MCUNet：在IoT设备上进行微型深度学习
MCUNet: Tiny Deep Learning on IoT Devices
摘要：
基于微控制器单元（MCU）的微型物联网设备上的机器学习很有吸引力，但也很有挑战性：微控制器的内存甚至比手机小2-3个数量级。我们提出MCUNet，一个框架，共同设计的高效神经架构（TinyNAS）和轻量级推理引擎（TinyEngine），使微控制器上的ImageNet规模的推理。TinyNAS采用两阶段神经架构搜索方法，首先优化搜索空间以适应资源约束，然后在优化的搜索空间中专门化网络架构。TinyNAS可以在低搜索成本下自动处理各种约束（即设备，延迟，能源，内存）。TinyNAS与TinyEngine共同设计，TinyEngine是一个内存高效的推理库，可以扩展搜索空间并适合更大的模型。TinyEngine根据整体网络拓扑而不是分层优化来调整内存调度，与TF-Lite Micro和CMSIS-NN相比，内存使用量减少了4.8倍，推理速度加快了1.7- 3.3倍。MCUNet是第一个在现成的商业微控制器上实现ImageNet top1精度>70%的产品，与量化的MobileNetV 2和ResNet-18相比，使用的SRAM和Flash减少了3.5倍。在视觉和音频唤醒词任务上，MCUNet实现了最先进的准确性，运行速度比MobileNetV 2和基于ProxylessNAS的解决方案快2.4- 3.4倍，峰值SRAM小3.7- 4.1倍。我们的研究表明，物联网设备上始终在线的微型机器学习时代已经到来。代码和模型可以在这里找到：https://tinyml.mit.edu。
英文摘要：
Machine learning on tiny IoT devices based on microcontroller units (MCU) is appealing but challenging: the memory of microcontrollers is 2-3 orders of magnitude smaller even than mobile phones. We propose MCUNet, a framework that jointly designs the efficient neural architecture (TinyNAS) and the lightweight inference engine (TinyEngine), enabling ImageNet-scale inference on microcontrollers. TinyNAS adopts a two-stage neural architecture search approach that first optimizes the search space to fit the resource constraints, then specializes the network architecture in the optimized search space. TinyNAS can automatically handle diverse constraints (i.e.device, latency, energy, memory) under low search costs.TinyNAS is co-designed with TinyEngine, a memory-efficient inference library to expand the search space and fit a larger model. TinyEngine adapts the memory scheduling according to the overall network topology rather than layer-wise optimization, reducing the memory usage by 4.8x, and accelerating the inference by 1.7-3.3x compared to TF-Lite Micro and CMSIS-NN. MCUNet is the first to achieves >70% ImageNet top1 accuracy on an off-the-shelf commercial microcontroller, using 3.5x less SRAM and 5.7x less Flash compared to quantized MobileNetV2 and ResNet-18. On visual&audio wake words tasks, MCUNet achieves state-of-the-art accuracy and runs 2.4-3.4x faster than MobileNetV2 and ProxylessNAS-based solutions with 3.7-4.1x smaller peak SRAM. Our study suggests that the era of always-on tiny machine learning on IoT devices has arrived. Code and models can be found here: https://tinyml.mit.edu.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
