Evaluación del rendimiento de redes neuronales en dispositivos edge mediante el framework NC-SDK

In the world of Internet of Things (IoT), edge computing has increased its popularity in recent years. This study describes the Neural Compute Software Development Kit (NCSDK) package, which contains a set of development tools in order to be able to adapt, compile and run inferences from different d...

Descripción completa

Detalles Bibliográficos
Autor: Morán Montero, David
Tipo de recurso: tesis de maestría
Fecha de publicación:2024
País:España
Institución:Universidad Complutense de Madrid (UCM)
Repositorio:Docta Complutense
Idioma:inglés
OAI Identifier:oai:docta.ucm.es:20.500.14352/109073
Acceso en línea:https://hdl.handle.net/20.500.14352/109073
Access Level:acceso abierto
Palabra clave:004(043.3)
NC-SDK
PowerVR
Redes neuronales
Rendimiento
Inferencia
Neural networks
Performance
Inference
Informática (Informática)
33 Ciencias Tecnológicas
id ES_706d7e7e58d14ca197cc899ba8ced8dc
oai_identifier_str oai:docta.ucm.es:20.500.14352/109073
network_acronym_str ES
network_name_str España
repository_id_str
spelling Evaluación del rendimiento de redes neuronales en dispositivos edge mediante el framework NC-SDKPerformance benchmark of neural networks on edge devices using the NC-SDK frameworkMorán Montero, David004(043.3)NC-SDKPowerVRRedes neuronalesRendimientoInferenciaNeural networksPerformanceInferenceInformática (Informática)33 Ciencias TecnológicasIn the world of Internet of Things (IoT), edge computing has increased its popularity in recent years. This study describes the Neural Compute Software Development Kit (NCSDK) package, which contains a set of development tools in order to be able to adapt, compile and run inferences from different deep learning models on certain specific devices. This project demonstrates the workflow with the NC-SDK package, highlighting the processes of adapting deep learning models from various implementations, compiling neural networks for execution on the deployment platform, and executing distinct models using the PowerVR GPU. Finally, it is conducted a performance benchmark on different ML categories, such as image classification, object detection and segmentation, and language processing. The obtained results will be compared and analyzed with CPU usage by other frameworks.Igual Peña, Francisco DanielPiñuel Moreno, LuisUniversidad Complutense de Madrid20242024-01-0120242024-01-01master thesishttp://purl.org/coar/resource_type/c_bdccAMhttp://purl.org/coar/version/c_ab4af688f83e57aainfo:eu-repo/semantics/masterThesisapplication/pdfhttps://hdl.handle.net/20.500.14352/109073reponame:Docta Complutenseinstname:Universidad Complutense de Madrid (UCM)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2Attribution-NonCommercial-NoDerivatives 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:docta.ucm.es:20.500.14352/1090732026-06-02T12:44:21Z
dc.title.none.fl_str_mv Evaluación del rendimiento de redes neuronales en dispositivos edge mediante el framework NC-SDK
Performance benchmark of neural networks on edge devices using the NC-SDK framework
title Evaluación del rendimiento de redes neuronales en dispositivos edge mediante el framework NC-SDK
spellingShingle Evaluación del rendimiento de redes neuronales en dispositivos edge mediante el framework NC-SDK
Morán Montero, David
004(043.3)
NC-SDK
PowerVR
Redes neuronales
Rendimiento
Inferencia
Neural networks
Performance
Inference
Informática (Informática)
33 Ciencias Tecnológicas
title_short Evaluación del rendimiento de redes neuronales en dispositivos edge mediante el framework NC-SDK
title_full Evaluación del rendimiento de redes neuronales en dispositivos edge mediante el framework NC-SDK
title_fullStr Evaluación del rendimiento de redes neuronales en dispositivos edge mediante el framework NC-SDK
title_full_unstemmed Evaluación del rendimiento de redes neuronales en dispositivos edge mediante el framework NC-SDK
title_sort Evaluación del rendimiento de redes neuronales en dispositivos edge mediante el framework NC-SDK
dc.creator.none.fl_str_mv Morán Montero, David
author Morán Montero, David
author_facet Morán Montero, David
author_role author
dc.contributor.none.fl_str_mv Igual Peña, Francisco Daniel
Piñuel Moreno, Luis
Universidad Complutense de Madrid
dc.subject.none.fl_str_mv 004(043.3)
NC-SDK
PowerVR
Redes neuronales
Rendimiento
Inferencia
Neural networks
Performance
Inference
Informática (Informática)
33 Ciencias Tecnológicas
topic 004(043.3)
NC-SDK
PowerVR
Redes neuronales
Rendimiento
Inferencia
Neural networks
Performance
Inference
Informática (Informática)
33 Ciencias Tecnológicas
description In the world of Internet of Things (IoT), edge computing has increased its popularity in recent years. This study describes the Neural Compute Software Development Kit (NCSDK) package, which contains a set of development tools in order to be able to adapt, compile and run inferences from different deep learning models on certain specific devices. This project demonstrates the workflow with the NC-SDK package, highlighting the processes of adapting deep learning models from various implementations, compiling neural networks for execution on the deployment platform, and executing distinct models using the PowerVR GPU. Finally, it is conducted a performance benchmark on different ML categories, such as image classification, object detection and segmentation, and language processing. The obtained results will be compared and analyzed with CPU usage by other frameworks.
publishDate 2024
dc.date.none.fl_str_mv 2024
2024-01-01
2024
2024-01-01
dc.type.none.fl_str_mv master thesis
http://purl.org/coar/resource_type/c_bdcc
AM
http://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.openaire.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
dc.identifier.none.fl_str_mv https://hdl.handle.net/20.500.14352/109073
url https://hdl.handle.net/20.500.14352/109073
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivatives 4.0 International
http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivatives 4.0 International
http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Docta Complutense
instname:Universidad Complutense de Madrid (UCM)
instname_str Universidad Complutense de Madrid (UCM)
reponame_str Docta Complutense
collection Docta Complutense
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869410579817431040
score 15,812455

Similares en LA Referencia