STMicroelectronics streamlines AI model development for STM32 developers

STMicroelectronics has redesigned the workflow in ST Edge AI Suite, consolidating the developer environment with four new tools that streamline deployment of embedded machine-learning models on STM32 microcontrollers.

Model Explorer – the first new tool in the latest update – provides an intuitive web interface for users to browse and find the right AI model among the pre-trained models that were previously accessible though Model Zoo Github repository. Dataset Factory helps capture and transform raw data into usable, reliable datasets. Model Factory assists application-targeted training, customization, quantization, and additional refinements, and helps optimize models for STM32 MCUs. To validate performance before deployment, Model Bench gives users a web interface for benchmarking models on hardware remotely by leveraging the ST board farm. Model Bench 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, Edge AI Solution Group VP 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 over 260,000 projects through Edge AI Suite and the number is growing continuously. The user community includes engineers in major blue-chip technology brands and companies of all sizes including startups and independent developers.

From consumer electronics to industrial sensors, controls, medical devices, and automotive systems, embedded AI holds the key to delivering competitive capabilities, performance, and power consumption. Engineers need next-generation tools and workflows that are built for selecting models and adapting them to the use case, optimizing memory and compute, and validating performance on target hardware.

ST Edge AI Suite connects users with the broader STM32 ecosystem that contains over 4,000 commercial part numbers. The associated powerful STM32Cube ecosystem provides tools to select and configure MCUs, contains software libraries and code examples, and lets users work within their preferred integrated development environment (IDE). STM32Cube also connects users with evaluation hardware, from low-cost STM32 Nucleo boards to full-featured Discovery kits, and expansion cards such as wireless connectivity, vision, time-of-flight, IoT sensing, motor drives, and more.

The new tools will be available in late November. Register to be notified at https://content.st.com/new-stm32-edge-ai-tools.html.

To use the current version of ST Edge AI Suite, go to https://www.st.com/edge-ai-suite

STM32 is a registered and/or unregistered trademark of STMicroelectronics International NV or its affiliates in the EU and/or elsewhere. In particular, STM32 is registered in the US Patent and Trademark Office.