arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.09503cs.CV
收藏

移动设备上卷积神经网络的资源需求建模

Modeling the Resource Requirements of Convolutional Neural Networks on Mobile Devices

Peking University(北京大学);IBM Research(IBM研究院);Army Research Laboratory(陆军研究实验室);Pennsylvania State University(宾夕法尼亚州立大学)

Zongqing Lu, Swati Rallapalli, Kevin Chan, Thomas La Porta

摘要:

卷积神经网络(CNN)具有捕捉复杂模式的能力,具有很高的推理精度,从而彻底改变了计算机视觉的研究。然而,这些神经网络日益复杂的性质意味着它们特别适合具有强大GPU的服务器计算机。我们设想,深度学习应用最终将广泛部署在移动设备上,例如,智能手机、自动驾驶汽车和无人机。因此,在本文中,我们的目标是了解移动设备上CNN的资源需求(时间,内存)。首先,通过在移动CPU和GPU上部署几种流行的CNN,我们测量和分析了CNN每一层的性能和资源使用情况。我们的研究结果指出了优化移动设备性能的潜在方法。其次,我们对不同CNN计算的资源需求进行建模。最后,基于测量、分析和建模,我们构建并评估了我们的建模工具Augur,该工具以CNN配置(描述符)作为输入,并估计了CNN的计算时间和资源使用情况,以了解CNN是否以及如何有效地在给定的移动平台上运行。在这样做的过程中,Augur解决了几个挑战:(i)如何克服proling和测量开销;(ii)如何捕获具有不同处理器,内存和缓存大小的不同移动平台的差异;以及(iii)如何考虑不同CNN配置的层数,类型和大小的差异。

英文摘要:

Convolutional Neural Networks (CNNs) have revolutionized the research in computer vision, due to their ability to capture complex patterns, resulting in high inference accuracies. However, the increasingly complex nature of these neural networks means that they are particularly suited for server computers with powerful GPUs. We envision that deep learning applications will be eventually and widely deployed on mobile devices, e.g., smartphones, self-driving cars, and drones. Therefore, in this paper, we aim to understand the resource requirements (time, memory) of CNNs on mobile devices. First, by deploying several popular CNNs on mobile CPUs and GPUs, we measure and analyze the performance and resource usage for every layer of the CNNs. Our findings point out the potential ways of optimizing the performance on mobile devices. Second, we model the resource requirements of the different CNN computations. Finally, based on the measurement, pro ling, and modeling, we build and evaluate our modeling tool, Augur, which takes a CNN configuration (descriptor) as the input and estimates the compute time and resource usage of the CNN, to give insights about whether and how e ciently a CNN can be run on a given mobile platform. In doing so Augur tackles several challenges: (i) how to overcome pro ling and measurement overhead; (ii) how to capture the variance in different mobile platforms with different processors, memory, and cache sizes; and (iii) how to account for the variance in the number, type and size of layers of the different CNN configurations.

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。

↑