Giters

Alibaba-MIIL / ImageNet21K

Official Pytorch Implementation of: "ImageNet-21K Pretraining for the Masses"(NeurIPS, 2021) paper

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Anyone here have trouble reaching the mentioned accuracy for ViT-B?

Phuoc-Hoan-Le opened this issue · comments

commented

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!