Edge Impulse: An MLOps Platform for Tiny Machine Learning

TL;DR

Edge Impulse is a cloud-based MLOps platform that simplifies the development and deployment of TinyML systems across diverse hardware, addressing fragmentation and optimization challenges in embedded machine learning.

Contribution

The paper introduces Edge Impulse, a comprehensive MLOps platform that streamlines TinyML development, offering extensible, portable software stacks for heterogeneous embedded hardware.

Findings

Hosts over 118,000 projects from nearly 51,000 developers

Supports various software and hardware optimizations for TinyML

Facilitates scalable and portable TinyML system development

Abstract

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.