About LMain.1

LMain.1 · 2023-05-15

The approach described on the official XCUBE-AI documentation is not working for my case.

LMain.1 · 2023-05-13

I am using a STM32WL55JC2 Nucleo Board that mounts a dual core M4/M0+, I changed the linker script in order to have more RAM and FLASH on the M4, but this change is not reflected on the X-CUBE AI interface when adding a new network.Is it possible to ...

LMain.1 · 2023-05-17

Hello, Thank you so much! This solved the issue!I definitely got confused with pointers.

LMain.1 · 2023-05-17

Even trying without the allocate input and output in the activation buffer option does not solve the issue. I keep getting 0 outputs for both the output layers

LMain.1 · 2023-05-16

Now the code is working, but I always get 0 as output.Here is my code:/* Global handle to reference the instance of the NN */ static ai_handle network = AI_HANDLE_NULL; static ai_u8 activations[AI_NETWORK_DATA_ACTIVATIONS_SIZE]; /* C-table to store...

LMain.1 · 2023-05-15

I am not able to correctly initialize the output buffer. When I try to access its size or meta_info to dequantize the output, I get random values...

LMain.1 · 2023-05-15

Thank you! That's what I thought. I think an option to generate the network code would be to use the STM32Cube.AI Developer Cloud as well.

User statistics

User Activity

How can I handle multiple outputs networks?

How to change RAM limits on X-Cube AI for a dual core MCU.

Re: How can I handle multiple outputs networks?

Re: How can I handle multiple outputs networks?

Re: How can I handle multiple outputs networks?

Re: How can I handle multiple outputs networks?

Re: How to change RAM limits on X-Cube AI for a dual core MCU.