MPL-pytorch icon indicating copy to clipboard operation
MPL-pytorch copied to clipboard

Why do we expand labels?

Open conorturner opened this issue 3 years ago • 0 comments

https://github.com/kekmodel/MPL-pytorch/blob/7fb5b40cd53179bf4c09ef0f916815c3272d3e9d/data.py#L138

Hey all,

I've been working my way through this implementation and cannot work out why the expand labels options exists? It seems that even if the labels aren't expanded the data loader will loop anyway.

Can anyone explain why this is needed?

conorturner avatar Sep 22 '22 11:09 conorturner