Machine vision tasks present challenges for resource constrained edge devices, particularly as they execute multiple tasks with variable workloads. A robust approach that can dynamically adapt in runtime while maintaining the maximum quality of service (QoS) within resource constraints, is needed. The paper presents a lightweight approach that monitors the runtime workload constraint and leverages accuracy-throughput trade-off. Optimisation techniques are included which find the configurations for each task for optimal accuracy, energy and memory and manages transparent switching between configurations. For an accuracy drop of 1%, we show a 1.6x higher achieved frame processing rate with further improvements possible at lower accuracy.

翻译：机器的愿景任务对资源有限的边缘装置提出了挑战,特别是当它们执行多种任务,工作量变化不定时。需要一种强有力的方法,既能在运行时动态适应,同时又在资源限制范围内维持最高服务质量(Qos),文件提出了一种轻量级方法,用以监测运行时工作量限制,并利用准确性-吞吐权衡。优化技术包括找到每项任务的配置,以便实现最佳准确性、能量和内存,并管理各种配置之间的透明转换。准确性下降1%,我们显示出1.6x更高的框架处理率,并有可能以更低的精确度进一步改进。