This paper deploys and explores variants of TinyissimoYOLO, a highly flexible and fully quantized ultra-lightweight object detection network designed for edge systems with a power envelope of a few milliwatts. With experimental measurements, we present a comprehensive characterization of the network's detection performance, exploring the impact of various parameters, including input resolution, number of object classes, and hidden layer adjustments. We deploy variants of TinyissimoYOLO on state-of-the-art ultra-low-power extreme edge platforms, presenting an in-depth a comparison on latency, energy efficiency, and their ability to efficiently parallelize the workload. In particular, the paper presents a comparison between a novel parallel RISC-V processor (GAP9 from Greenwaves) with and without use of its on-chip hardware accelerator, an ARM Cortex-M7 core (STM32H7 from ST Microelectronics), two ARM Cortex-M4 cores (STM32L4 from STM and Apollo4b from Ambiq), and a multi-core platform with a CNN hardware accelerator (Analog Devices MAX78000). Experimental results show that the GAP9's hardware accelerator achieves the lowest inference latency and energy at 2.12ms and 150uJ respectively, which is around 2x faster and 20% more efficient than the next best platform, the MAX78000. The hardware accelerator of GAP9 can even run an increased resolution version of TinyissimoYOLO with 112x112 pixels and 10 detection classes within 3.2ms, consuming 245uJ. To showcase the competitiveness of a versatile general-purpose system we also deployed and profiled a multi-core implementation on GAP9 at different operating points, achieving 11.3ms with the lowest-latency and 490uJ with the most energy-efficient configuration. With this paper, we demonstrate the suitability and flexibility of TinyissimoYOLO on state-of-the-art detection datasets for real-time ultra-low-power edge inference.

翻译：本文部署并探索了TinyissimoYOLO的多种变体——这是一种专为功耗仅数毫瓦的边缘系统设计的高度灵活且全量化的超轻量级目标检测网络。通过实验测量，我们全面表征了网络的检测性能，探究了输入分辨率、目标类别数量及隐藏层调整等参数的影响。我们在最先进的超低功耗极限边缘平台上部署了多种TinyissimoYOLO变体，深入比较了延迟、能效及并行化工作效率。特别地，本文对比了新型并行化RISC-V处理器（Greenwaves公司的GAP9，含/不含片上硬件加速器）、ARM Cortex-M7内核（意法半导体的STM32H7）、两款ARM Cortex-M4内核（ST微电子公司的STM32L4与Ambiq公司的Apollo4b）以及搭载CNN硬件加速器的多核平台（Analog Devices的MAX78000）。实验结果表明，GAP9的硬件加速器实现了最低推理延迟（2.12ms）和最低能耗（150uJ），性能较次优平台MAX78000提升约2倍且能效提高20%。GAP9的硬件加速器甚至能以112×112像素分辨率及10个检测类别运行增强版的TinyissimoYOLO，延迟仅3.2ms、能耗245uJ。为展示通用型多功能系统的竞争力，我们还部署并分析了GAP9多核实现方案在不同工作点下的性能表现——最低延迟配置下耗时11.3ms，最高能效配置下能耗490uJ。通过本文，我们证明了TinyissimoYOLO在面向实时超低功耗边缘推理的最先进检测数据集上的适用性与灵活性。