How to deploy a custom PyTorch AI model on the STM32N6570?

[llcc]

I want to deploy a PyTorch AI model on the STM32N6570. I have already trained the model and converted it to an ONNX file. I’m looking for a quantization, compilation, and deployment example or tutorial. The speech enhancement example in the STM32 AI Model Zoo Services doesn't match my use case. Although the input shape is the same, my model does not require any pre-processing. I only want to feed input data into the model and observe the output. Also, I would like to know if it's possible to perform deployment without providing a dataset.

[Julian E.]

Hello @llcc,

To do so you need to store your application and model in external flash (to avoid being erased on reboot) and create a FSBL to load your application and model to the internal ram on startup.

You can read more about that here:

https://community.st.com/t5/stm32-mcus/how-to-create-an-stm32n6-fsbl-load-and-run/ta-p/768206

We are also working on a tutorial for the DK board that should explain that.

Have a good day,

Julian