Pytorch implementation of TokenMix (ECCV 2022)
This repo is the offcial implementation of the paper TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers
@article{UniNet,
author = {Jihao Liu, Boxiao Liu, Hang Zhou, Yu Liu, Hongsheng Li},
journal = {arXiv:2207.08409},
title = {TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers},
year = {2022},
}
8/9/2022 Update the source code.
Following TokenLabeling to prepare ImageNet data and label maps generated with NFNet-F6.
The code is tested with torch==1.11 and timm==0.5.4.
Currently, we supporting running experiments with slurm. You can reproduce the results of Deit-small as follows:
sh exp/deit_small/run.sh partition
| Model | epochs | Top-1 Acc. | Ckpt |
|---|---|---|---|
| Deit-tiny | 300 | 73.2 | - |
| Deit-small | 300 | 80.8 | - |
| Deit-base | 300 | 82.9 | - |
