Anyone here have trouble reaching the mentioned accuracy for ViT-B? #65
Description
Anyone here have trouble reaching the mentioned accuracy for ViT-B? For some reason, the best accuracy I can get is 77% top1 without KD. While in the paper they said they reach 81% top1 without KD and 84.4% top1 with KD. Anyone manage to get that accuracy? If so, can you tell me what hyperparameters did you use? Thanks!