Dear ST community,
We've been evaluating STM32N6 NPU since early january. We aim to deploy yolov8n / yolov11n inside the NPU.
So far we've been able to use modelzoo provided by ST. We weren't able to do the same with yolov8 or yolov11n we trained using ultralytics scripts.
Here the procedure we applied :
- Download repo modelzoo and modelzoo-services
- Verify that stm32ai_main.py associated with deployment_n6_yolo11n_config.yaml does work (it does, we just modify it to target Nucleo board)
- Download / train yolov11n model using ultralytics framework use same input dimensions; export to Tflite format
- Use ST script to quantize tflite mode (tflite_quant.py)
- Import the quantized tflite model and modify the .yaml to use our trained model instead of the ST version.
- Let the design flow execute
After that, nothing happen on the board. I've opened STM32Cube to see what happens on debug level. When reaching Run_Inference the NPU sort of "stall" (infinite loop in hardware error some sort)
Attached to this post :
- Yolov11n model we trained / quantize
- Yolov8n model we trained / quantize
- .yaml configuration we use to deploy on Nucleo
Has anyone managed to deploy a yolov11n on this target ?
Best regards,
