EMNAPE: efficient multi-dimensional neural architecture pruning for EdgeAI

• Main Authors: Kong, Hao, Luo, Xiangzhong, Huai, Shuo, Liu, Di, Subramaniam, Ravi, Makaya, Christian, Lin, Qian, Liu, Weichen
• 其他作者: School of Computer Science and Engineering
• 格式: Conference or Workshop Item
• 語言: English
• 出版: 2023
• 主題: Engineering::Computer science and engineering; Heuristic Algorithms; Computational Modeling
• 在線閱讀: https://hdl.handle.net/10356/167488
• 機構: Nanyang Technological University

In this paper, we propose a multi-dimensional pruning framework, EMNAPE, to jointly prune the three dimensions (depth, width, and resolution) of convolutional neural networks (CNNs) for better execution efficiency on embedded hardware. In EMNAPE, we introduce a two-stage evaluation strategy to evalu...