How to integrate Edge AI Developer Cloud generated NPU code into STM32N6570‑DK project?

[Duc]

Hello,

I am working with the STM32N6570‑DK discovery kit and using the ST Edge AI Developer Cloud to generate code for my neural network. The tool produces a project with multiple files (model, runtime, headers, etc.), but I am struggling to understand how to actually integrate this into my STM32N6 application.

Specifically, I would like to know:

• What is the expected input format (tensor dimensions, quantization type) and how do I feed my sensor/camera data into it?

• How do I retrieve the output from the inference (classification vector, bounding boxes, etc.) and use it in my application logic?

• How should I connect the generated code with my application (main loop, data acquisition from camera/audio, etc.)?

I have looked through the STM32N6 examples and documentation, but they don’t clearly explain how to bridge the generated AI code with a working application. Any guidance or pointers to documentation/examples would be greatly appreciated.

Thanks in advance!

[Julian E.]

Hello @Duc,

We are working on better documentation regarding the use of the N6, but for now, we have the following that can help you.

First you have multiple packages showcasing different usecases. The getting started ones are the simpliest BareMetal application that we have. You can find all of these here:

STM32N6-AI | Software - STMicroelectronics

Then, we have the documentation of the ST Edge AI Core (and in particular the part about the N6) here: https://stedgeai-dc.st.com/assets/embedded-docs/index.html

And lastly, we have a tutorial on how to create a project from scratch. Note that the N6 is not well supported by cubeMX (which is why the getting started are not done with it), but it can be interesting for you to look at the part of the tutorial presenting the main code, to better understand the inputs and outputs:

How to build an AI application from scratch on the... - STMicroelectronics Community

Have a good day,

Julian

[Duc]

Hi @Julian E. ,

Thank you for your reply. I had reviewed those documents before raising my question, but I’m glad to hear that your team is working on improving the documentation for the STM32N6.