Variational Channel Distribution Pruning and Mixed-Precision Quantization for Neural Network Model Compression

Wan Ting Chang, Chih Hung Kuo, Li Chun Fang

研究成果: Conference contribution

1 引文 斯高帕斯(Scopus)

摘要

This paper presents a model compression frame-work for both pruning and quantizing according to the channel distribution information. We apply the variational inference technique to train a Bayesian deep neural network, in which the parameters are modeled by probability distributions. According to the characteristic of the probability distribution, we can prune the redundant channels and determine the bit-width layer by layer. The experiments conducted on the CIFAR10 dataset with the VGG16 show that the number of parameters can be saved by 58.91x. The proposed compression approach can help implement hardware circuits for efficient edge and mobile computing.

原文English
主出版物標題2022 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2022 - Proceedings
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9781665409216
DOIs
出版狀態Published - 2022
事件2022 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2022 - Hsinchu, Taiwan
持續時間: 2022 4月 182022 4月 21

出版系列

名字2022 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2022 - Proceedings

Conference

Conference2022 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2022
國家/地區Taiwan
城市Hsinchu
期間22-04-1822-04-21

All Science Journal Classification (ASJC) codes

  • 硬體和架構
  • 電氣與電子工程
  • 安全、風險、可靠性和品質

指紋

深入研究「Variational Channel Distribution Pruning and Mixed-Precision Quantization for Neural Network Model Compression」主題。共同形成了獨特的指紋。

引用此