Convolutional Layers Acceleration By Exploring Optimal Filter Structures

Hsi Ling Chen, Jar Ferr Yang, Song An Mao

研究成果: Conference contribution

摘要

CNN models are becoming more and more mature, many of them adopt deeper structures to better accomplish the task objectives, such that the increased computational and storage burdens are unfavorable for the implementation in edge devices. In this paper, we propose an approach to optimize the filter structure by starting from the convolutional filter and finding their minimum structure. The reductions of the filters for the minimum structure in terms of space and channels, the number of model parameters and the computational complexity are effectively reduced. Since the current channel pruning method prunes the same channel for each convolutional layer, which easily leads to a trade-off between the pruning rate and accuracy loss. Instead we propose a new channel pruning approach to find the most suitable required channels for each filter to provide a more detailed pruning method. Experiments conducted on the classification CNN models, such as VGG16 and ResNet56, show that the proposed method can successfully reduce the computations of the models without losing much model accuracy effectively. The proposed method performs well in compressing the model and reducing the number of parameters required by the models for real applications.

原文English
主出版物標題RASSE 2022 - IEEE International Conference on Recent Advances in Systems Science and Engineering, Symposium Proceedings
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9781665494915
DOIs
出版狀態Published - 2022
事件2022 IEEE International Conference on Recent Advances in Systems Science and Engineering, RASSE 2022 - Tainan, Taiwan
持續時間: 2022 11月 72022 11月 10

出版系列

名字RASSE 2022 - IEEE International Conference on Recent Advances in Systems Science and Engineering, Symposium Proceedings

Conference

Conference2022 IEEE International Conference on Recent Advances in Systems Science and Engineering, RASSE 2022
國家/地區Taiwan
城市Tainan
期間22-11-0722-11-10

All Science Journal Classification (ASJC) codes

  • 人工智慧
  • 電腦網路與通信
  • 電腦科學應用
  • 資訊系統
  • 資訊系統與管理

指紋

深入研究「Convolutional Layers Acceleration By Exploring Optimal Filter Structures」主題。共同形成了獨特的指紋。

引用此