LL_ATON_Set_User_Input_Buffer/_Output_Buffer just returns WRONG_INDEX

[RafaelVVolkmer]

Hello,
ST Team and Community!

Recently, I've been working on implementing an AI model based on YoloV11n, built to run on an N6570. I'm trying to transform the raw memory that the model returns to me into a standard YoloV11n output, so I can have the data I need for my application.

Analyzing a little deeper and doing the reverse path to link two functions documented in the LL_ATON lib:

We have that, inside the network.c, generated by CubeAI, the final symbol that should have the implementation of the function simply just returns WORNG_INDEX for both LL_ATON_Set_User_Input_Buffer and LL_ATON_Set_User_Output_Buffer. Was it supposed to happen this way?

Here, in the official documentation for the LL_ATON lib, it says something about a compilation flag that is required for the user to allocate buffers this way. Could this be the reason for the generation error, or is the function actually not implemented?

My current settings for the cubeAI package - for context:

Best regards,

Rafael V. Volkmer

[Billy OWEN]

Hi @RafaelVVolkmer 

This post has been escalated to the ST Online Support Team for additional assistance.  We'll contact you directly.

Regards,

Billy

[RafaelVVolkmer · Accepted solution]

Hello,
ST Team and Community!

For future readers:

- By default, input and output buffers are automatically allocated by the compiler;

- In X-CUBE-AI, under Advanced Options, the fields “Use activation buffer for input buffer” and “Use activation buffer for output buffer” must be enabled to allow the compiler to handle buffer allocation;

- If these options are disabled, the functions LL_ATON_Set_User_Input_Buffer_Default and LL_ATON_Set_User_Output_Buffer_Default can be used to manually allocate the buffers.

- In the STEdgeAI CLI, these options can be disabled by adding the flags --no-inputs-allocation and/or --no-outputs-allocation.

Case solved! Thank you very much, ST team and community