English   español  
Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/194359
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

Demo: CNN Performance Prediction on a CPU based Edge Platform

AuthorsVelasco-Montero, D.; Fernández-Berni, J. CSIC ORCID CVN; Carmona-Galán, R. CSIC ORCID ; Rodríguez-Vázquez, Ángel CSIC ORCID
KeywordsEmbedded vision system
Visual inference
Deep neural networks,
CPU based hardware
Inference performance
Issue Date2019
PublisherAssociation for Computing Machinery
CitationICDSC 2019 Proceedings of the 13th International Conference on Distributed Smart Cameras Article No. 29 (2019)
AbstractThe implementation of algorithms based on Dee p Learning at edge visual systems is currently a challenge. In addition to accuracy, the network architecture also has an impact on inference performance in terms of throughput and power consumption. This demo showcases per layer inference performance of various convolut ional neural networks running at a low cost edge platform . Furthermore, a n empirical model is applied to predict processing time and power consumption prior to actually running the networks A comparison between the prediction from our model and the actual inference performance is displayed in real time
DescriptionProceeding ICDSC 2019 Proceedings of the 13th International Conference on Distributed Smart Cameras Article No. 29. Trento, Italy — September 09 - 11, 2019
Publisher version (URL)https://doi.org/10.1145/3349801.3357131
URIhttp://hdl.handle.net/10261/194359
DOIhttp://dx.doi.org/10.1145/3349801.3357131
Appears in Collections:(IMSE-CNM) Comunicaciones congresos
Files in This Item:
File Description SizeFormat 
demo_ICDSC2019_DVelasco.pdf282,91 kBAdobe 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.