TensorRT  7.2.1.6
NVIDIA TensorRT
Looking for a C++ dev who knows TensorRT?
I'm looking for work. Hire me!
nvinfer1::plugin::PriorBoxParameters Struct Reference

The PriorBox plugin layer generates the prior boxes of designated sizes and aspect ratios across all dimensions (H x W). More...

Collaboration diagram for nvinfer1::plugin::PriorBoxParameters:

Public Attributes

float * minSize
 
float * maxSize
 
float * aspectRatios
 
int32_t numMinSize
 
int32_t numMaxSize
 
int32_t numAspectRatios
 
bool flip
 
bool clip
 
float variance [4]
 
int32_t imgH
 
int32_t imgW
 
float stepH
 
float stepW
 
float offset
 

Detailed Description

The PriorBox plugin layer generates the prior boxes of designated sizes and aspect ratios across all dimensions (H x W).

PriorBoxParameters defines a set of parameters for creating the PriorBox plugin layer. It contains:

Parameters
minSizeMinimum box size in pixels. Can not be nullptr.
maxSizeMaximum box size in pixels. Can be nullptr.
aspectRatiosAspect ratios of the boxes. Can be nullptr.
numMinSizeNumber of element in minSize. Must be larger than 0.
numMaxSizeNumber of elements in maxSize. Can be 0 or same as numMinSize.
numAspectRatiosNumber of elements in aspectRatios. Can be 0.
flipIf true, will flip each aspect ratio. For example, if there is an aspect ratio "r", the aspect ratio "1.0/r" will be generated as well.
clipIf true, will clip the prior so that it is within [0,1].
varianceVariance for adjusting the prior boxes.
imgHImage height. If 0, then the H dimension of the data tensor will be used.
imgWImage width. If 0, then the W dimension of the data tensor will be used.
stepHStep in H. If 0, then (float)imgH/h will be used where h is the H dimension of the 1st input tensor.
stepWStep in W. If 0, then (float)imgW/w will be used where w is the W dimension of the 1st input tensor.
offsetOffset to the top left corner of each cell.

Member Data Documentation

◆ minSize

float* nvinfer1::plugin::PriorBoxParameters::minSize

◆ maxSize

float * nvinfer1::plugin::PriorBoxParameters::maxSize

◆ aspectRatios

float * nvinfer1::plugin::PriorBoxParameters::aspectRatios

◆ numMinSize

int32_t nvinfer1::plugin::PriorBoxParameters::numMinSize

◆ numMaxSize

int32_t nvinfer1::plugin::PriorBoxParameters::numMaxSize

◆ numAspectRatios

int32_t nvinfer1::plugin::PriorBoxParameters::numAspectRatios

◆ flip

bool nvinfer1::plugin::PriorBoxParameters::flip

◆ clip

bool nvinfer1::plugin::PriorBoxParameters::clip

◆ variance

float nvinfer1::plugin::PriorBoxParameters::variance[4]

◆ imgH

int32_t nvinfer1::plugin::PriorBoxParameters::imgH

◆ imgW

int32_t nvinfer1::plugin::PriorBoxParameters::imgW

◆ stepH

float nvinfer1::plugin::PriorBoxParameters::stepH

◆ stepW

float nvinfer1::plugin::PriorBoxParameters::stepW

◆ offset

float nvinfer1::plugin::PriorBoxParameters::offset

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