O'Keeffe, Simon and Villing, Rudi (2017) Evaluating Quantized Convolutional Neural Networks for Embedded Systems. In: Irish Machine Vision and Image Processing Conference Proceedings 2017. Irish Pattern Recognition & Classification Society, pp. 261-264. ISBN 9780993420726

Preview

Download (1MB) | Preview

Abstract

This paper presents a deep learning approach which evaluates accuracy and inference time speedups in deep convolutional neural networks under various network quantizations. Quantized networks can result in much faster inference time allowing them to be deployed in real time on an embedded system such as a robot. We evaluate networks with activations quantized to 1, 2, 4, and 8-bits and binary weights. We found that network quantization can yield a significant speedup for a small drop in classification accuracy. Specifically, modifying one of our networks to use an 8-bit quantized input layer and 2-bit activations in hidden layers, we calculate a theoretical 9.9x speedup in exchange for an F1 score decrease of just 3.4% relative to a full precision implementation. Higher speedups are obtainable by designing a network architecture containing a smaller proportion of the total multiplications within the input layer.

Item Type:	Book Section
Keywords:	Convolutional Neural Networks; Deep Learning; Network Quantization;
Academic Unit:	Faculty of Science and Engineering > Electronic Engineering
Item ID:	9769
Depositing User:	Rudi Villing
Date Deposited:	14 Aug 2018 15:27
Publisher:	Irish Pattern Recognition & Classification Society
Refereed:	Yes
URI:
Use Licence:	This item is available under a Creative Commons Attribution Non Commercial Share Alike Licence (CC BY-NC-SA). Details of this licence are available here

Repository Staff Only(login required)

Item control page

Downloads

Origin of downloads