How to Allocate Separate Memory Ranges for Multiple AI Models in X-CUBE-AI on Nucleo-N657X0-Q

[LisaB]

Hello everyone,

I'm using a Nucleo-N657X0-Q and trying to integrate two different neural network models into my STM32CubeIDE project via X-CUBE-AI.

The issue I'm encountering is that both models are assigned overlapping memory regions:

• npuRAM5: 0x342E0000 - 0x34350000 → model uses 0x342E0000 - 0x342E00C0

• octoFlash: 0x70000000 - 0x73FFFFF8 → model uses 0x70000000 - 0x700038A0

Is there a way to manually assign an offset or configure the memory so that each model uses a distinct memory area?

Thanks in advance for your help!

[LisaB]

The solution is to create two different profiles, one for each of the two models.

Each profile corresponds to a different region of the external flash. This is done by changing the starting address and the memory size in Advanced Settings, Memory Pools.