Jeya Maria Jose

I believe this has something to do with the input type (3 channel or 1 channel) option. Can you please post the command line you used in terminal?

I did not use the postprocess.py; It was from the UNET++ code base upon which this code is built on.

The embedding dimension is 768 while tokenizing. Please refer this line: https://github.com/jeya-maria-jose/UNeXt-pytorch/blob/6ad0855114a35afbf81decf5dc912cd8de70476a/archs.py#L163

Yes, deep supervision part was not used in UNeXt training.