DeepSense:商用移动设备上基于gpu的深度卷积神经网络框架

Huynh Nguyen Loc, R. Balan, Youngki Lee
{"title":"DeepSense:商用移动设备上基于gpu的深度卷积神经网络框架","authors":"Huynh Nguyen Loc, R. Balan, Youngki Lee","doi":"10.1145/2935643.2935650","DOIUrl":null,"url":null,"abstract":"Recently, a branch of machine learning algorithms called deep learning gained huge attention to boost up accuracy of a variety of sensing applications. However, execution of deep learning algorithm such as convolutional neural network on mobile processor is non-trivial due to intensive computational requirements. In this paper, we present our early design of DeepSense - a mobile GPU-based deep convolutional neural network (CNN) framework. For its design, we first explored the differences between server-class and mobile-class GPUs, and studied effectiveness of various optimization strategies such as branch divergence elimination and memory vectorization. Our results show that DeepSense is able to execute a variety of CNN models for image recognition, object detection and face recognition in soft real time with no or marginal accuracy tradeoffs. Experiments also show that our framework is scalable across multiple devices with different GPU architectures (e.g. Adreno and Mali).","PeriodicalId":345713,"journal":{"name":"WearSys '16","volume":"22 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"60","resultStr":"{\"title\":\"DeepSense: A GPU-based Deep Convolutional Neural Network Framework on Commodity Mobile Devices\",\"authors\":\"Huynh Nguyen Loc, R. Balan, Youngki Lee\",\"doi\":\"10.1145/2935643.2935650\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Recently, a branch of machine learning algorithms called deep learning gained huge attention to boost up accuracy of a variety of sensing applications. However, execution of deep learning algorithm such as convolutional neural network on mobile processor is non-trivial due to intensive computational requirements. In this paper, we present our early design of DeepSense - a mobile GPU-based deep convolutional neural network (CNN) framework. For its design, we first explored the differences between server-class and mobile-class GPUs, and studied effectiveness of various optimization strategies such as branch divergence elimination and memory vectorization. Our results show that DeepSense is able to execute a variety of CNN models for image recognition, object detection and face recognition in soft real time with no or marginal accuracy tradeoffs. Experiments also show that our framework is scalable across multiple devices with different GPU architectures (e.g. Adreno and Mali).\",\"PeriodicalId\":345713,\"journal\":{\"name\":\"WearSys '16\",\"volume\":\"22 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-06-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"60\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"WearSys '16\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/2935643.2935650\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"WearSys '16","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/2935643.2935650","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 60

摘要

最近,机器学习算法的一个分支深度学习获得了广泛关注,以提高各种传感应用的准确性。然而,卷积神经网络等深度学习算法在移动处理器上的执行由于计算量大而不是简单的。在本文中,我们介绍了DeepSense的早期设计-一个基于移动gpu的深度卷积神经网络(CNN)框架。对于其设计,我们首先探讨了服务器级和移动级gpu的差异,并研究了各种优化策略的有效性,如分支分歧消除和内存矢量化。我们的研究结果表明,DeepSense能够在软实时情况下执行各种CNN模型,用于图像识别、目标检测和人脸识别,而没有或只有边际精度权衡。实验还表明,我们的框架可扩展到具有不同GPU架构的多个设备(例如Adreno和Mali)。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
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
DeepSense: A GPU-based Deep Convolutional Neural Network Framework on Commodity Mobile Devices
Recently, a branch of machine learning algorithms called deep learning gained huge attention to boost up accuracy of a variety of sensing applications. However, execution of deep learning algorithm such as convolutional neural network on mobile processor is non-trivial due to intensive computational requirements. In this paper, we present our early design of DeepSense - a mobile GPU-based deep convolutional neural network (CNN) framework. For its design, we first explored the differences between server-class and mobile-class GPUs, and studied effectiveness of various optimization strategies such as branch divergence elimination and memory vectorization. Our results show that DeepSense is able to execute a variety of CNN models for image recognition, object detection and face recognition in soft real time with no or marginal accuracy tradeoffs. Experiments also show that our framework is scalable across multiple devices with different GPU architectures (e.g. Adreno and Mali).
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
MiHub: Wearable Management for IoT In-ear Biosignal Recording System: A Wearable For Automatic Whole-night Sleep Staging CryptoCoP: Lightweight, Energy-efficient Encryption and Privacy for Wearable Devices DeepSense: A GPU-based Deep Convolutional Neural Network Framework on Commodity Mobile Devices Wireless Smartphone Keyboard for Visually Challenged Users
×
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