How to achieve non max suppression and remove object multiple object detections?

We trained a custom model for person detection and we encountered the problem of having multiple bounding boxes for the same person with our custom resnet ssd model. Is there a way to achieve NMS to remove these bounding boxes?

Hi,

SSD-based model are already integrated an NMS layer.
It’s recommended to tune the NMS paramter to see if helps first.

/usr/src/tensorrt/samples/sampleUffSSD/config.py

NMS = gs.create_plugin_node(name="NMS", op="NMS_TRT",
    shareLocation=1,
    varianceEncodedInTarget=0,
    backgroundLabelId=0,
    confidenceThreshold=1e-8,
    nmsThreshold=0.6,
    topK=100,
    keepTopK=100,
    numClasses=91,
    inputOrder=[0, 2, 1],
    confSigmoid=1,
    isNormalized=1)

Thansk.