By Qing-Long Zhang and Yu-Bin Yang
[State Key Laboratory for Novel Software Technology at Nanjing University]
This repo is the official implementation of "SA-Net: Shuffle Attention for Deep Convolutional Neural Networks".
Figure 1: The Diagram of a shuffle attention module.
We provide baseline sa_resnet models pretrained on ImageNet-1k.
| name | acc@1 | #params (M) | url |
|---|---|---|---|
| sa_resnet50 | 77.88 | 25.56 | BaiduDrive(474p) |
| sa_resnet101 | 78.95 | 44.55 | BaiduDrive(6nxm) |
To evaluate a pre-trained sa_resnet50 on ImageNet val with a single GPU run:
python main.py -a sa_resnet50 -e --resume /path/to/sa_resnet50.pth.tar /path/to/imagenet
This should give
* Acc@1 77.882 Acc@5 93.892
@article{zhql2021sanet,
title={SA-Net: Shuffle Attention for Deep Convolutional Neural Networks},
author={Zhang, Qinglong and Yang, Yubin},
journal={arXiv preprint arXiv:2102.00240},
year={2021}
}