Evaluation of deep learning accelerators for object detection at the edge

Abstract

Deep learning is moving more and more from the cloud towards the edge. Therefore, embedded devices are needed that are reasonably cheap, energy-efficient and fast enough. In this paper we evaluate the performance and energy consumption of popular, off-the-shelf commercial devices for deep learning inferencing. We compare the Intel Neural Compute Stick 2, the Google Coral Edge TPU and the Nvidia Jetson Nano with the Raspberry Pi 4 for their suitability as a central controller in an autonomous vehicle for the formula student driverless.

Mehr zum Titel

Titel Evaluation of deep learning accelerators for object detection at the edge
Medien KI 2020: Advances in Artificial Intelligence
Verlag Springer International Publishing
Heft ---
Band ---
ISBN 978-3-030-58284-5
Verfasser/Herausgeber Pascal Puchtler, Prof. Dr. René Peinl
Seiten S. 320-326
Veröffentlichungsdatum 09.09.2020
Projekttitel ---
Zitation Puchtler, Pascal; Peinl, René (2020): Evaluation of deep learning accelerators for object detection at the edge. KI 2020: Advances in Artificial Intelligence, S. S. 320-326.