STM32H753ZI and NanoEdgeAI

[LucasCalsing]

I wanted to run ready-made examples for the STM32H753ZI in NanoEdge AI but I couldn't find any. Does anyone have any tips or a ready-made example?

[Julian E.]

Hi @LucasCalsing,

I don’t think there is an example specifically for this board.

NanoEdge AI libraries are straightforward to integrate and are not dependent on a particular hardware platform.

I recommend looking at:

AI:How to Build an Anomaly Detection Project for Predictive Maintenance with NanoEdge AI Studio - stm32mcu

(This is for Anomaly detection, but for all project, the idea is pretty much the same)

The simplest POC you can build is to:

1. Create an MX project for your board with the default settings.
2. In main, allocate a buffer matching the size of the data you used in NanoEdge.
   (You can put random values inside)
3. After including the NanoEdge library, call:
   • an initialization function,
   • optionally a learning function if you are doing anomaly detection,
   • and then the inference function.
4. Finally print the result

And that’s all you need for a basic proof of concept.

Then you would need to configure your sensor and continue your project

You can also look at the example datalogger we published.
I believe all example are doing both datalogging and a simple prediction loop:

GitHub - stm32-hotspot/stm32ai-nanoedge-datalogger: STM32 Application for datalogging feature with NanoEdge AI Studio · GitHub

Have a good day,

Julian