STMicroelectronics releases tools to accelerate MCU edge-AI development
Embedded AI developers and data scientists can use what is believed to be the industry’s first set of tools and services to get edge AI technology on the market faster and with less complexity. The STM32Cube.AI Developer Cloud helps hardware and software decision-making, said STMicroelectronics. It provides access to an extensive suite of online development tools built around the STM32 family of microcontrollers (MCUs).
According to Ricardo De Sa Earp, executive vice president, general purpose microcontroller sub group, STMicroelectronics The “Our goal is to deliver the best hardware, software, and services to meet the challenges faced by embedded developers and data scientists so that they can develop their edge AI application faster and with less hassle”.
The MCU AI Developer Cloud works with the company’s STM32Cube.AI ecosystem. The Developer Cloud tool brings the possibility to remotely benchmark models on STM32 hardware through the cloud to save on workload and cost, added De Sa Earp.
The STM32Cube.AI desktop front end serves the growing demand for edge AI-based systems and includes developer resources to validate and generate optimised STM32 AI libraries from trained Neural Networks. The STM32Cube.AI Developer is the accompanying online version of the tool. It delivers a set of industry firsts, said ST, including an online interface to generate optimised C-code for STM32 microcontrollers, without requiring prior software installation. The proven neural network optimisation supports data scientists and developers to develop edge-AI projects, added ST.
There is also access to the STM32 model zoo, a repository of trainable deep-learning models and demos to speed application development. Initially, use cases, available on GitHub, include human motion sensing for activity recognition and tracking, computer vision for image classification or object detection and audio event detection for audio classification.
The introduction also sees access to what is believed to be the world’s first online benchmarking service for edge-AI neural networks on STM32 boards. The cloud-accessible board farm features a broad range of STM32 boards, refreshed regularly, allowing data scientists and developers to remotely measure the actual performance of the optimised models.