Search
Abstract
With the advances in systems-on-a-chip technologies, there is a growing demand to deploy intelligent vision systems on low-cost microcomputers. To address this challenge, much of the recent research has focused on reducing the model size and computational complexity of contemporary convolutional neural networks (CNNs). The state-of-the-art lightweight CNN is MobileNetV3. However, it was designed to achieve a good trade-off between accuracy and latency on a single large core of a Google Pixel 1 smartphone. Accordingly, MobileNetV3 is not optimized for platforms with different hardware characteristics and its predecessors may perform better for a given target platform. The aim of this paper is twofold: 1) to analyze the performance of different compact CNNs on Raspberry Pi 4; 2) to manually adapted the most promising models to better utilize the Raspberry Pi 4 hardware. After exploring a number of modifications, we present a new CNN architecture, namely MobileNetV3-Small-Pi, which is 36% faster and slightly more accurate on ImageNet classification compared to the baseline MobileNetV3-Small.
Citations
-
6
CrossRef
-
0
Web of Science
-
1 1
Scopus
Authors (3)
Cite as
Full text
- Publication version
- Accepted or Published Version
- DOI:
- Digital Object Identifier (open in new tab) 10.1016/j.procs.2021.08.238
- License
-
open in new tab
Keywords
Details
- Category:
- Conference activity
- Type:
- publikacja w wydawnictwie zbiorowym recenzowanym (także w materiałach konferencyjnych)
- Published in:
-
Procedia Computer Science
no. 192,
pages 2249 - 2258,
ISSN: 1877-0509 - Language:
- English
- Publication year:
- 2021
- Bibliographic description:
- Glegoła W., Karpus A., Przybyłek A.: MobileNet family tailored for Raspberry Pi// / : , 2021, s.2249-2258
- DOI:
- Digital Object Identifier (open in new tab) 10.1016/j.procs.2021.08.238
- Verified by:
- Gdańsk University of Technology
seen 77 times