FPGA-based accelerator for losslessly quantized convolutional neural networks

Mankit Sit, Ryosuke Kazami, Hideharu Amano

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Convolutional Neural Networks (CNN) have been widely used for various computer vision tasks. While GPUs are the most common platform for CNN implementation, FPGAs are promising alternatives to provide better energy efficiency. Recent work demonstrates the potential of network quantization to reduce the model size and enhance computation efficiency while maintaining comparable accuracy to the full precision counterparts. Quantized CNN is especially suitable for FPGA implementation due to the presence of values with non-trivial bitwidth. In this paper, we present the design of an FPGA-based accelerator for losslessly quantized CNNs using High Level Synthesis tool. The experiment result shows that our design achieves 12.9 GOPS/Watt for quantized Alexnet on Imagnet Dataset.

Original languageEnglish
Title of host publication2017 International Conference on Field-Programmable Technology, ICFPT 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages295-298
Number of pages4
ISBN (Electronic)9781538626559
DOIs
Publication statusPublished - 2018 Feb 2
Event16th IEEE International Conference on Field-Programmable Technology, ICFPT 2017 - Melbourne, Australia
Duration: 2017 Dec 112017 Dec 13

Publication series

Name2017 International Conference on Field-Programmable Technology, ICFPT 2017
Volume2018-January

Other

Other16th IEEE International Conference on Field-Programmable Technology, ICFPT 2017
CountryAustralia
CityMelbourne
Period17/12/1117/12/13

ASJC Scopus subject areas

  • Hardware and Architecture
  • Software
  • Instrumentation

Fingerprint Dive into the research topics of 'FPGA-based accelerator for losslessly quantized convolutional neural networks'. Together they form a unique fingerprint.

  • Cite this

    Sit, M., Kazami, R., & Amano, H. (2018). FPGA-based accelerator for losslessly quantized convolutional neural networks. In 2017 International Conference on Field-Programmable Technology, ICFPT 2017 (pp. 295-298). (2017 International Conference on Field-Programmable Technology, ICFPT 2017; Vol. 2018-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/FPT.2017.8280164