Issue: [TensorRT] ERROR: UFFParser: Validator error: NMS: Unsupported operation _NMS_TRT

AI & Data Science Deep Learning (Training & Inference) TensorRT
1

I am trying to add a non-max suppression layer referencing the ‘config.py’ file in sampleUffSSD.
Following is the log.

Using output node NMS
Converting to UFF graph
Warning: No conversion function registered for layer: NMS_TRT yet.
Converting NMS as custom op: NMS_TRT
No. nodes: 2
UFF Output written to tmp.graph.uff
('register input: ', True)
parsing uff model into engine model
[TensorRT] ERROR: UFFParser: Validator error: NMS: Unsupported operation _NMS_TRT
[TensorRT] ERROR: Network must have at least one output

Tensorrt Version: 5.0.2.6
Ubuntu 16.04

Do I need something additional to install the plugins ?

Function to preprocess the loaded graph

def get_graph_with_nms(dg, input_shape):
    channels, height, width = input_shape

    Input = gs.create_plugin_node(name="Input",
        op="Placeholder",
        dtype=tf.float32,
        shape=[1, channels, height, width])
    PriorBox = gs.create_plugin_node(name="GridAnchor",
                                     op="GridAnchor_TRT",
                                     minSize=0.2,
                                     maxSize=0.95,
                                     aspectRatios=[1.0, 2.0, 0.5, 3.0,
                                                   0.33],
                                     variance=[0.1, 0.1, 0.2, 0.2],
                                     featureMapShapes=[19, 10, 5, 3, 2, 1],
                                     numLayers=6
                                     )

    NMS = gs.create_plugin_node(
        name="NMS",
        op="NMS_TRT",
        shareLocation=1,
        varianceEncodedInTarget=0,
        backgroundLabelId=0,
        confidenceThreshold=0.5,
        nmsThreshold=0.3,
        topK=100,
        keepTopK=100,
        numClasses=91,
        inputOrder=[0, 1, 2],
        confSigmoid=1,
        isNormalized=1
    )
    concat_priorbox = gs.create_node(
        "concat_priorbox",
        op="ConcatV2",
        dtype=tf.float32,
        axis=2
    )
    concat_box_loc = gs.create_plugin_node(
        "concat_box_loc",
        op="FlattenConcat_TRT",
        dtype=tf.float32,
        axis=1,
        ignoreBatch=0
    )
    concat_box_conf = gs.create_plugin_node(
        "concat_box_conf",
        op="FlattenConcat_TRT",
        dtype=tf.float32,
        axis=1,
        ignoreBatch=0
    )

    # Create a mapping of namespace names -> plugin nodes.
    namespace_plugin_map = {
        "MultipleGridAnchorGenerator": PriorBox,
        "Postprocessor": NMS,
        "Preprocessor/map": Input,
        "ToFloat": Input,
        # "image_tensor": Input,
        "Concatenate": concat_priorbox,
        "concat": concat_box_loc,
        "concat_1": concat_box_conf
    }

    for node in dg.graph_inputs:
        namespace_plugin_map[node.name] = Input
    dg.collapse_namespaces(namespace_plugin_map)
    # dg.find_nodes_by_op("NMS_TRT")[0].input.remove("Input")
    dg.remove(dg.graph_outputs,
              remove_exclusive_dependencies=False)

    return dg