Package org.bytedeco.tensorrt.nvinfer_plugin

Class Summary

Class	Description
DetectionOutputParameters	\brief The DetectionOutput plugin layer generates the detection output based on location and confidence predictions by doing non maximum suppression.
GridAnchorParameters	\brief The Anchor Generator plugin layer generates the prior boxes of designated sizes and aspect ratios across all dimensions (H x W).
NMSParameters	\brief The NMSParameters are used by the BatchedNMSPlugin for performing the non_max_suppression operation over boxes for object detection networks.
PriorBoxParameters	\brief The PriorBox plugin layer generates the prior boxes of designated sizes and aspect ratios across all dimensions (H x W).
Quadruple	\brief The Permute plugin layer permutes the input tensor by changing the memory order of the data.
RegionParameters	\brief The Region plugin layer performs region proposal calculation: generate 5 bounding boxes per cell (for yolo9000, generate 3 bounding boxes per cell).
RPROIParams	\brief RPROIParams is used to create the RPROIPlugin instance.
softmaxTree	\brief When performing yolo9000, softmaxTree is helping to do softmax on confidence scores, for element to get the precise classification through word-tree structured classification definition.