OptDNN: Automatic deep neural networks optimizer for edge computing

IF 1.3 Q3 COMPUTER SCIENCE, SOFTWARE ENGINEERING Software Impacts Pub Date : 2024-04-05 DOI:10.1016/j.simpa.2024.100641
Luca Giovannesi, Gabriele Proietti Mattia, Roberto Beraldi
{"title":"OptDNN: Automatic deep neural networks optimizer for edge computing","authors":"Luca Giovannesi,&nbsp;Gabriele Proietti Mattia,&nbsp;Roberto Beraldi","doi":"10.1016/j.simpa.2024.100641","DOIUrl":null,"url":null,"abstract":"<div><p>DNNs are widely used for complex tasks like image and signal processing, and they are in increasing demand for implementation on Internet of Things (IoT) devices. For these devices, optimizing DNN models is a necessary task. Generally, standard optimization approaches require specialists to manually fine-tune hyper-parameters to find a good trade-off between efficiency and accuracy. In this paper, we propose OptDNN, a software that employs innovative and automatic approaches to determine optimal hyper-parameters for pruning, clustering, and quantization. The models optimized by OptDNN have a smaller memory footprint, faster inference time, and a similar accuracy to the original models.</p></div>","PeriodicalId":29771,"journal":{"name":"Software Impacts","volume":"20 ","pages":"Article 100641"},"PeriodicalIF":1.3000,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2665963824000290/pdfft?md5=9408edc33cd6715a12afa1a8f06365fc&pid=1-s2.0-S2665963824000290-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Software Impacts","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2665963824000290","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}
引用次数: 0

Abstract

DNNs are widely used for complex tasks like image and signal processing, and they are in increasing demand for implementation on Internet of Things (IoT) devices. For these devices, optimizing DNN models is a necessary task. Generally, standard optimization approaches require specialists to manually fine-tune hyper-parameters to find a good trade-off between efficiency and accuracy. In this paper, we propose OptDNN, a software that employs innovative and automatic approaches to determine optimal hyper-parameters for pruning, clustering, and quantization. The models optimized by OptDNN have a smaller memory footprint, faster inference time, and a similar accuracy to the original models.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
OptDNN:用于边缘计算的深度神经网络自动优化器
DNN 被广泛应用于图像和信号处理等复杂任务,在物联网(IoT)设备上的应用需求也日益增加。对于这些设备来说,优化 DNN 模型是一项必要的任务。一般来说,标准优化方法需要专家手动微调超参数,以便在效率和准确性之间找到良好的平衡。在本文中,我们提出了 OptDNN 软件,它采用创新的自动方法来确定剪枝、聚类和量化的最佳超参数。经过 OptDNN 优化的模型内存占用更小,推理时间更快,精度与原始模型相似。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Software Impacts
Software Impacts Software
CiteScore
2.70
自引率
9.50%
发文量
0
审稿时长
16 days
期刊最新文献
mGFD: CloudGenerator SlabCutOpt: A code for ornamental stone slab cut optimization LandSin: A differential ML and google API-enabled web server for real-time land insights and beyond EnhancedBERT: A python software tailored for arabic word sense disambiguation PostgreSQL: Relational database structures application on capacitated lot-sizing for pharmaceutical tablets manufacturing processes
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1