Yes I confirm that the implementation of the kernels are different.
If you see a significant accuracy drop using X-CUBE-AI then it may be an issue we have to work on.
Regards
The STM32Cube.AI (i.e. X-CUBE-AI) library used on the target has it's own implementation of the neural network kernels so you may see different results between the results when executed in Python versus the target.
In the X-Cube-AI tool you have 2 v...
As stated in the documentation (now online)
https://stedgeai-dc.st.com/assets/embedded-docs/embedded_client_api_legacy.html
his helper function aggregates the call of the create and init functions (see code in the generated 'network.c' file). It allo...
We support ST Boards that has an embedded stlink with virtual com port support connected to a USART on the target
You can find ST boards on the STM32H7 here: https://www.st.com/content/st_com/en/search.html#q=stm32h7-t=tools-page=1
You can always for...
