RVT: Robust Vision Transformers
This repository contains PyTorch code for Robust Vision Transformers.
For details see Rethinking the Design Principles of Robust Vision Transformer by Xiaofeng Mao, Gege Qi, Yuefeng Chen, Yuan He and Hui Xue.
Usage
First, clone the repository locally:
git clone https://github.com/vtddggg/Robust-Vision-Transformer.git
Then, install PyTorch 1.7.0+ and torchvision 0.8.1+ and pytorch-image-models 0.3.2:
conda install -c pytorch pytorch torchvision
pip install timm==0.3.2
We use 4 nodes with 8 gpus to train RVT-Ti, RVT-S and RVT-B:
Training RVT-Ti
python -m torch.distributed.launch --nproc_per_node=8 --nnodes=4 main.py --model rvt_tiny --data-path /path/to/imagenet --output_dir output --dist-eval
Training RVT-S
python -m torch.distributed.launch --nproc_per_node=8 --nnodes=4 main.py --model rvt_small --data-path /path/to/imagenet --output_dir output --dist-eval
Training RVT-B
python -m torch.distributed.launch --nproc_per_node=8 --nnodes=4 main.py --model rvt_base --data-path /path/to/imagenet --output_dir output --batch-size 32 --dist-eval
If you want to train RVT-Ti*, RVT-S* or RVT-B*, simply add --use_mask and --use_patch_aug to enable positon-aware attention scaling and patch-wise augmentation.
[email protected]">
19 Dec 13, 2022
39 Oct 08, 2022
41 May 18, 2022
477 Jan 06, 2023
12 Oct 25, 2021
58 Dec 21, 2022
272 Dec 20, 2022
268 Jan 09, 2023
6k Jan 02, 2023
348 Dec 23, 2022
105 May 15, 2022
184 Jan 03, 2023
47 Nov 26, 2022
9 Jun 17, 2022
9 May 22, 2022
2 Sep 21, 2022
172 Dec 19, 2022
205 Dec 29, 2022
298 Dec 10, 2022
51 Dec 22, 2022