Getting Started with STM32N6 Vision: Running Your First Object Detection Model
A hands-on walkthrough for deploying a pretrained YOLOv8n model to the STM32N6's onboard NPU, from toolchain setup to reading live detection results off a camera feed.
A hands-on walkthrough for deploying a pretrained YOLOv8n model to the STM32N6's onboard NPU, from toolchain setup to reading live detection results off a camera feed.
The STM32N6 includes a dedicated hardware NPU delivering up to 600 GOPS. This article explains what the NPU is, how it compares to running inference on a Cortex-M7, what models it supports, and the full STM32Cube.AI deployment pipeline for the NVX-N6 Vision board.