Optimum selection of DNN model and framework for edge inference

This paper describes a methodology to select the optimum combination of deep neural network and software framework for visual inference on embedded systems. As a first step, benchmarking is required. In particular, we have benchmarked six popular network models running on four deep learning framewor...

ver descrição completa

Detalhes bibliográficos
Autores: Velasco-Montero, Delia, Fernández-Berni, J., Carmona-Galán, R., Rodríguez-Vázquez, Ángel
Formato: artículo
Fecha de publicación:2018
País:España
Recursos:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/195639
Acesso em linha:http://hdl.handle.net/10261/195639
Access Level:acceso abierto
Palavra-chave:edge inference
Convolutional neural networks
Benchmarking
embedded vision
Deep learning
high-level specifications
Descrição
Resumo:This paper describes a methodology to select the optimum combination of deep neural network and software framework for visual inference on embedded systems. As a first step, benchmarking is required. In particular, we have benchmarked six popular network models running on four deep learning frameworks implemented on a low-cost embedded platform. Three key performance metrics have been measured and compared with the resulting 24 combinations: accuracy, throughput, and power consumption. Then, application-level specifications come into play. We propose a figure of merit enabling the evaluation of each network/framework pair in terms of relative importance of the aforementioned metrics for a targeted application. We prove through numerical analysis and meaningful graphical representations that only a reduced subset of the combinations must actually be considered for real deployment. Our approach can be extended to other networks, frameworks, and performance parameters, thus supporting system-level design decisions in the ever-changing ecosystem of embedded deep learning technology.