Hardware-aware Neural Architecture Search (NAS) technologies have been proposed to automate and speed up model design to meet both quality and inference efficiency requirements on a given hardware. Prior arts have shown the capability of NAS on hardware specific network design. In this whitepaper, we further extend the use of NAS to Intel Movidius VPU (Vision Processor Units). To determine the hardware-cost to be incorporated into the NAS process, we introduced two methods: pre-collected hardware-cost on device and device-specific hardware-cost model VPUNN. With the help of NAS, for classification task on VPU, we can achieve 1.3x fps acceleration over Mobilenet-v2-1.4 and 2.2x acceleration over Resnet50 with the same accuracy score. For super resolution task on VPU, we can achieve 1.08x PSNR and 6x higher fps compared with EDSR3.

翻译：硬件感知神经架构搜索（NAS）技术已被提出，用于自动化并加速模型设计，以满足特定硬件上的质量与推理效率需求。已有研究展示了NAS在硬件专用网络设计上的能力。在本白皮书中，我们进一步将NAS的应用扩展到英特尔Movidius VPU（视觉处理器单元）。为确定纳入NAS流程的硬件成本，我们引入了两种方法：设备上预采集的硬件成本及设备专属的硬件成本模型VPUNN。借助NAS，在VPU上的分类任务中，我们可在相同准确率下实现相比Mobilenet-v2-1.4快1.3倍的帧率加速，以及相比Resnet50快2.2倍的加速。在VPU上的超分辨率任务中，相较于EDSR3，我们可实现1.08倍PSNR提升及6倍帧率提升。