STM32N6-AI

Description

The STM32N6 AI ecosystem (STM32N6-AI) is STMicroelectronics' collection of tools and resources to support the development and deployment of AI models on the high-performance STM32N6 series microcontrollers.

The STM32N6 microcontroller (MCU) is the first to feature STMicroelectronics' proprietary Neural-ART Accelerator neural processing unit (NPU) for a major leap in AI/ML performance.

STM32N6-AI tools are designed to streamline the development process and ensure that developers can achieve optimal performance and efficiency. They offer support for both bring your own data (BYOD) and bring your own model (BYOM) approaches to match users' best development practices and preferences.

Tools such as STM32 model zoo (github.com/STMicroelectronics/stm32ai-modelzoo), ST Edge AI Developer Cloud (STEDGEAI-DC), STM32Cube.AI (X-CUBE-AI), and ST Edge AI Core (STEdgeAI-Core) mobilize the STM32N6 potential for AI and computer vision (CV) applications.

Additionally, STM32N6-AI offers various software packages that serve as examples and starting points for a user's AI projects:

• For AI: Include simple CV and audio applications such as people detection or image classification, as well as more complex and optimized applications such as pose estimation, instance segmentation, hand landmark detection, and audio scene recognition.
• For video: Demonstrate a complete application involving H264 encoding and USB video device class stream output data to a PC.

Overall, STM32N6-AI provides access to a full ecosystem of software and tools dedicated to help build next-generation machine learning applications at the edge with the STM32N6. The Neural-ART Accelerator NPU embedded in the STM32N6 efficiently handles AI inference tasks and provides an exceptional acceleration for NN models execution. This integration makes edge AI on MCU both practical and widespread, and offers a powerful, efficient, and scalable solution for a diverse range of applications.

The Neural-ART Accelerator is fully supported by ST Edge AI Core, including STM32Cube.AI and ST Edge AI Developer Cloud. These tools optimize the NN models and generate the code to be executed in hardware by the NPU. They analyze the neural network, prepare the data, and map its operators to the appropriate hardware resources to fully leverage the NPU capabilities without hassle and to benefit from optimal AI acceleration. Streamlined support for models from the most popular AI frameworks such as Keras, TensorFlow™, and ONNX ensures a smooth AI development pipeline.

ST Edge AI Suite

All the tools and software packages contributing to the STM32N6 AI ecosystem are part of STMicroelectronics ST Edge AI Suite, which is an integrated collection of software tools designed to facilitate the development and deployment of embedded AI applications. This comprehensive suite supports both optimization and deployment of machine learning algorithms and neural network models, from data collection to the final deployment on hardware, streamlining the workflow for professionals across various disciplines.

The ST Edge AI Suite supports various STMicroelectronics products: STM32 microcontrollers and microprocessors, Neural-ART Accelerator, Stellar microcontrollers, and smart sensors.

The ST Edge AI Suite represents a strategic move to democratize edge AI technology, making it a pivotal resource for developers looking to harness the power of AI in embedded systems efficiently and effectively.