A Channel Pruning Optimization With Layer-Wise Sensitivity in a Single-Shot Manner Under Computational Constraints
Open Access
- 27 December 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 7043-7055
Abstract
In the constrained computing environments such as mobile device or satellite on-board system, various computational factors of hardware resource can restrict the processing of deep learning (DL) services. Recent DL models such as satellite image analysis mainly require larger resource memory occupation for intermediate feature map footprint than the given memory specification of hardware resource and larger computational overhead (in FLOP) to meet service-level objective in the sense of hardware accelerator. As one of the solutions, we propose a new method of controlling the layer-wise channel pruning in a single-shot manner that can decide how much channels to prune in each layer by observing dataset once without full pretraining. To improve the robustness of the performance degradation, we also propose a layer-wise sensitivity and formulate the optimization problems for deciding layer-wise pruning ratio under target computational constraints. In the paper, the optimal conditions are theoretically derived, and the practical optimum searching schemes are proposed using the optimal conditions. On the empirical evaluation, the proposed methods show robustness on performance degradation, and present feasibility on DL serving under constrained computing environments by reducing memory occupation, providing acceleration effect and throughput improvement while keeping the accuracy performance.Keywords
Funding Information
- Challengeable Future Defense Technology Research and Development Program of Agency for Defense Development, in 2022 (915027201)
- Samsung Electronics Company Ltd (IO201210-07976-01)
This publication has 26 references indexed in Scilit:
- DeepThings: Distributed Adaptive Deep Learning Inference on Resource-Constrained IoT Edge ClustersIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2018
- Channel Pruning for Accelerating Very Deep Neural Networks2017
- An Evaluation of the NVIDIA TX1 for Supporting Real-Time Computer-Vision Workloads2017
- EIEACM SIGARCH Computer Architecture News, 2016
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Deep Residual Learning for Image Recognition2016
- Wide Residual Networks2016
- Bag-of-visual-words and spatial extensions for land-use classification2010
- One-shot learning of object categoriesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006
- A theory of the learnableCommunications of the ACM, 1984