Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/194359
Share/Export:
logo share SHARE BASE
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE
DC FieldValueLanguage
dc.contributor.authorVelasco-Montero, D.es_ES
dc.contributor.authorFernández-Berni, J.es_ES
dc.contributor.authorCarmona-Galán, R.es_ES
dc.contributor.authorRodríguez-Vázquez, Ángeles_ES
dc.date.accessioned2019-11-12T09:24:10Z-
dc.date.available2019-11-12T09:24:10Z-
dc.date.issued2019-
dc.identifier.citationICDSC 2019 Proceedings of the 13th International Conference on Distributed Smart Cameras Article No. 29 (2019)es_ES
dc.identifier.urihttp://hdl.handle.net/10261/194359-
dc.descriptionProceeding ICDSC 2019 Proceedings of the 13th International Conference on Distributed Smart Cameras Article No. 29. Trento, Italy — September 09 - 11, 2019es_ES
dc.description.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 timees_ES
dc.language.isoenges_ES
dc.publisherAssociation for Computing Machineryes_ES
dc.relation.isversionofPostprintes_ES
dc.rightsopenAccesses_ES
dc.subjectEmbedded vision systemes_ES
dc.subjectVisual inferencees_ES
dc.subjectDeep neural networks,es_ES
dc.subjectCPU based hardwarees_ES
dc.subjectInference performancees_ES
dc.titleDemo: CNN Performance Prediction on a CPU based Edge Platformes_ES
dc.typeactas de congresoes_ES
dc.identifier.doi10.1145/3349801.3357131-
dc.description.peerreviewedPeer reviewedes_ES
dc.relation.publisherversionhttps://doi.org/10.1145/3349801.3357131es_ES
dc.relation.csices_ES
oprm.item.hasRevisionno ko 0 false*
item.fulltextWith Fulltext-
item.openairetypeactas de congreso-
item.cerifentitytypePublications-
item.languageiso639-1en-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.grantfulltextopen-
Appears in Collections:(IMSE-CNM) Comunicaciones congresos
Files in This Item:
File Description SizeFormat
demo_ICDSC2019_DVelasco.pdf282,91 kBAdobe PDFThumbnail
View/Open
Show simple item record

Google ScholarTM

Check

Altmetric

Dimensions


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