Research on Compression Optimization Algorithm for Super-resolution Reconstruction Network

Xiaodong Zhao, Yanfang Fu, Feng Tian, Xunying Zhang

科研成果: 书/报告/会议事项章节会议稿件同行评审

1 引用 (Scopus)

摘要

Under the condition of limited resources of embedded systems, the paper proposes a compression optimization algorithm based on pruning and quantization, so that the computational requirements of the super-resolution reconstruction algorithm based on a Convolutional Neural Network (CNN) can be met. First, a multiple regularization pruning optimization algorithm based on an attention module and a BatchNorm layer is proposed. Then, a coordination optimization algorithm of INT8 training and quantization for FPGA architecture is proposed. The performance of the pruning optimization algorithm was verified for the Super-Resolution CNN (SRCNN), the Fast Super-Resolution CNN (FSRCNN), and the Very Deep Super-resolution CNN (VDSRCNN). As for SRCNN, the performance of the quantization optimization algorithm was verified on the FPGA EC2 hardware simulation platform. The results show that the proposed compression optimization algorithm can achieve a good balance between network accuracy and inference speed.

源语言英语
主期刊名2022 9th International Forum on Electrical Engineering and Automation, IFEEA 2022
出版商Institute of Electrical and Electronics Engineers Inc.
1075-1079
页数5
ISBN(电子版)9781665464215
DOI
出版状态已出版 - 2022
活动9th International Forum on Electrical Engineering and Automation, IFEEA 2022 - Virtual, Online, 中国
期限: 4 11月 20226 11月 2022

出版系列

姓名2022 9th International Forum on Electrical Engineering and Automation, IFEEA 2022

会议

会议9th International Forum on Electrical Engineering and Automation, IFEEA 2022
国家/地区中国
Virtual, Online
时期4/11/226/11/22

指纹

探究 'Research on Compression Optimization Algorithm for Super-resolution Reconstruction Network' 的科研主题。它们共同构成独一无二的指纹。

引用此