- idUS
- Investigación
- Ciencias
- Instituto de Microelectrónica de Sevilla (IMSE-CNM)
- Browsing Instituto de Microelectrónica de Sevilla (IMSE-CNM) by Author
Browsing Instituto de Microelectrónica de Sevilla (IMSE-CNM) by Author "Velasco Montero, Delia"
Now showing items 1-5 of 5
-
Article
Impact of thermal throttling on long-term visual inference in a cpu-based edge device
Benoit-Cattin, Théo; Velasco Montero, Delia; Fernández Berni, Jorge (Multidisciplinary Digital Publishing Institute (MDPI), 2020)Many application scenarios of edge visual inference, e.g., robotics or environmental monitoring, eventually require long ...
-
Presentation
On the Correlation of CNN Performance and Hardware Metrics for Visual Inference on a Low-Cost CPU-based Platform
Velasco Montero, Delia; Fernández Berni, Jorge; Carmona Galán, Ricardo; Rodríguez Vázquez, Ángel Benito (Institute of Electrical and Electronics Engineers, 2019)While providing the same functionality, the various Deep Learning software frameworks available these days do not provide ...
-
Presentation
On-The-Fly Deployment of Deep Neural Networks on Heterogeneous Hardware in a Low-Cost Smart Camera
Velasco Montero, Delia; Fernández Berni, Jorge; Carmona Galán, Ricardo; Rodríguez Vázquez, Ángel Benito (Association for Computing Machinery, 2018)This demo showcases a low-cost smart camera where different hardware configurations can be selected to perform image ...
-
Article
Optimum Selection of DNN Model and Framework for Edge Inference
Velasco Montero, Delia; Fernández Berni, Jorge; Carmona Galán, Ricardo; Rodríguez Vázquez, Ángel Benito (IEEE, 2018)This paper describes a methodology to select the optimum combination of deep neuralnetwork and software framework for ...
-
Article
PreVIous: A Methodology for Prediction of Visual Inference Performance on IoT Devices
Velasco Montero, Delia; Fernández Berni, Jorge; Carmona Galán, Ricardo; Rodríguez Vázquez, Ángel Benito (Institute of Electrical and Electronics Engineers, 2020)This article presents PreVIous, a methodology to predict the performance of convolutional neural networks (CNNs) in terms ...