History

Ma Zerun d1473e4a7f [Dependency] Update mmcv dependency version (#509 ) * Update mmcv dependency version * Add code info in some metafiles		2021-11-02 18:08:30 +08:00
..
README.md	[Docs] Fix missing checkpoints links in T2T-ViT.	2021-10-29 10:42:10 +08:00
metafile.yml	[Dependency] Update mmcv dependency version (#509 )	2021-11-02 18:08:30 +08:00
t2t-vit-t-14_8xb64_in1k.py	[Feature] Add Tokens-to-Token ViT backbone and converted checkpoints. (#467 )	2021-10-29 10:37:16 +08:00
t2t-vit-t-19_8xb64_in1k.py	[Feature] Add Tokens-to-Token ViT backbone and converted checkpoints. (#467 )	2021-10-29 10:37:16 +08:00
t2t-vit-t-24_8xb64_in1k.py	[Feature] Add Tokens-to-Token ViT backbone and converted checkpoints. (#467 )	2021-10-29 10:37:16 +08:00

README.md

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.