English   español  
Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/163973
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
Exportar a otros formatos:

Title

Performance Analysis of Real-Time DNN Inference on Raspberry Pi

AuthorsVelasco-Montero, Delia; Fernández-Berni, J. ; Carmona-Galán, R. ; Rodríguez-Vázquez, Ángel
KeywordsDeep Learning
Convolutional Neural Networks
Embedded Vision
Raspberry Pi
Inference
Perfomance
Issue Date2018
PublisherThe International Society for Optics and Photonics
Citationin Real-Time Image and Video Processing Conference, SPIE Defense + Commercial Sensing Symposium, Orlando FL USA, April 2018.
AbstractDeep Neural Networks (DNNs) have emerged as the reference processing architecture for the implementation of multiple computer vision tasks. They achieve much higher accuracy than traditional algorithms based on shallow learning. However, it comes at the cost of a substantial increase of computational resources. This constitutes a challenge for embedded vision systems performing edge inference as opposed to cloud processing. In such a demanding scenario, several open-source frameworks have been developed, e.g. Ca e, OpenCV, TensorFlow, Theano, Torch or MXNet. All of these tools enable the deployment of various state-of-the-art DNN models for inference, though each one relies on particular optimization libraries and techniques resulting in di erent performance behavior. In this paper, we present a comparative study of some of these frameworks in terms of power consumption, throughput and precision for some of the most popular Convolutional Neural Networks (CNN) models. The benchmarking system is Raspberry Pi 3 Model B, a low-cost embedded platform with limited resources. We highlight the advantages and limitations associated with the practical use of the analyzed frameworks. Some guidelines are provided for suitable selection of a speci c tool according to prescribed application requirements.
Publisher version (URL)https://spie.org/SIC/conferencedetails/real-time-image-video-processing?SSO=1
URIhttp://hdl.handle.net/10261/163973
Appears in Collections:(IMSE-CNM) Artículos
Files in This Item:
File Description SizeFormat 
Performance_Analysis_of_Real_Time_DNN_on_RPi.pdf275,23 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.