2023-06-28 07:34 AM - edited 2023-06-28 07:37 AM
Hi
I have a really simple Neural Network (Keras) with 3 float32 inputs and 3 float32 outputs.
Size: 2.2KB RAM 16kBFlash and 1600MACC, really small network, in my opinion it should not be a problem at all to run that.
For testing i wanted to try the simplest way possible to run that Network on a STML4 MCU.
I used CubeMX, integraded the Model and created and built an example Project by using a "ApplicationTemplate".
All went prefect.
so know i have an example Project where everything is generated. especially a file called "app_x_cube-ai.c".
There is a init function called: "MX_X_CUBE_AI_Init()" and a RunAI function called " MX_X_CUBE_AI_Process", looking like this
I have set a breakpoint to have a look at output data "f32DataOut". it is always wrong.
I am pretty shure my input data is also not processed correctly.
Has anyone an idea what i could do ?
is datatype processed correctly, did i miss something ?
any hint would be great.
I attached the complete "app_x-cube-ai.c" File. Everything else is generated in CubeMx
Thanks in advance