Orpheus: a New Deep Learning Framework for Easy Deployment and Evaluation of Edge Inference

Gibson, P. and Cano, J. (2020) Orpheus: a New Deep Learning Framework for Easy Deployment and Evaluation of Edge Inference. In: 2020 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), 23-26 Aug 2020, pp. 229-230. ISBN 9781728147987 (doi: 10.1109/ISPASS48437.2020.00042)

[img] Text
221588.pdf - Accepted Version



Optimising deep learning inference across edge devices and optimisation targets such as inference time, memory footprint and power consumption is a key challenge due to the ubiquity of neural networks. Today, production deep learning frameworks provide useful abstractions to aid machine learning engineers and systems researchers. However, in exchange they can suffer from compatibility challenges (especially on constrained platforms), inaccessible code complexity, or design choices that otherwise limit research from a systems perspective. This paper presents Orpheus, a new deep learning framework for easy prototyping, deployment and evaluation of inference optimisations. Orpheus features a small codebase, minimal dependencies, and a simple process for integrating other third party systems. We present some preliminary evaluation results.

Item Type:Conference Proceedings
Additional Information:This work was supported by the European Union’s Horizon 2020 research and innovation programme under grant agreement No 732204 (Bonseyes), and by the Swiss State Secretariat for Education, Research and Innovation (SERI) under contract number 16.0159.
Glasgow Author(s) Enlighten ID:Cano Reyes, Dr Jose and Gibson, Mx Perry
Authors: Gibson, P., and Cano, J.
College/School:College of Science and Engineering > School of Computing Science
Copyright Holders:Copyright © 2020 IEEE
Publisher Policy:Reproduced in accordance with the copyright policy of the publisher
Related URLs:

University Staff: Request a correction | Enlighten Editors: Update this record