Deploying neural networks on H755ZIQ

[vigneshn10]

I am working on a project where I am required to deploy a Neural network on STM32 Nucleo- H755ZIQ. And I feel stuck because I am unable to properly run it on the board using Stm32CubeIDE with X cube ai. I downloaded the .ioc file and the project files from ST Edge AI Developer Cloud but I could'nt figure out how to properly flash it on the board and verify it. I also cant seem to figure out the clock configuration, usart, and I dont know how to access a serial monitor on mac. I have .csv files to test the model on the board, but I cant figure out where to insert the file for testing. I tried using Simulink hoping it'll be easier but the stm32 hardware support package is not supported on MacOS(M1). 
Can anyone help me out figuring out the pipeline to deploy this model? 
I am fairly new to stm32 MCUs and have limited experience in embedded.
It is a Keras model which takes in ECG data in string arrays and classifies it. Right now I am only feeding the model with .csv files of ecg snippets but in future i would like to expand on real time ecg detection and classification using AD8232 sensor. 

[Julian E.]

Hello @vigneshn10,

 

Using AI and MCUs is a pretty advance topic.

 

I would suggest that you create a new project in CubeMX for the STM32 Nucleo- H755ZIQ board, then enable X Cube AI and select the Application template.

 

After that, browse for your model and use the different option given:

• Analyze: to test if your model passes the ST Edge AI Core generation, is small enough etc
• Validate on desktop: to see if you get differences between your python model and converted C model
• Validate on target: to compare the model performances on the real target.

 

To validate your model with your .csv, I think you need to convert it to a .npz file.

 

Once you have done that, you can give a name to your project and generate the code.

The generated code is an example of running an inference with a random input. That should help you start.

 

Then you can take a look at the ST Model Zoo to go further but still be helped.

GitHub - STMicroelectronics/stm32ai-modelzoo-services: AI Model Zoo services for STM32 devices

 

Have a good day,

Julian