snn's Introduction

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

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

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

Dataset

Following this repository,

Download the ImageNet dataset from http://www.image-net.org.
Then move validation images to labeled subfolders, using the following script.

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}
}