Towards Real-Time DNN Inference on Mobile Platforms with Model Pruning and Compiler Optimization

Wei Niu; Pu Zhao; Zheng Zhan; Xue Lin; Yanzhi Wang; Bin Ren

Towards Real-Time DNN Inference on Mobile Platforms with Model Pruning and Compiler Optimization

Machine Learning 2020-04-24 v1 Computer Vision and Pattern Recognition Multimedia

Authors: Wei Niu , Pu Zhao , Zheng Zhan , Xue Lin , Yanzhi Wang , Bin Ren

Abstract

High-end mobile platforms rapidly serve as primary computing devices for a wide range of Deep Neural Network (DNN) applications. However, the constrained computation and storage resources on these devices still pose significant challenges for real-time DNN inference executions. To address this problem, we propose a set of hardware-friendly structured model pruning and compiler optimization techniques to accelerate DNN executions on mobile devices. This demo shows that these optimizations can enable real-time mobile execution of multiple DNN applications, including style transfer, DNN coloring and super resolution.

Keywords

deep neural network acceleration deep neural network model compression

Cite

@article{arxiv.2004.11250,
  title  = {Towards Real-Time DNN Inference on Mobile Platforms with Model Pruning and Compiler Optimization},
  author = {Wei Niu and Pu Zhao and Zheng Zhan and Xue Lin and Yanzhi Wang and Bin Ren},
  journal= {arXiv preprint arXiv:2004.11250},
  year   = {2020}
}

Comments

accepted by the IJCAI-PRICAI 2020 Demonstrations Track

Towards Real-Time DNN Inference on Mobile Platforms with Model Pruning and Compiler Optimization

Abstract

Keywords

Cite

Comments

Related papers