English   español  
Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/220048
Share/Impact:
Statistics
logo share SHARE   Add this article to your Mendeley library MendeleyBASE
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE
Exportar a otros formatos:

Title

Performance assessment of deep learning frameworks through metrics of CPU hardware exploitation on an embedded platform

AuthorsVelasco-Montero, D.; Fernández-Berni, J. ; Carmona-Galán, R. ; Rodríguez-Vázquez, Ángel
KeywordsConvolutional neural networks
Deep learning
Edge inference
Embedded vision
Hardware performance
Software frameworks
Issue Date2020
PublisherFERIT
CitationInternational Journal of Electrical and Computer Engineering Systems 11: 1- 11 (2020)
AbstractIn this paper, we analyze heterogeneous performance exhibited by some popular deep learning software frameworks for visual inference on a resource-constrained hardware platform. Benchmarking of Caffe, OpenCV, TensorFlow, and Caffe2 is performed on the same set of convolutional neural networks in terms of instantaneous throughput, power consumption, memory footprint, and CPU utilization. To understand the resulting dissimilar behavior, we thoroughly examine how the resources in the processor are differently exploited by these frameworks. We demonstrate that a strong correlation exists between hardware events occurring in the processor and inference performance. The proposedhardware-aware analysis aims to findlimitations andbottlenecks emerging from the jointinteraction offrameworks andnetworks on a particular CPU-based platform. This provides insight into introducing suitable modifications in bothtypes of components to enhance their global performance. It also facilitates the selection of frameworks and networks among a large diversity of these components available these days for visual understanding.
URIhttp://hdl.handle.net/10261/220048
Identifiersissn: 1847-7003
Appears in Collections:(IMSE-CNM) Artículos
Files in This Item:
File Description SizeFormat 
11-01-01.pdf1,45 MBAdobe PDFThumbnail
View/Open
Show full item record
Review this work
 


WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.