.Size([128, 128, 5, 5, 3]).
        size mismatch for convs.4.convs.0.0.scale: copying a param with shape torch.Size([1, 1, 4, 1, 1]) from checkpoint, the shape in current model is torch.Size([1, 1, 5, 1, 1]).
        size mismatch for convs.4.convs.1.1.weight: copying a param with shape torch.Size([256, 128, 2, 4, 3]) from checkpoint, the shape in current model is torch.Size([256, 128, 4, 5, 3]).
        size mismatch for convs.4.convs.1.1.mask: copying a param with shape torch.Size([256, 128, 2, 4, 3]) from checkpoint, the shape in current model is torch.Size([256, 128, 4, 5, 3]).
        size mismatch for convs.4.convs.1.1.scale: copying a param with shape torch.Size([1, 1, 2, 1, 1]) from checkpoint, the shape in current model is torch.Size([1, 1, 4, 1, 1]).
        size mismatch for convs.4.skip.1.weight: copying a param with shape torch.Size([256, 128, 2, 4, 1]) from checkpoint, the shape in current model is torch.Size([256, 128, 4, 5, 1]).
        size mismatch for convs.4.skip.1.mask: copying a param with shape torch.Size([256, 128, 2, 4, 1]) from checkpoint, the shape in current model is torch.Size([256, 128, 4, 5, 1]).
        size mismatch for convs.4.skip.1.scale: copying a param with shape torch.Size([1, 1, 2, 1, 1]) from checkpoint, the shape in current model is torch.Size([1, 1, 4, 1, 1]).
        size mismatch for final_conv.0.weight: copying a param with shape torch.Size([256, 257, 2, 2, 3]) from checkpoint, the shape in current model is torch.Size([256, 257, 4, 4, 3]).
        size mismatch for final_conv.0.mask: copying a param with shape torch.Size([256, 257, 2, 2, 3]) from checkpoint, the shape in current model is torch.Size([256, 257, 4, 4, 3]).
        size mismatch for final_conv.0.scale: copying a param with shape torch.Size([1, 1, 2, 1, 1]) from checkpoint, the shape in current model is torch.Size([1, 1, 4, 1, 1]).
        size mismatch for final_linear.0.weight: copying a param with shape torch.Size([256, 2048]) from checkpoint, the shape in current model is torch.Size([256, 4096]).
        size mismatch for latent_predictor.linear1.weight: copying a param with shape torch.Size([7168, 4096]) from checkpoint, the shape in current model is torch.Size([7168, 5120]).

[sigal-raab]

Dear @ZipperDeng, Thank you for your interest in our project. I will be happy to help by the end of this month. Until then I am occupied with previous commitments. Can you bear that long?

[ZipperDeng]

Dear @ZipperDeng, Thank you for your interest in our project. I will be happy to help by the end of this month. Until then I am occupied with previous commitments. Can you bear that long?

@sigal-raab OK, thanks, I am looking forward to your reply when you are not busy.

[sigal-raab]

@ZipperDeng, apologies for the delay, this will take a bit longer, but we are on it!

[ZipperDeng]

@sigal-raab ,

thanks for your responsiblity that still remember my issue.

i found that the encoder example doesn't work with pretrained encode model from newest README https://drive.google.com/file/d/1AoyS3DCuqPNhlQfo7LkANa1TVqCLSM03/view，the error message is above.

but it works with encoder model trained by myself following train_encoder.py.

so I think there might be something wrong on pretrained encode model.

[sigal-raab]

I believe you are right. I hope to replace the trained encoder with a valid one as soon as possible.

[ZipperDeng]

thanks a lot,you are very welcome!

[sigal-raab]

We pushed a fix for this problem. If you still see any problems, please re-open this issue.