Batching for Green AI - An Exploratory Study on Inference

Conference Paper (2023)
Author(s)

T.E.R. Yarally

Luis Cruz (TU Delft - Software Engineering)

Daniel Feitosa (University Medical Center Groningen)

J. Sallou (TU Delft - Software Engineering)

A. van Deursen (TU Delft - Software Engineering)

Research Group
Software Engineering
DOI related publication
https://doi.org/10.1109/SEAA60479.2023.00026
More Info
expand_more
Publication Year
2023
Language
English
Research Group
Software Engineering
Bibliographical Note
Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. @en
Pages (from-to)
112-119
Publisher
IEEE
ISBN (electronic)
979-8-3503-4235-2
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

The batch size is an essential parameter to tune during the development of new neural networks. Amongst other quality indicators, it has a large degree of influence on the model’s accuracy, generalisability, training times and parallelisability. This fact is generally known and commonly studied. However, during the application phase of a deep learning model, when the model is utilised by an end-user for inference, we find that there is a disregard for the potential benefits of introducing a batch size. In this study, we examine the effect of input batching on the energy consumption and response times of five fully-trained neural networks for computer vision that were considered state-of-the-art at the time of their publication. The results suggest that batching has a significant effect on both of these metrics. Furthermore, we present a timeline of the energy efficiency and accuracy of neural networks over the past decade. We find that in general, energy consumption rises at a much steeper pace than accuracy and question the necessity of this evolution. Additionally, we highlight one particular network, ShuffleNetV2 (2018), that achieved a competitive performance for its time while maintaining a much lower energy consumption. Nevertheless, we highlight that the results are model dependent.

Files

Batching_for_Green_AI_-_An_Exp... (pdf)
(pdf | 0.961 Mb)
- Embargo expired in 08-07-2024
License info not available