Support for autogenerated code by STM32Cube.AI

[FCata]

Good morning,

I have created a project with CubeMX.AI based on an .h5 file constructed in keras following the steps shown on ST tutorial

https://www.youtube.com/watch?v=grgNXdkmzzQ (Getting Started with STM32Cube.AI).

Is it possibile to have an example showing how to exploit the generated code in order to solve

a generic problem of classification for a new sample of data?

Best regards

[Sbv]

Hi,

Did you find answer to this question?I am also looking for the same.

[Romain LE DONGE]

Hi,

If you're looking for an example of code using X-Cube-AI for a custom project you can check this GitHub link:

https://github.com/ROC5COR/HousePricePredictionOnSTM32

This project uses an old version of X-Cube-AI v3.3.0 but the idea is here.

However the project is not a classification but a regression problem (House prices prediction) but you can just get rid of the output prediction and use a threshold to make it a classification problem with your own NN

Hope this can help you :)

Romain