Today we launched Edge Impulse: TinyML as a service to enable machine learning for all developers with an open source device SDK. Edge Impulse enables the easy collection of real sensor data, live signal processing from raw data to neural networks, testing and deployment to any target device. Sign up for a free developer account and get started with the ST IoT Discovery board. Our open source SDKs allow you to collect data from or deploy code to any device.
TinyML enables exciting applications on extremely low-power MCUs. For example, we can detect human motion from just 10 minutes of training data, detect human keywords and classify audio patterns from the environment in real-time. We have prepared some example projects with videos to show you how!
- Getting started with Edge Impulse
- Alex Glow working on TinyML (Video)
- Building a continuous motion detection system (Video)
- Building an audio classifier (Video)
Semiconductor leader STMicroelectronics is supporting the launch of the platform on the STM32 family of microcontrollers that further expands the STM32Cube.AI ecosystem. "TinyML is opening up exciting new Machine-Learning applications for embedded devices and working with Edge Impulse allows us to quickly enable the software developer community on STM32," says Raphael Apfeldorfer, Head of AI Solution Marketing at STMicroelectronics.
Edge Impulse is a developer platform, where users can contribute to and extend both algorithms and target device support. Device software including SDKs, clients and generated code are provided as open source under an Apache 2.0 license. Get involved with porting and extending our GitHub repositories here. We collaborate with the TensorFlow Lite Micro project to support the widest range of ML architectures, operators and targets.
Machine learning at the very edge will enable valuable use of the 99% of sensor data that is discarded today due to cost, bandwidth or power constraints. A huge variety of inputs can be processed including radar, motion, electromagnetic fields, audio, images and device logs. TinyML will have a big impact across industries including health, white goods, mobility, industry, retail and agriculture. Read more from Fika Ventures about the market opportunity for TinyML.
Edge Impulse is free for individual developers as we believe in enabling innovation. An enterprise version is available by subscription for world class teams deploying TinyML in innovative products.