Guidelines for ASC from FP-AI-SENSING1

[MSant.11]

Did you ever prepare a guideline like this one https://wiki.st.com/stm32mcu/wiki/AI:How_to_perform_motion_sensing_on_STM32L4_IoTnode but for ASC instead?

I have my own two-classes NN, keras model and the B-L475E-IOT01.

After replacing asc and asc_data files in the FP-AI-SENSING1 package, building failed with errors and warnings that mostly are not related to the different inferences.

New ASC files are generated by the latest X-CUBE-AI and X-CUBE-MX but seem to be not compatible with the ones in FP-AI-SENSING1

Thanks

M

[ShivaRagu]

Hi,

When you do with your own dataset for ASC, use the below versions while creating neural networks models.

   Keras---2.2.4 

     Tensor flow---1.14.0 

      Librosa---0.8.0 

when you generate code in MX use below version.

STM32MX CUBE- 5.0 

 X-CUBE AI-4.1.0 

Because, all codes in FP-AI-SENSING1 Pack, they have generated the code as mentioned above.

Regards,

shankari

[ChipHead]

As you commented, we need to use X-CUBE AI-4.1.0 to convert the network model for ASC to C source code. Otherwise, the source will not compile.

I wonder if there is a version of FP-AI-SENSING1 available for us to use CUBE AI 7.3.0 instead of CUBE AI-4.10. ​

• FP-AI-SENSING1, https://www.st.com/en/embedded-software/fp-ai-sensing1.html