How the data was sent during the "validate on target" process?

[Joseph_]

I built a simple FCNN model based on onnx(regression, 4 input and 4 output), including three hidden layers with 64, 32, 16 nodes, and successfully "validate on target" in STM32 through X-CUBE-AI.

Now I want to send(receive) data directly to(from) the STM32 via the serial port, instead of clicking the button "validate on target". However, I don't know how the data from the npy file was sent during the "validate on target" process. Is there any documentation to explain the process?

[Julian E.]

Hello @Joseph_ ,

I think that you can look out to this document:

https://www.st.com/resource/en/user_manual/dm00570145-getting-started-with-x-cube-ai-expansion-package-for-artificial-intelligence-ai-stmicroelectronics.pdf

I am not familiar with this document, but I think that page 32, 38 (and probably other pages) may help you.

You can also look at: ST Edge AI Developer Cloud and specifically the documents under the category "STM32 target".

Let me know if it does not answer your question.

Have a good day,

Julian