The NMSParameters are used by the BatchedNMSPlugin for performing the non_max_suppression operation over boxes for object detection networks. More...

Public Attributes
bool	shareLocation

int32_t	backgroundLabelId

int32_t	numClasses
	Number of classes in the network. More...

int32_t	topK
	Number of bounding boxes to be fed into the NMS step. More...

int32_t	keepTopK

float	scoreThreshold
	Scalar threshold for score (low scoring boxes are removed). More...

float	iouThreshold

bool	isNormalized

Detailed Description

The NMSParameters are used by the BatchedNMSPlugin for performing the non_max_suppression operation over boxes for object detection networks.

Deprecated:: Deprecated in TensorRT 10.0. BatchedNMSPlugin plugin is deprecated.

Member Data Documentation

int32_t nvinfer1::plugin::NMSParameters::backgroundLabelId

Label ID for the background class. If there is no background class, set it as -1

float nvinfer1::plugin::NMSParameters::iouThreshold

A scalar threshold for IOU (new boxes that have high IOU overlap with previously selected boxes are removed).

bool nvinfer1::plugin::NMSParameters::isNormalized

Set to false, if the box coordinates are not normalized, i.e. not in the range [0,1]. Defaults to false.

int32_t nvinfer1::plugin::NMSParameters::keepTopK

Number of total bounding boxes to be kept per image after NMS step. Should be less than or equal to the topK value.

int32_t nvinfer1::plugin::NMSParameters::numClasses

Number of classes in the network.

float nvinfer1::plugin::NMSParameters::scoreThreshold

Scalar threshold for score (low scoring boxes are removed).

bool nvinfer1::plugin::NMSParameters::shareLocation

If set to true, the boxes inputs are shared across all classes. If set to false, the boxes input should account for per class box data.

int32_t nvinfer1::plugin::NMSParameters::topK

Number of bounding boxes to be fed into the NMS step.

The documentation for this struct was generated from the following file: