YOLOv8n Integration Issues in People Detection and Tracking Demo on STM32N6570-DK

[DavidNgan]

I tried to use YOLOv8n instead of YOLOX in the people detection and tracking project. However, after modifying the related files (app_config.h, postprocess_conf.h, and main.c) and generating the model weights for YOLOv8n, the people detection and tracking demo does not work as expected. I can build and boot the program through dev mode, but no tracking boxes or text overlays (e.g. inference speed) are displayed—only raw camera capture is shown.

What is the possible issue that happened, and how should I debug? What addtional infromation should i provide?

[Julian E.]

Hi @DavidNgan,

I suggest you use the st model zoo services: 

STMicroelectronics/stm32ai-modelzoo-services: AI Model Zoo services for STM32 devices

I attached a zip containing the yaml to deploy the model with model zoo services and the model I took form ultralytics.

After deployment, you can look at stm32ai-modelzoo-services\application_code\object_detection\STM32N6\Application\STM32N6570-DK to find the source code and in particular, how the app_config.h was edited.

Have a good day,

Julian