arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1909.04783cs.DCcs.PF
收藏

表征移动应用的深度神经网络推理性能

Characterizing the Deep Neural Networks Inference Performance of Mobile Applications

Samuel S. Ogden, Tian Guo

摘要:

当今的移动应用越来越多地利用深度神经网络来提供新的功能,例如图像和语音识别。要使用预先训练的深度神经网络,移动开发人员可以将其托管在云服务器中,称为基于云的推理,或者将其与移动应用程序一起发布,称为设备上的推理。在这项工作中,我们使用流行的卷积神经网络研究了这两种常见方法在移动设备和公共云上的推理性能。我们的测量研究表明,需要设备上和基于云的推理来支持移动应用程序。特别是,较新的移动设备能够在合理的时间内运行移动优化的CNN模型。然而,对于较旧的移动设备或使用更复杂的CNN模型,移动应用程序应该选择基于云的推理。我们进一步证明,可变的网络条件可能导致基于云的推理端到端时间不佳。为了支持高效的基于云的推理,我们提出了一种称为CNNSelect的CNN模型选择算法,该算法为每个推理请求动态选择最合适的CNN模型,并调整其选择以匹配由可变移动环境引起的不同SLA和执行时间预算。CNNSelect的关键思想是使用一组CNN模型在运行时进行推理速度和准确性的权衡。我们证明了CNNSelect平滑地提高了推理准确性,同时在比贪婪基线多88.5%的情况下保持了SLA的实现。

英文摘要:

Today's mobile applications are increasingly leveraging deep neural networks to provide novel features, such as image and speech recognitions. To use a pre-trained deep neural network, mobile developers can either host it in a cloud server, referred to as cloud-based inference, or ship it with their mobile application, referred to as on-device inference. In this work, we investigate the inference performance of these two common approaches on both mobile devices and public clouds, using popular convolutional neural networks. Our measurement study suggests the need for both on-device and cloud-based inferences for supporting mobile applications. In particular, newer mobile devices is able to run mobile-optimized CNN models in reasonable time. However, for older mobile devices or to use more complex CNN models, mobile applications should opt in for cloud-based inference. We further demonstrate that variable network conditions can lead to poor cloud-based inference end-to-end time. To support efficient cloud-based inference, we propose a CNN model selection algorithm called CNNSelect that dynamically selects the most appropriate CNN model for each inference request, and adapts its selection to match different SLAs and execution time budgets that are caused by variable mobile environments. The key idea of CNNSelect is to make inference speed and accuracy trade-offs at runtime using a set of CNN models. We demonstrated that CNNSelect smoothly improves inference accuracy while maintaining SLA attainment in 88.5% more cases than a greedy baseline.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑