PreVIous: A Methodology for Prediction of Visual Inference Performance on IoT Devices

1 code implementation • 13 Dec 2019 • Delia Velasco-Montero, Jorge Fernández-Berni, Ricardo Carmona-Galán, Ángel Rodríguez-Vázquez

This paper presents PreVIous, a methodology to predict the performance of convolutional neural networks (CNNs) in terms of throughput and energy consumption on vision-enabled devices for the Internet of Things.

Neural Architecture Search