Assign value in GstNvInferObjectInfo

Accelerated Computing Intelligent Video Analytics DeepStream SDK
5

It gets it from the following struct NvDsInferFrameOutput in the sources\includes\nvdsinfer_context.h file.
sources\gst-plugins\gst-nvinfer\gstnvinfer.cpp

        attach_metadata_detector (nvinfer, GST_MINI_OBJECT (tensor_out_object.get()),
                frame, frame_output.detectionOutput, init_params->segmentationThreshold);

And the batch_output is from the OutputBatch queue.

    batch_output = &tensor_out_object->batch_output;
    /* Dequeue inferencing output from NvDsInferContext */
    status = nvdsinfer_ctx->dequeueOutputBatch (*batch_output);

Since it’s open source, you can add some log yourself to check the process.

1 Like