STM32 CUBE-AI Running Multi network

[bkrzn]

I am producing two different models on STM32CubeIde on STM32CubeIde. I want to use two different networks by using Multi network functions in app_x-cube-ai.c file but I was not successful. Is there a document or sample code about this?

 

uint8_t init_multi_network(void)
{
if ((error = ai_mnetwork_create("onnx", &onnx_, NULL).type) == AI_ERROR_NONE)
{

if(ai_mnetwork_init(onnx_))
{
p_ai_input = ai_platform_inputs_get(onnx_,NULL); // !!!!!!!ai buffer get function is not returning valid value, returning zero
}
}
else
{

};

 

return 0;

}
;

[Julian E.]

Hello @bkrzn ,

 

Using multiple model is similar to using one, X cube AI will generate of the files required for each model with their set of functions.

 

I found this thread that may help you:

Can I implement multiple models through X-CUBE-AI? - STMicroelectronics Community

 

You also have the documentation of X Cube AI:

https://www.st.com/resource/en/user_manual/um2526-getting-started-with-xcubeai-expansion-package-for-artificial-intelligence-ai-stmicroelectronics.pdf 

https://stedgeai-dc.st.com/assets/embedded-docs/embedded_client_api_legacy.html 

 

Have a good day,

Julian

 

[bkrzn]

Thanks for fast reply,

Can i get an multi-network example code with multinetwork Api functions.

const char* ai_mnetwork_find(const char *name, ai_int idx);
ai_error ai_mnetwork_create(const char *name, ai_handle* network, const ai_buffer*
network_config);
ai_bool ai_mnetwork_get_info(ai_handle network, ai_network_report* report);
ai_error ai_mnetwork_get_error(ai_handle network);
ai_handle ai_mnetwork_destroy(ai_handle network);
ai_bool ai_mnetwork_init(ai_handle network, const ai_network_params* params);
ai_i32 ai_mnetwork_run(ai_handle network, const ai_buffer* input, ai_buffer* output);

 

I couldn't find anywhere