论文标题
边缘冲动：小型机器学习的MLOPS平台
Edge Impulse: An MLOps Platform for Tiny Machine Learning
论文作者
论文摘要
Edge Impulse是一个基于云的机器学习操作（MLOPS）平台，用于开发嵌入式和边缘ML（Tinyml）系统，可以部署到广泛的硬件目标。当前的Tinyml工作流程受到零散的软件堆栈和异质部署硬件的困扰，这使得ML模型优化变得困难且无法保持。我们提出了Edge Impulse，这是一个实用的MLOP平台，用于大规模开发Tinyml系统。 Edge Impulse通过支持各种软件和硬件优化，以为多种嵌入式系统创建可扩展且可移植的软件堆栈来解决这些挑战，并简化TinyML设计周期。截至2022年10月，Edge Impulse拥有来自50,953个开发商的118,185个项目。
Edge Impulse is a cloud-based machine learning operations (MLOps) platform for developing embedded and edge ML (TinyML) systems that can be deployed to a wide range of hardware targets. Current TinyML workflows are plagued by fragmented software stacks and heterogeneous deployment hardware, making ML model optimizations difficult and unportable. We present Edge Impulse, a practical MLOps platform for developing TinyML systems at scale. Edge Impulse addresses these challenges and streamlines the TinyML design cycle by supporting various software and hardware optimizations to create an extensible and portable software stack for a multitude of embedded systems. As of Oct. 2022, Edge Impulse hosts 118,185 projects from 50,953 developers.
