Filter Pruning Algorithm Based on Deep Reinforcement Learning

被引：0
|
作者：
Liu Y. [1 ]
Teng Y. [1 ]
Niu T. [1 ]
Zhi J. [1 ]
机构：
[1] School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing
来源：
Beijing Youdian Daxue Xuebao/Journal of Beijing University of Posts and Telecommunications | 2023年 / 46卷 / 03期
关键词：
deep learning model; deep reinforcement learning; edge computing; filter pruning;
D O I：
10.13190/j.jbupt.2022-140
中图分类号：
学科分类号：
摘要：
When the deep neural network model is deployed on the terminal device, it faces the problem of insufficient computing capabilities and storage resources. Model pruning provides an effective model compression method, which can reduce the number of parameters and reduce the computational complexity while ensuring the accuracy of the model. However, the traditional pruning methodsmostly rely on prior knowledge to set pruning rate and pruning standard. They ignore the pruning sensitivity and parameter distribution difference of different layers of deep model, and lack fine-grained optimization. To solve this problem, a filter pruning scheme based on reinforcement learning is proposed to minimize the precision loss of the model after pruning while satisfying the target sparsity. In the proposed scheme, the parameterized deep Q-networks algorithm is used to solve the constructed nonlinear optimization problem with mixed variables. Experimental results show that the proposed scheme can select suitable pruning standard and pruning rate for each layer, and reduce the precision loss of the model after pruning. © 2023 Beijing University of Posts and Telecommunications. All rights reserved.
引用
收藏
页码：31 / 36
页数：5
相关论文
共 9 条
  • [1] HE K M, ZHANG X Y, REN S Q, Et al., Deep residual learning for image recognition [ C], 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp. 770-778, (2016)
  • [2] HOWARD A, SANDLER M, CHU G, Et al., Searching for mobilenetV3 [ C ], 2019 IEEE / CVF International Conference on Computer Vision, pp. 1314-1324, (2019)
  • [3] HAN S, MAO H Z, DALLY W J., Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding, 2015 IEEE Conference on Computer Vision and Pattern Recognition, pp. 223-232, (2015)
  • [4] LIN M B, JI R R, WANG Y, Et al., Hrank: filter pruning using high-rank feature map [ C], 2020 IEEE / CVF Conference on Computer Vision and Pattern Recognition, pp. 1529-1538, (2020)
  • [5] CHENG J, WANG P S, LI G, Et al., Recent advances in efficient computation of deep convolutional neural networks, Frontiers of Information Technology & Electronic Engineering, 19, 1, pp. 64-77, (2018)
  • [6] LI H, KADAV A, SAMET H, Et al., Pruningfilters for effificientconvnets, 2017 International Conference on Learning Representations, pp. 323-330, (2017)
  • [7] HE Y, KANG G L, DONG X Y, Et al., Soft filter pruning for accelerating deep convolutional neural networks, International Joint Conference on Artificial Intelligence, 50, 9, pp. 2234-2240, (2018)
  • [8] HE Y, LIU P, WANG Z W, Et al., Filter pruning via geometric median for deep convolutional neural networks acceleration, 2019 IEEE / CVF Conference on Computer Vision and Pattern Recognition, pp. 4340-4349, (2019)
  • [9] ZHOU B L, KHOSLA A, OLIVA A, Et al., Learning deep features for discriminative localization [ C], 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921-2929, (2016)
1