segmentation_models.pytorch Mix ViT in

Mix ViT in_channels restriction

Open chrislfathom opened this issue 1 year ago • 2 comments

What's the reasoning behind limiting the Mix Visual Transformer encoder #632 to 3 input channels?

https://github.com/qubvel/segmentation_models.pytorch/blob/master/segmentation_models_pytorch/encoders/mix_transformer.py#L468

I couldn't spot anything in the paper or the original SegFormer implementation.

Oct 23 '23 15:10 chrislfathom

This issue is stale because it has been open 60 days with no activity. Remove stale label or comment or this will be closed in 7 days.

Dec 23 '23 01:12 github-actions[bot]

I've removed the restriction and the model appears to learn. Is there any argument for this restriction?

Dec 23 '23 08:12 lucasc896

This issue is stale because it has been open 60 days with no activity. Remove stale label or comment or this will be closed in 7 days.

Feb 23 '24 01:02 github-actions[bot]

This issue was closed because it has been stalled for 7 days with no activity.

Mar 01 '24 01:03 github-actions[bot]