omihub777 / ViT-CIFARLinks

PyTorch implementation for Vision Transformer[Dosovitskiy, A.(ICLR'21)] modified to obtain over 90% accuracy FROM SCRATCH on CIFAR-10 with small number of parameters (= 6.3M, originally ViT-B has 86M).
194Updated last year

Alternatives and similar repositories for ViT-CIFAR

Users that are interested in ViT-CIFAR are comparing it to the libraries listed below

Sorting: