Optimizing Deep Learning Inference on Embedded Systems Through Adaptive Model Selection

no code implementations • 9 Nov 2019 • Vicent Sanz Marco, Ben Taylor, Zheng Wang, Yehia Elkhatib

For image classification, we achieve a 1. 8x reduction in inference time with a 7. 52% improvement in accuracy, over the most-capable single DNN model.

Image Classification Machine Translation +2

Adaptive Selection of Deep Learning Models on Embedded Systems

no code implementations • 11 May 2018 • Ben Taylor, Vicent Sanz Marco, Willy Wolff, Yehia Elkhatib, Zheng Wang

This paper presents an adaptive scheme to determine which DNN model to use for a given input, by considering the desired accuracy and inference time.

Image Classification