Skip to content

yikaiw/SNN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks

By Yikai Wang, Yi Yang, Fuchun Sun, Anbang Yao.

This pytorch implementation is a two-stage improved version of our paper "Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks", published in ICCV 2021.

Dataset

Following this repository,

Requirements:

  • python3, pytorch 1.4.0, torchvision 0.5.0

Training

(1) Step1: binarizing activations (or you can omit this step by using our Step1 model checkpoint_ba.pth.tar),

  • Change directory to ./step1,
  • Run the folowing script,
CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py --data=path/to/ILSVRC2012/  --batch_size=512 --learning_rate=1e-3 --epochs=256 --weight_decay=1e-5

(2) Step2: binarizing weights + activations,

  • Change directory to ./step2,
  • Create new folder ./models and copy checkpoint_ba.pth.tar (obtained from Step1) to ./models,
  • Run the folowing script,
CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py --data=path/to/ILSVRC2012/  --batch_size=512 --learning_rate=1e-3 --epochs=256 --weight_decay=0 --bit-num=5
  • Comment: --bit-num=5 corresponds to 0.56 bit (bit-num indicates tau in the paper).

Results

This implementation is based on ResNet-18 of ReActNet.

Bit-Width Top1-Acc Top5-Acc #Params Bit-OPs Model & Log
1W / 1A 65.7% 86.3% 10.99Mbit 1.677G Google Drive
0.67W / 1A 63.4% 84.5% 7.324Mbit 0.883G Google Drive
0.56W / 1A 62.1% 83.8% 6.103Mbit 0.501G Google Drive
0.44W / 1A 60.7% 82.7% 4.882Mbit 0.297G Google Drive

Citation

If you find our code useful for your research, please consider citing:

@inproceedings{wang2021snn,
    title={Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks},
    author={Wang, Yikai and Yang, Yi and Sun, Fuchun and Yao, Anbang},
    booktitle={International Conference on Computer Vision (ICCV)},
    year={2021}
}

License

SNN is released under MIT License.