Exploring Distributed Deep Learning Inference Using Raspberry Pi Spark Cluster

Citation

James, Nicholas and Ong, Lee Yeng and Leow, Meng Chew (2022) Exploring Distributed Deep Learning Inference Using Raspberry Pi Spark Cluster. Future Internet, 14 (8). p. 220. ISSN 1999-5903

[img] Text
futureinternet-14-00220.pdf - Published Version
Restricted to Repository staff only

Download (6MB)

Abstract

Raspberry Pi (Pi) is a versatile general-purpose embedded computing device that can be used for both machine learning (ML) and deep learning (DL) inference applications such as face detection. This study trials the use of a Pi Spark cluster for distributed inference in TensorFlow. Specifically, it investigates the performance difference between a 2-node Pi 4B Spark cluster and other systems, including a single Pi 4B and a mid-end desktop computer. Enhancements for the Pi 4B were studied and compared against the Spark cluster to identify the more effective method in increasing the Pi 4B’s DL performance. Three experiments involving DL inference, which in turn involve image classification and face detection tasks, were carried out. Results showed that enhancing the Pi 4B was faster than using a cluster as there was no significant performance difference between using the cluster and a single Pi 4B. The difference between the mid-end computer and a single Pi 4B was between 6 and 15 times in the experiments. In the meantime, enhancing the Pi 4B is the more effective approach for increasing the DL performance, and more work needs to be done for scalable distributed DL inference to eventuate.

Item Type: Article
Uncontrolled Keywords: Cluster, machine learning (ML), deep learning (DL), Spark, TensorFlow, Raspberry Pi (Pi),
Subjects: Q Science > Q Science (General) > Q300-390 Cybernetics
Divisions: Faculty of Information Science and Technology (FIST)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 06 Oct 2022 07:09
Last Modified: 06 Oct 2022 07:09
URII: http://shdl.mmu.edu.my/id/eprint/10481

Downloads

Downloads per month over past year

View ItemEdit (login required)