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: The inferring of the concat operator on the PC side works well, but the output result of the inferring on the board side is erroneous

Part Number: SK-TDA4VM


Hi Team,

I have a model that includes a concat operator, and the output result of the cocat operator of the inference model using onnxrt_ep.py on the PC side is normal, but the output result of the concat operator of the inference model on the board side is incorrect. Could you please tell me the reason? The official version of 08.02 is used. Is the libtidl_onnxrt_EP.so file on the PC side the same as the libtidl_onnxrt_EP.so file on the board side? Where can I see the source code of this file?

Kind regards,

Katherine