On-The-Fly Deployment of Deep Neural Networks on Heterogeneous Hardware in a Low-Cost Smart Camera
| Autor: | Ricardo Carmona-Galan, Jorge Fernández-Berni, Delia Velasco-Montero, Ángel Rodríguez-Vázquez |
|---|---|
| Přispěvatelé: | Universidad de Sevilla. Departamento de Electrónica y Electromagnetismo |
| Rok vydání: | 2018 |
| Předmět: |
Heterogeneous hardware
business.industry Computer science On the fly 010401 analytical chemistry Smart camera Control reconfiguration 02 engineering and technology 01 natural sciences Visual inference 0104 chemical sciences Software deployment Embedded vision system Deep neural networks 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing business Computer hardware Network model |
| Zdroj: | idUS. Depósito de Investigación de la Universidad de Sevilla instname ICDSC Proceedings of the 12th International Conference on Distributed Smart Cameras Proceedings of the 12th International Conference on Distributed Smart Cameras-ICDSC 18 Proceedings of the 12th International Conference on Distributed Smart Cameras-ICDSC '18 Digital.CSIC. Repositorio Institucional del CSIC |
| Popis: | This demo showcases a low-cost smart camera where different hardware configurations can be selected to perform image recognition on deep neural networks. Both the hardware configuration and the network model can be changed any time on the fly. Up to 24 hardware-model combinations are possible, enabling dynamic reconfiguration according to prescribed application requirements. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|