The STM32Cube. AI Developer Cloud will allow developers to evaluate performance of the AI models and choose a proper hardware architecture earlier in the process so we can converge more quickly on the development of AI applications.
STMicroelectronics has unveiled the world’s first MCU Edge-AI Developer Cloud. The STM32Cube. AI Developer Cloud opens access to an extensive suite of online development tools built around the STM32 family of microcontrollers (MCUs). The STM32Cube.AI desktop front-end includes the resources for developers to validate and generate optimized STM32 AI libraries from trained Neural Networks. While the STM32Cube.AI Developer Cloud which is an online tool offers interface to generate optimized C-code for STM32 microcontrollers, without requiring prior software installation. This new tool brings the possibility to remotely benchmark models on STM32 hardware through the cloud to save on workload and cost. The tool can be used for various use cases including human motion sensing for activity recognition and tracking, computer vision for image classification or object detection, audio event detection for audio classification, etc.
“The Model zoo, STM32Cube.AI online interface, and remote benchmarking capabilities on STM32 boards makes it easier for our data scientists with various hardware knowledge to evaluate embeddability of AI models into our products’ microcontrollers. Additionally, being capable of testing our models on several STM32 microcontrollers in a few clicks enables us to consider embedded AI processing at an earlier stage in the design process and to take advantage of it to design advanced features.” Didier PELLEGRIN, VP AI Anticipation and Strategy, Schneider Electric.
Serving the growing demand for edge AI-based systems, the STM32Cube.AI desktop front-end includes the resources for developers to validate and generate optimized STM32 AI libraries from trained Neural Networks. ST has also released an online tool called the STM32Cube.AI Developer Cloud, an online version of the tool which simplifies the validation of a process for the developers.
The STM32 Cube ecosystem enables the online interface to generate optimized C-code for STM32 microcontrollers, without requiring prior software installation. It will allow data scientists and developers to utilise the already validated Neural Network optimization performance to develop edge-AI projects.
It opens access to the STM32 model zoo, a repository of trainable deep-learning models and demos to speed application development. Furthermore, the STM32 cube provides access to 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 optimized models.
STMicroelectronics is the largest European semiconductor contract manufacturing and design company. It owns and operates its own semiconductor wafer fabs. The company manufactures MCUs and components for low-powered electronics applications such as embedded system products and even the power electronics components which are used in high-powered grids.