Tweeted By @ajmooch
Normalizer-Free ResNets: Our ICLR2021 paper w/ @sohamde_& @SamuelMLSmith
— Andy Brock (@ajmooch) January 22, 2021
We show how to train deep ResNets w/o *any* normalization to ImageNet test accuracies competitive with ResNets, and EfficientNets at a range of FLOP budgets, while training faster.https://t.co/2WMhCkaxJh pic.twitter.com/nwF7lT25BK