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
翻译:动态神经网络(DyNNS)已成为可行的技术,在保持计算效率的同时,能够对受资源限制的边缘装置提供情报,同时保持计算效率;在许多情况下,由于DyNNS在设计阶段所开发的基本主干结构独立于两个设计阶段:(一) 动态计算特征,例如早期退出,以及(二) 基础硬件的资源效率特征,例如动态电压和频率缩放(DVFS),因此DyNS的落实可能不尽理想,因为其基础主干结构在设计阶段是开发的:(一) 动态计算特征,例如早期退出;(二) 动态电压和频率缩放(DVFS) 基础硬件的资源效率特征。针对这一点,我们介绍了HANAS,这是一个新的硬件-Aware动态神经结构搜索框架,实现了DyNNE的骨干结构、早期退出功能和DVFS设置的优化,以最大限度地提高性能和资源效率。我们利用CIFAR-100数据集和多种边缘计算平台的实验发现,HADAS的动态模型与常规动态动力模型相比,实现了高达57%的能源效率增益,同时保持理想的准确分数。我们的代码可在http://gith/Halimabouzid/HADAS查阅。