A study of lightweighting method using reinforcement learning

Yoshihiro Harada; Noriko Yata; Yoshitsugu Manabe

doi:10.1117/12.2626090

30 April 2022 A study of lightweighting method using reinforcement learning

Yoshihiro Harada, Noriko Yata, Yoshitsugu Manabe

Proceedings Volume 12177, International Workshop on Advanced Imaging Technology (IWAIT) 2022; 121772M (2022) https://doi.org/10.1117/12.2626090
Event: International Workshop on Advanced Imaging Technology 2022 (IWAIT 2022), 2022, Hong Kong, China

Abstract

Deep neural networks (DNNs) are capable of achieving high performance in various tasks. However, the huge number of parameters and floating point operations make it difficult to deploy them on edge devices. Therefore, in recent years, a lot of researches have been done to reduce the weight of deep convolutional neural networks. Conventional research prunes based on a set of criteria, but we do not know if those criteria are optimal or not. In order to solve this problem, this paper proposes a method to select parameters for pruning automatically. Specifically, all parameter information is input, and reinforcement learning is used to select and prune parameters that do not affect the accuracy. Our method prunes one filter or node in one action and compresses it by repeating the action. The proposed method was able to highly compress the CNN with minimal degradation in accuracy and reduce about 97.0% of the parameters with 2.53% degradation in CIFAR10 image classification task on VGG16.

Citation Download Citation

Yoshihiro Harada, Noriko Yata, and Yoshitsugu Manabe "A study of lightweighting method using reinforcement learning", Proc. SPIE 12177, International Workshop on Advanced Imaging Technology (IWAIT) 2022, 121772M (30 April 2022); https://doi.org/10.1117/12.2626090

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available