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.

TDA4VM: OpenVX Exceeded max parameters for a kernel

Part Number: TDA4VM

Dear experts,

I am helping customer to develop TIDL applications. In one use case, their model will output more than 15 output_tensors. When we integrated with OpenVX( using tivxTIDLNode), we find that there is a limitation in max number of parameters. Could you please suggest which micro to change to enable more parameters?

Here is the log:

APP: Init ... Done !!!

     0.000923 s: VX_ZONE_INIT:Enabled

     0.001404 s: VX_ZONE_ERROR:Enabled

     0.001680 s: VX_ZONE_WARNING:Enabled

     0.002611 s: VX_ZONE_INIT:[tivxInit:64] Initialization Done !!!

     0.006030 s: VX_ZONE_INIT:[tivxHostInit:44] Initialization Done for HOST !!!

     0.684712 s: VX_ZONE_ERROR:[tivxAddKernelTIDL:260] invalid values for num_input_tensors or num_output_tensors

     0.685161 s: VX_ZONE_ERROR:[tivxTIDLNode:101] Exceeded max parameters for a kernel

I found a micro: "TIVX_KERNEL_MAX_PARAMS" == 16 in tiovx/include/TI/tivx_config.h.

Please help to confirm if it the correct place. Thanks!

Thanks & Best Regards!

ZM