Hello dogg, There are many aspects in your question.There is a simple service to convert a h5 model to TFLiteoperation_mode: quantizationYou need to provide an h5 model, in the model_path.A quantization dataset in quantization_path.to be quick, the s...

Hello dogg, The situation triggers me an idea.Between the versions of X-CUBE-AI, the implementation of the AI kernels is continuously improving.Your problem sounds like a misalignment between C, H, and lib files of X-CUBE-AI versions that you have in...

Thank you Magnus,you are right. This is the correct way of doing it.I am reworking the wiki, to make it easier. Stay tune !With Kind Regards,Nicolas,

I did the Wiki again on my side and did not face any issue.For your case and would verify two steps :Delete the following files and replace them with the ones from workspace/stm32ai_output:In Src:network.cnetwork_data.cnetwork_data_params.c (for X-CU...