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.
As of the demo " app_tidl_seg_cam", when create output tensor; (SDK8.0)
static void createOutputTensors(vx_context context, vx_user_data_object config, vx_tensor output_tensors[]) { vx_size input_sizes[APP_MAX_TENSOR_DIMS]; vx_map_id map_id_config; vx_uint32 id; tivxTIDLJ7Params *tidlParams; sTIDL_IOBufDesc_t *ioBufDesc; vxMapUserDataObject(config, 0, sizeof(tivxTIDLJ7Params), &map_id_config, (void **)&tidlParams, VX_READ_ONLY, VX_MEMORY_TYPE_HOST, 0); ioBufDesc = (sTIDL_IOBufDesc_t *)&tidlParams->ioBufDesc; for(id = 0; id < ioBufDesc->numInputBuf; id++) { input_sizes[0] = ioBufDesc->inWidth[id] + ioBufDesc->inPadL[id] + ioBufDesc->inPadR[id]; input_sizes[1] = ioBufDesc->inHeight[id] + ioBufDesc->inPadT[id] + ioBufDesc->inPadB[id]; input_sizes[2] = ioBufDesc->inNumChannels[id]; vx_enum data_type = get_vx_tensor_datatype(ioBufDesc->inElementType[id]); output_tensors[id] = vxCreateTensor(context, 3, input_sizes, data_type, 0); } vxUnmapUserDataObject(config, map_id_config); return; }
Why we use inWidth, inHeight ... and input_size to create output tensors ? what's the logic here.