Hardware-Friendly Progressive Pruning Framework for CNN Model Compression using Universal Pattern Sets

Wei-Cheng Chou, Cheng-Wei Huang,Juinn-Dar Huang

2022 International Symposium on VLSI Design, Automation and Test (VLSI-DAT)（2022）

引用 0|浏览0

暂无评分

摘要

Pattern-based weight pruning on CNNs has been proven an effective model reduction technique. In this paper, we first present how to select hardware-friendly pruning pattern sets that are universal to various models. We then propose a progressive pruning framework, which produces more globally optimized outcomes. Moreover, to the best of our knowledge, this is the first paper dealing with the pruni...

查看译文

关键词

Design automation,Computational modeling,Very large scale integration,Reduced order systems,Convolutional neural networks

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要