From e1dcbb365e0c46503824cd37b3bedc002005fee2 Mon Sep 17 00:00:00 2001 From: Kai Han Date: Fri, 16 Sep 2022 22:25:09 +0800 Subject: [PATCH] Update readme.md --- vig_pytorch/readme.md | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/vig_pytorch/readme.md b/vig_pytorch/readme.md index 9fc1db5..ac09dd7 100644 --- a/vig_pytorch/readme.md +++ b/vig_pytorch/readme.md @@ -1,5 +1,5 @@ # Vision GNN -By Kai Han, Yunhe Wang, Jianyuan Guo, Yehui Tang and Enhua Wu. [[arXiv link]](https://arxiv.org/abs/2206.00272) +By Kai Han, Yunhe Wang, Jianyuan Guo, Yehui Tang and Enhua Wu. NeurIPS 2022. [[arXiv link]](https://arxiv.org/abs/2206.00272) ![image](../fig/vig.png) @@ -10,13 +10,15 @@ torchprofile 0.0.4, apex ## ViG Code -Paper: [Vision GNN: An Image is Worth Graph of Nodes](https://arxiv.org/abs/2206.00272) +NeurIPS 2022 Paper: [Vision GNN: An Image is Worth Graph of Nodes](https://arxiv.org/abs/2206.00272) - Training example for 8 GPUs: ``` python -m torch.distributed.launch --nproc_per_node=8 train.py /path/to/imagenet/ --model pvig_s_224_gelu --sched cosine --epochs 300 --opt adamw -j 8 --warmup-lr 1e-6 --mixup .8 --cutmix 1.0 --model-ema --model-ema-decay 0.99996 --aa rand-m9-mstd0.5-inc1 --color-jitter 0.4 --warmup-epochs 20 --opt-eps 1e-8 --repeated-aug --remode pixel --reprob 0.25 --amp --lr 2e-3 --weight-decay .05 --drop 0 --drop-path .1 -b 128 --output /path/to/save/models/ ``` +Data preparation follows the [official pytorch example](https://github.com/pytorch/examples/tree/main/imagenet) + - Pretrained models |Model|Params (M)|FLOPs (B)|Top-1|BaiduDisk URL|Github Release| @@ -33,12 +35,11 @@ python train.py /path/to/imagenet/ --model pvig_s_224_gelu -b 128 --pretrain_pat ## Citation ``` -@misc{vig, +@inproceedings{han2022vig, title={Vision GNN: An Image is Worth Graph of Nodes}, author={Kai Han and Yunhe Wang and Jianyuan Guo and Yehui Tang and Enhua Wu}, - year={2022}, - eprint={2206.00272}, - archivePrefix={arXiv} + booktitle={NeurIPS}, + year={2022} } ```