Demo: On-The-Fly Deployment of Deep Neural Networks on Heterogeneous Hardware in a Low-Cost Smart Camera

被引:0
作者
Velasco-Montero, D. [1 ]
Fernandez-Berni, J. [1 ]
Carmona-Galan, R. [1 ]
Rodriguez-Vazquez, A. [1 ]
机构
[1] Univ Seville, CSIC, Inst Microelect Sevilla IMSE CNM, Seville, Spain
来源
PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON DISTRIBUTED SMART CAMERAS (ICDSC'18) | 2018年
基金
欧盟地平线“2020”;
关键词
Smart camera; embedded vision system; visual inference; deep neural networks; heterogeneous hardware;
D O I
10.1145/3243394.3243705
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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.
引用
收藏
页数:2
相关论文
共 4 条
[1]  
[Anonymous], 2017, Intel movidius neural compute sticks
[2]  
[Anonymous], 2016, RASPBERRY PI 3 MODEL
[3]   Deep learning [J].
LeCun, Yann ;
Bengio, Yoshua ;
Hinton, Geoffrey .
NATURE, 2015, 521 (7553) :436-444
[4]   Embedded Deep Neural Network Processing: Algorithmic and Processor Techniques Bring Deep Learning to IoT and Edge Devices [J].
Verhelst, Marian ;
Moons, Bert .
IEEE Solid-State Circuits Magazine, 2017, 9 (04) :55-65