STMicroelectronics has redesigned the workflow in ST Edge AI Suite, bringing together four new tools that streamline the deployment of embedded machine learning models on STM32 microcontrollers.
Four tools for model development and testing
Model Explorer provides a web interface for browsing and selecting pre-trained AI models previously available through the Model Zoo GitHub repository. Dataset Factory helps users capture raw data and turn it into reliable datasets. Model Factory supports application-specific training, customisation, quantisation and other refinements, helping users optimise models for STM32 microcontrollers. Model Bench provides a web interface for benchmarking models remotely on ST’s board farm, allowing users to validate performance before deployment. It replaces ST Edge AI Developer Cloud.
“Working efficiently with AI models is a priority for designers as local inference becomes a defining aspect of today’s smart products,” said Stephane Henry, vice president of the Edge AI Solution Group at STMicroelectronics. “Today we have the largest collection of AI models of any microcontroller vendor, with over 400 pre-trained models including a large selection for sensing applications; aka physical AI. With Model Explorer, Model Factory, Dataset Factory and Model Bench in ST Edge AI Suite, we now consolidate this support in an environment purpose-built for designers targeting STM32 devices.”
ST supports more than 260,000 projects through Edge AI Suite, and the number continues to grow. Its user community includes engineers at major technology companies, start-ups and independent developers.
From consumer electronics to industrial sensors, controls, medical devices and automotive systems, embedded AI can help engineers add features while meeting performance and power consumption targets. Engineers need tools to select models, adapt them to the application, optimise memory and processing requirements, and validate performance on the target hardware.
Connecting developers to the STM32 ecosystem
ST Edge AI Suite connects users with the wider STM32 ecosystem, which includes more than 4,000 commercial part numbers. The associated STM32Cube ecosystem provides tools for selecting and configuring microcontrollers, offers software libraries and code examples, and lets users work in their preferred integrated development environment (IDE). It also connects users with evaluation hardware, from low-cost STM32 Nucleo boards to full-featured Discovery kits, as well as expansion cards for wireless connectivity, vision, time-of-flight sensing, IoT sensing and motor drives.
The new tools will be available in late November. Register to be notified.
To use the current version, visit ST Edge AI Suite.
Read other recent instrumentation news: https://instrumentation.co.uk/category/news/
