A Platform Independent Model Design and Adaptation for Edge Intelligence

Chaolong Zhang*, Jiliu Zhou, Jia He, Zhijie Xu, Jin Jin, Chao Kong, Yuanping Xu, Benjun Guo, Qiuyan Gai

*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

Abstract

Along with the rapid developments in deep learning and edge computing technologies, deploying models on mobile devices is a trend for modern applications. However, the resource-constrained and heterogeneous edge devices fail to cope with complicated model inference. To tackle this challenge, this study explores the platform independent model design based on Open Neural Network Exchange. Then we quantize the existing heavy deep learning models into lightweight ones by applying low-precision arithmetic and partitioning the computational graph into sub-graphs for parallel execution and hardware-based acceleration on heterogeneous systems. This study evaluates the efficiency and effectiveness among different quantization settings and analyses the impacts for model acceleration. The experiments show that the quantized models with uint8 type computation perform faster inference while still preserve high performance. This result suggests a novel solution for the research on edge intelligence.

Original languageEnglish
Title of host publicationICAC 2024 - 29th International Conference on Automation and Computing
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350360882
DOIs
Publication statusPublished - 2024
Externally publishedYes
Event29th International Conference on Automation and Computing, ICAC 2024 - Sunderland, United Kingdom
Duration: 28 Aug 202430 Aug 2024

Publication series

NameICAC 2024 - 29th International Conference on Automation and Computing

Conference

Conference29th International Conference on Automation and Computing, ICAC 2024
Country/TerritoryUnited Kingdom
CitySunderland
Period28/08/2430/08/24

Keywords

  • Edge Computing
  • Edge Intelligence
  • IoT
  • Model Inference
  • ONNX
  • Quantization

Fingerprint

Dive into the research topics of 'A Platform Independent Model Design and Adaptation for Edge Intelligence'. Together they form a unique fingerprint.

Cite this