This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

SK-TDA4VM: How to run 2 subgraphs compiled from one model in PSDK-RTOS

Part Number: SK-TDA4VM

Hi team,

The customer's model has 2 output.  so after model compiled using onnxrt_ep.py i got 2 subgraph like below:

The customer would like to know how to run this model in PSDK-RTOS ?  They run this model on PC emulation mode, and got a output which type is list including 2 array like image up. but don't know how to run this model using PSDK-RTOS.

Could you help check this case? Thanks.

Best Regards,

Cherry

  • Hi Cherry,

    To clarify, is the customer trying to run this model on a baremetal RTOS without running Linux on the A72 core? Or are they fine with running this with Linux+RTOS SDK?

    If customers are using Linux+RTOS SDK then we have some examples on our Edge AI Cloud Tool. I think the examples all use models that give one list output instead of two, but this can still be used as a reference. 

    I will post the link to Edge AI Cloud Tool here: https://dev.ti.com/edgeai/

    Regards,

    Takuma