SimpleViT misleading summary

[asusdisciple]

First of all: Thanks for the awesome implementations of various Vision Transoformer models! It really helped a lot.

I personally had an issue with the summary of the SimpleViT, which implies that this implementation comes with MixUp and RandAugment. However this transforms are not in the code itself, maybe it should be noted that they have to be implemented by the user or you should leave away the paragraph right away to make it more clear and concise (since transforms dont have anything to do with the model structure anyways). Best regards