mmclassification/configs/t2t_vit

Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet

Introduction

@article{yuan2021tokens,
  title={Tokens-to-token vit: Training vision transformers from scratch on imagenet},
  author={Yuan, Li and Chen, Yunpeng and Wang, Tao and Yu, Weihao and Shi, Yujun and Tay, Francis EH and Feng, Jiashi and Yan, Shuicheng},
  journal={arXiv preprint arXiv:2101.11986},
  year={2021}
}

Pretrain model

The pre-trained modles are converted from official repo.

ImageNet-1k

Model	Params(M)	Flops(G)	Top-1 (%)	Top-5 (%)	Config	Download
T2T-ViT_t-14*	21.47	4.34	81.69	95.85	config	model | log
T2T-ViT_t-19*	39.08	7.80	82.43	96.08	config	model | log
T2T-ViT_t-24*	64.00	12.69	82.55	96.06	config	model | log

Models with * are converted from other repos.

Results and models

Waiting for adding.