DiReCt: Resource-Aware Dynamic Model Reconfiguration for Convolutional Neural Network in Mobile Systems
DiReCt: Resource-Aware Dynamic Model Reconfiguration for Convolutional Neural Network in Mobile Systems
复制标题
DOI：
10.1145/3218603.3218652
复制
发表时间：
2018-07
期刊：
影响因子：
--
通讯作者：
Zirui Xu;Zhuwei Qin;Fuxun Yu;Chenchen Liu;Xiang Chen
中科院分区：
文献类型：
--
作者：
Zirui Xu;Zhuwei Qin;Fuxun Yu;Chenchen Liu;Xiang Chen
尽管卷积神经网络（CNNs）已广泛应用于各种应用中，但它们在资源受限的移动系统中的部署仍然是一个重大问题。为了克服计算资源的限制，例如有限的内存和能量容量，许多针对移动CNN优化的工作被提出。然而，它们中的大多数缺乏对CNN计算消耗的全面建模分析，并且仅仅关注静态优化方案，而不考虑不同的移动计算场景。在这项工作中，我们提出了DiReCt——一种资源感知的CNN重配置系统。利用精确的CNN计算消耗建模和移动资源约束分析，DiReCt能够以不同的精度和资源消耗水平对CNN进行重配置，以适应各种移动计算场景。实验结果表明：DiReCt中提出的计算消耗模型能够以94.1%的准确率很好地估计CNN的计算消耗，并且DiReCt实现了至多34.9%的计算加速、52.7%的内存减少以及27.1%的节能。最终，DiReCt能够有效地使CNNs适应动态的移动使用场景以实现最佳性能。
Although Convolutional Neural Networks (CNNs) have been widely applied in various applications, their deployment in resource-constrained mobile systems remains a significant concern. To overcome the computation resource constraints, such as limited memory and energy capacity, many works are proposed for mobile CNN optimization. However, most of them lack a comprehensive modeling analysis of the CNN computation consumption and merely focus on static optimization schemes regardless of different mobile computation scenarios. In this work, we proposed DiReCt -- a resource-aware CNN reconfiguration system. Leveraging accurate CNN computation consumption modeling and mobile resource constraint analysis, DiReCt can reconfigure a CNN with different accuracy and resource consumption levels to adapt to various mobile computation scenarios. The experiment results show that: the proposed computation consumption models in DiReCt can well estimate the CNN computation consumption with 94.1% accuracy, and DiReCt achieves at most 34.9% computation acceleration, 52.7% memory reduction, and 27.1% energy saving. Eventually, DiReCt can effectively adapt CNNs to dynamic mobile usage scenarios for optimal performance.