in_channels parameter change causes size mismatch

[mparigi]

When changing the kwarg (in_channels) from 3 to 2, like

torch.hub.load('mateuszbuda/brain-segmentation-pytorch', 'unet',
    in_channels=2, out_channels=1, init_features=32, pretrained=True)

this error occurs:

...module.py", line 1044, in load_state_dict
    raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for UNet:
        size mismatch for encoder1.enc1conv1.weight: copying a param with shape torch.Size([32, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 2, 3, 3]).

[mateuszbuda]

Hi, this is correct, the model was trained on 3-channel input images. Trained weights can only be loaded for a model initialized with in_channels=3.

[coconutattitude]

Hi, how did you make this 3 channel images?

[mateuszbuda]

Image channels correspond to 3 MRI sequences: pre-contrast, FLAIR, and post-contrast. More detail in the paper: https://arxiv.org/abs/1906.03720

[coconutattitude]

I see you have some matlab functions for preprocessing. Are there any written for python?

[mateuszbuda]

All preprocessing steps are implemented in python in this repo.