Dynamic neural networks (DyNNs) have become viable techniques to enable intelligence on resource-constrained edge devices while maintaining computational efficiency. In many cases, the implementation of DyNNs can be sub-optimal due to its underlying backbone architecture being developed at the design stage independent of both: (i) the dynamic computing features, e.g. early exiting, and (ii) the resource efficiency features of the underlying hardware, e.g., dynamic voltage and frequency scaling (DVFS). Addressing this, we present HADAS, a novel Hardware-Aware Dynamic Neural Architecture Search framework that realizes DyNN architectures whose backbone, early exiting features, and DVFS settings have been jointly optimized to maximize performance and resource efficiency. Our experiments using the CIFAR-100 dataset and a diverse set of edge computing platforms have seen HADAS dynamic models achieve up to 57% energy efficiency gains compared to the conventional dynamic ones while maintaining the desired level of accuracy scores. Our code is available at https://github.com/HalimaBouzidi/HADAS
translated by 谷歌翻译
量化是在嵌入式系统或手机上部署训练有素的DNN模型时,是最应用的深神经网络(DNN)压缩策略之一。这是由于其对广泛的应用和情况的简单性和适应性,而不是特定的人工智能(AI)加速器和编译器,这些加速器和编译器通常仅用于某些特定的硬件(例如Google Coral Edge TPU)。随着对量化的需求不断增长,确保该策略的可靠性成为一个关键挑战。传统的测试方法收集越来越多的真实数据以进行更好的评估,通常是不切实际的,因为输入空间的尺寸很大,并且原始DNN及其量化的对应物之间的相似性很高。结果,高级评估策略已变得至关重要。在本文中,我们提出了Diverget,这是一个基于搜索的测试框架,用于量化评估。 Diverget定义了变质关系的空间,该空间模拟了输入上的自然扭曲。然后,它最佳地探索了这些关系,以揭示不同算术精度的DNN之间的分歧。我们评估了应用于高光谱遥感图像的最先进的DNN上的Diverget的性能。我们选择了遥感DNN,因为它们越来越多地部署在诸如气候变化研究和天文学之类的关键领域中的边缘(例如,高级无人机)。我们的结果表明,Diverget成功地挑战了已建立的量化技术的鲁棒性,以防止自然变化的数据,并胜过其最新的并发,Diffchaser,其成功率(平均)是四倍。
translated by 谷歌翻译