A Computing Kernel for Network Binarization on PyTorch
University of Electronic Science and Technology of China, Chengdu, China
arXiv:1911.04477 [cs.LG], (11 Nov 2019)
@misc{xi2019computing,
title={A Computing Kernel for Network Binarization on PyTorch},
author={Xianda Xu and Marco Pedersoli},
year={2019},
eprint={1911.04477},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
Deep Neural Networks have now achieved state-of-the-art results in a wide range of tasks including image classification, object detection and so on. However, they are both computation consuming and memory intensive, making them difficult to deploy on low-power devices. Network binarization is one of the existing effective techniques for model compression and acceleration, but there is no computing kernel yet to support it on PyTorch. In this paper we developed a computing kernel supporting 1-bit xnor and bitcount computation on PyTorch. Experimental results show that our kernel could accelerate the inference of the binarized neural network by 3 times in GPU and by 4.5 times in CPU compared with the control group.
November 17, 2019 by hgpu
