Share Email Print
cover

Proceedings Paper

OpenCL-code generation framework for MobileNets with depthwise separable convolution and merged layers
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Deep convolutional neural networks are increasingly used in various parallel embedded platforms such as mobile GPUs, AMD APUs, and FPGAs. At the same time, many new models have been developed for embedded platforms, such as MobileNet. In order to balance accuracy, speed and resource requirements and achieve cross-platform versatility, we have developed a software framework for in-depth research. Generated an OpenCL code that takes full advantage of parallel resources and improves the parallel efficiency of OpenCL code. Another advantage is that it optimizes and consolidates the network and compiles offline, making the entire application most efficient. MobileNets uses nonlongitudinal separable convolution (deep separable convolution) instead of standard convolution. Experiments with MobileNet have shown that the OpenCL code generation framework can significantly improve the efficiency of use.

Paper Details

Date Published: 14 February 2020
PDF: 8 pages
Proc. SPIE 11431, MIPPR 2019: Parallel Processing of Images and Optimization Techniques; and Medical Imaging, 1143108 (14 February 2020); doi: 10.1117/12.2541926
Show Author Affiliations
Bin Zhou, Beijing Aerospace Automatic Control Institute (China)
Songzhi Jin, Beijing Aerospace Automatic Control Institute (China)
Yanxin Liu, Beijing Aerospace Automatic Control Institute (China)
Mengxi Hao, Beijing Aerospace Automatic Control Institute (China)
Hui Zhang, Beijing Aerospace Automatic Control Institute (China)


Published in SPIE Proceedings Vol. 11431:
MIPPR 2019: Parallel Processing of Images and Optimization Techniques; and Medical Imaging
Hong Sun; Bruce Hirsch; Chao Cai, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray