arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2112.09852cs.CV
收藏

LegoDNN:移动视觉深度神经网络的块粒度缩放

LegoDNN: Block-grained Scaling of Deep Neural Networks for Mobile Vision

Beijing Institute of Technology(北京理工大学);Midea Group(美的集团);TU Delft(代尔夫特理工大学)

Rui Han, Qinglong Zhang, Chi Harold Liu, Guoren Wang, Jian Tang, Lydia Y. Chen

摘要:

深度神经网络(DNN)已经成为移动和嵌入式系统中用于诸如图像/对象识别和分类的应用的普遍存在的技术。同时执行多个DNN的趋势加剧了满足资源受限的移动设备上的严格延迟/准确性要求的现有限制。现有技术揭示了通过根据资源动态缩放模型大小来探索准确性-资源权衡。然而,这样的模型缩放方法面临着迫在眉睫的挑战:(i)模型大小的大空间探索,以及(ii)不同模型组合的训练时间过长。在本文中,我们提出了LegoDNN,这是一种轻量级的块粒度扩展解决方案,用于在移动视觉系统中运行多DNN工作负载。LegoDNN通过只提取和训练DNN中的少量公共块(例如VGG中的5个和ResNet中的8个)来保证较短的模型训练时间。在运行时,LegoDNN最佳地结合了这些块的后代模型,以在特定资源和延迟约束下最大限度地提高准确性,同时通过DNN的智能块级缩放来减少切换开销。我们在TensorFlow Lite中实现了LegoDNN,并使用一组12个流行的DNN模型,针对最先进的技术(FLOP缩放,知识蒸馏和模型压缩)对其进行了广泛的评估。评估结果表明,LegoDNN在不增加训练时间的情况下,在模型大小上提供了1,296倍到279,936倍的选择,从而实现了高达31.74%的推理准确性提高和71.07%的缩放能耗降低。

英文摘要:

Deep neural networks (DNNs) have become ubiquitous techniques in mobile and embedded systems for applications such as image/object recognition and classification. The trend of executing multiple DNNs simultaneously exacerbate the existing limitations of meeting stringent latency/accuracy requirements on resource constrained mobile devices. The prior art sheds light on exploring the accuracy-resource tradeoff by scaling the model sizes in accordance to resource dynamics. However, such model scaling approaches face to imminent challenges: (i) large space exploration of model sizes, and (ii) prohibitively long training time for different model combinations. In this paper, we present LegoDNN, a lightweight, block-grained scaling solution for running multi-DNN workloads in mobile vision systems. LegoDNN guarantees short model training times by only extracting and training a small number of common blocks (e.g. 5 in VGG and 8 in ResNet) in a DNN. At run-time, LegoDNN optimally combines the descendant models of these blocks to maximize accuracy under specific resources and latency constraints, while reducing switching overhead via smart block-level scaling of the DNN. We implement LegoDNN in TensorFlow Lite and extensively evaluate it against state-of-the-art techniques (FLOP scaling, knowledge distillation and model compression) using a set of 12 popular DNN models. Evaluation results show that LegoDNN provides 1,296x to 279,936x more options in model sizes without increasing training time, thus achieving as much as 31.74% improvement in inference accuracy and 71.07% reduction in scaling energy consumptions.

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。

↑