In both training and evaluation, we normalize color channelsby subtracting the average color and dividing by the standar deviation, computed on ImageNet, after applying the augmentations
Hi @lucidrains , could you make the normalization parameters a class parameter? I'll be using it on a different dataset. Would be nice to be able to just pip-install instead of forking and adjusting
Appendix B, page 13, bottom:
In both training and evaluation, we normalize color channelsby subtracting the average color and dividing by the standar deviation, computed on ImageNet, after applying the augmentations