NanoEdge datalogger using STM32N6570-DK

[jmog]

Hi,

I have an STM32N6570-DK evaluation kit that I'm using to build a small ML demo. NanoEdge AI studio has the possibility to record a dataset using the Data Logger functionality. However that currently does not support my evaluation kit, or at least I am not able to find such option. I was hoping to use the inbuilt microphone to record sample data for my demo. Will the STM32N6570-DK be supported in the near future, or can I somehow make this work myself without official support?

[Julian E.]

Hello @jmog,

 

The N6 DK being added to the list of supported board for the data logger generator is unlikely as the N6 is not really a "nanoedge target" if I can say that.

The N6 is a very powerful MCU, kind of overkill for NanoEdge models.

So yes, you need to create the datalogger for this board yourself.

 

But we have the ST Model Zoo with example of applications where you can find an audio event detection application example (neural network application example with audio input data):

https://github.com/STMicroelectronics/stm32ai-modelzoo-services/tree/main/application_code/audio/STM32N6

I think you can look at this to see how the microphone was used.

 

Otherwise, you also have the STM32N6CubePackage that can maybe help you:

GitHub - STMicroelectronics/STM32CubeN6: STM32Cube MCU Full Package for the STM32N6 series - (HAL + LL Drivers, CMSIS Core, CMSIS Device, MW libraries plus a set of Projects running on all boards provided by ST)

 

As I said, you can obviously use the N6 to do Nanoedge project, but it is a bit overkill, and the neural acceleration will not be used.

I suggest looking more about the model zoo and how to adapt neural network with the stedgeai core instead, where the N6 is much more suited. 

 

Have a good day,

Julian

 

 

[jmog]

Hi Julian,

Thank you for the quick response. You are right that the N6 is a very powerful MCU for a small demo like this, but it happens to be what I have and I might eventually use it for something more demanding as well. Thanks again for the linked resources!