Spikformer: When Spiking Neural Network Meets Transformer, ICLR 2023
Reference
If you find this repo useful, please consider citing:
@inproceedings{
zhou2023spikformer,
title={Spikformer: When Spiking Neural Network Meets Transformer },
author={Zhaokun Zhou and Yuesheng Zhu and Chao He and Yaowei Wang and Shuicheng YAN and Yonghong Tian and Li Yuan},
booktitle={The Eleventh International Conference on Learning Representations },
year={2023},
url={https://openreview.net/forum?id=frE4fUwz_h}
}
Our codes are based on the official imagenet example by PyTorch, pytorch-image-models by Ross Wightman and SpikingJelly by Wei Fang.
Requirements
timm==0.5.4
cupy==10.3.1
pytorch==1.10.0+cu111
spikingjelly==0.0.0.0.12
pyyaml
data prepare: ImageNet with the following folder structure, you can extract imagenet by this script.
βimagenet/
βββtrain/
β βββ n01440764
β β βββ n01440764_10026.JPEG
β β βββ n01440764_10027.JPEG
β β βββ ......
β βββ ......
βββval/
β βββ n01440764
β β βββ ILSVRC2012_val_00000293.JPEG
β β βββ ILSVRC2012_val_00002138.JPEG
β β βββ ......
β βββ ......
Training on ImageNet
Setting hyper-parameters in imagenet.yml
cd imagenet
python -m torch.distributed.launch --nproc_per_node=8 train.py
Testing ImageNet Val data
cd imagenet
python test.py
Training on cifar10
Setting hyper-parameters in cifar10.yml
cd cifar10
python train.py
Training on cifar10DVS
cd cifar10dvs
python train.py