Saved in:
Bibliographic Details
Main Authors: Fu, Yonggan, Yu, Zhongzhi, Zhang, Yongan, Jiang, Yifan, Li, Chaojian, Liang, Yongyuan, Jiang, Mingchao, Wang, Zhangyang, Lin, Yingyan Celine
Format: Preprint
Published: 2021
Subjects:
Online Access:https://arxiv.org/abs/2104.10853
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910771571589120
author Fu, Yonggan
Yu, Zhongzhi
Zhang, Yongan
Jiang, Yifan
Li, Chaojian
Liang, Yongyuan
Jiang, Mingchao
Wang, Zhangyang
Lin, Yingyan Celine
author_facet Fu, Yonggan
Yu, Zhongzhi
Zhang, Yongan
Jiang, Yifan
Li, Chaojian
Liang, Yongyuan
Jiang, Mingchao
Wang, Zhangyang
Lin, Yingyan Celine
contents The promise of Deep Neural Network (DNN) powered Internet of Thing (IoT) devices has motivated a tremendous demand for automated solutions to enable fast development and deployment of efficient (1) DNNs equipped with instantaneous accuracy-efficiency trade-off capability to accommodate the time-varying resources at IoT devices and (2) dataflows to optimize DNNs' execution efficiency on different devices. Therefore, we propose InstantNet to automatically generate and deploy instantaneously switchable-precision networks which operate at variable bit-widths. Extensive experiments show that the proposed InstantNet consistently outperforms state-of-the-art designs.
format Preprint
id arxiv_https___arxiv_org_abs_2104_10853
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle InstantNet: Automated Generation and Deployment of Instantaneously Switchable-Precision Networks
Fu, Yonggan
Yu, Zhongzhi
Zhang, Yongan
Jiang, Yifan
Li, Chaojian
Liang, Yongyuan
Jiang, Mingchao
Wang, Zhangyang
Lin, Yingyan Celine
Machine Learning
The promise of Deep Neural Network (DNN) powered Internet of Thing (IoT) devices has motivated a tremendous demand for automated solutions to enable fast development and deployment of efficient (1) DNNs equipped with instantaneous accuracy-efficiency trade-off capability to accommodate the time-varying resources at IoT devices and (2) dataflows to optimize DNNs' execution efficiency on different devices. Therefore, we propose InstantNet to automatically generate and deploy instantaneously switchable-precision networks which operate at variable bit-widths. Extensive experiments show that the proposed InstantNet consistently outperforms state-of-the-art designs.
title InstantNet: Automated Generation and Deployment of Instantaneously Switchable-Precision Networks
topic Machine Learning
url https://arxiv.org/abs/2104.10853