Hardware-aware Neural Architecture Search (HW-NAS) is increasingly being used to design efficient deep learning architectures. An efficient and flexible search space is crucial to the success of HW-NAS. Current approaches focus on designing a macro-architecture and searching for the architecture's hyperparameters based on a set of possible values. This approach is biased by the expertise of deep learning (DL) engineers and standard modeling approaches. In this paper, we present a Grassroots Operator Search (GOS) methodology. Our HW-NAS adapts a given model for edge devices by searching for efficient operator replacement. We express each operator as a set of mathematical instructions that capture its behavior. The mathematical instructions are then used as the basis for searching and selecting efficient replacement operators that maintain the accuracy of the original model while reducing computational complexity. Our approach is grassroots since it relies on the mathematical foundations to construct new and efficient operators for DL architectures. We demonstrate on various DL models, that our method consistently outperforms the original models on two edge devices, namely Redmi Note 7S and Raspberry Pi3, with a minimum of 2.2x speedup while maintaining high accuracy. Additionally, we showcase a use case of our GOS approach in pulse rate estimation on wristband devices, where we achieve state-of-the-art performance, while maintaining reduced computational complexity, demonstrating the effectiveness of our approach in practical applications.

翻译：硬件感知神经架构搜索（HW-NAS）正越来越多地被用于设计高效的深度学习架构。一个高效且灵活的搜索空间对HW-NAS的成功至关重要。当前的方法主要聚焦于设计宏观架构，并基于一组可能值搜索该架构的超参数。这种方法受深度学习工程师的专家经验以及标准建模方式的影响而存在偏差。在本文中，我们提出一种草根算子搜索（GOS）方法论。我们的HW-NAS通过搜索高效的算子替换来适配给定模型以适应边缘设备。我们将每个算子表示为一组能够捕获其行为的数学指令。随后，这些数学指令被用作搜索和选择高效替换算子的基础，这些算子能在保持原始模型精度的同时降低计算复杂度。我们的方法是草根式的，因为它依赖于数学基础来为深度学习架构构建新的高效算子。我们在多种深度学习模型上证明，我们的方法在Redmi Note 7S和Raspberry Pi3两种边缘设备上始终优于原始模型，在保持高精度的同时实现了至少2.2倍的加速。此外，我们展示了GOS方法在腕带设备脉搏率估计中的应用案例，在该案例中我们实现了当前最佳性能，同时保持了较低的计算复杂度，证明了我们的方法在实际应用中的有效性。