To speed up the prototyping and development of embedded AI systems, STMicroelectronics has released new models and improved project support for its STM32 AI Model Zoo. With wearables, smart cameras and sensors, robotics, security and safety devices, and other devices, the company affirms it as a siginnificant expansion to what is noted as the industry’s greatest library of models for vision, audio, and sensing.
By embedding AI into everyday accessories, appliances, and other electrical devices, the technology’s revolutionary potential is unlocked while boosting productivity and conserving energy.
Compact microcontrollers, which have limited processing and memory by design, are at the heart of these devices, making it difficult for product developers to optimize AI models for both efficiency and performance. With the help of ST’s most recent STM32 AI Model Zoo, designers can make the most of the resources at their disposal and produce extremely effective models that use very little power.
This STM32 AI Model Zoo is part of the ST Edge AI Suite, which provides an extensive set of tools, libraries, and utilities that further streamline and expedite the development and implementation of AI algorithms on ST hardware, ensuring a seamless integration from prototype to production.
With the aim of assisting developers in overcoming the challenges of implementing AI at the edge with both software and hardware accelerated models, ST has been at the forefront of edge AI research, innovation, and development for more than ten years. Over 160,000 projects are still supported by ST’s AI tools every year.
The majority of the popular microcontrollers in the world are found in ST’s STM32 family, which is employed in a variety of applications such as wearables, consumer appliances, communication infrastructure, smart grids, smart cities, industrial automation, and even low-Earth-orbit satellites.
ST provides cutting-edge technology to end users quickly and affordably while improving sustainability by deliberately enabling AI adoption on general-purpose MCUs across different sectors.
Leadership Comments
“Turning data science into a working application tuned for an embedded platform is a complex engineering challenge, and developers need support throughout the journey,” said Stephane Henry, Edge AI Solution Group VP at STMicroelectronics. “While expanding the selection of models available, to help the STM32 developer community jump-start their projects, we are also strengthening the infrastructure all the way to deployment with STM32 AI Model Zoo 4.0. This is part of our commitment to make Physical AI a reality.”
To positions itself at the forefront of the fast-growing embedded AI, or edge AI market, the company also expanded its portfolio with AI-accelerated MCUs, such as the STM32N6 series.
Available as a standalone solution at: https://github.com/STMicroelectronics/stm32ai-modelzoo/
