Class Hierarchy

This inheritance list is sorted roughly, but not completely, alphabetically:

[detail level 123]

nvinfer1::plugin::DetectionOutputParameters	The DetectionOutput plugin layer generates the detection output based on location and confidence predictions by doing non maximum suppression. This plugin first decodes the bounding boxes based on the anchors generated. It then performs non_max_suppression on the decoded bouding boxes. DetectionOutputParameters defines a set of parameters for creating the DetectionOutput plugin layer. It contains:
nvinfer1::Dims	Structure to define the dimensions of a tensor
nvinfer1::Dims2	Descriptor for two-dimensional data
nvinfer1::DimsHW	Descriptor for two-dimensional spatial data
nvinfer1::Dims3	Descriptor for three-dimensional data
nvinfer1::DimsCHW	Descriptor for data with one channel dimension and two spatial dimensions
nvinfer1::Dims4	Descriptor for four-dimensional data
nvinfer1::DimsNCHW	Descriptor for data with one index dimension, one channel dimension and two spatial dimensions
nvuffparser::FieldCollection
nvuffparser::FieldMap	An array of field params used as a layer parameter for plugin layers
nvinfer1::plugin::GridAnchorParameters	The Anchor Generator plugin layer generates the prior boxes of designated sizes and aspect ratios across all dimensions (H x W). GridAnchorParameters defines a set of parameters for creating the plugin layer for all feature maps. It contains:
nvcaffeparser1::IBinaryProtoBlob	Object used to store and query data extracted from a binaryproto file using the ICaffeParser
nvcaffeparser1::IBlobNameToTensor	Object used to store and query Tensors after they have been extracted from a Caffe model using the ICaffeParser
nvinfer1::IBuilder	Builds an engine from a network definition
nvcaffeparser1::ICaffeParser	Class used for parsing Caffe models
nvinfer1::ICudaEngine	An engine for executing inference on a built network
nvinfer1::IExecutionContext	Context for executing inference using an engine
nvinfer1::IGpuAllocator	Application-implemented class for controlling allocation on the GPU
nvinfer1::IHostMemory	Class to handle library allocated memory that is accessible to the user
nvinfer1::IInt8Calibrator	Application-implemented interface for calibration
nvinfer1::IInt8EntropyCalibrator
nvinfer1::IInt8EntropyCalibrator2
nvinfer1::IInt8LegacyCalibrator
nvinfer1::ILayer	Base class for all layer classes in a network definition
nvinfer1::IActivationLayer	An Activation layer in a network definition
nvinfer1::IConcatenationLayer	A concatenation layer in a network definition
nvinfer1::IConstantLayer	Layer that represents a constant value
nvinfer1::IConvolutionLayer	A convolution layer in a network definition
nvinfer1::IDeconvolutionLayer	A deconvolution layer in a network definition
nvinfer1::IElementWiseLayer	A elementwise layer in a network definition
nvinfer1::IFullyConnectedLayer	A fully connected layer in a network definition. This layer expects an input tensor of three or more non-batch dimensions. The input is automatically reshaped into an MxV tensor X, where V is a product of the last three dimensions and M is a product of the remaining dimensions (where the product over 0 dimensions is defined as 1). For example:
nvinfer1::IGatherLayer
nvinfer1::IIdentityLayer	A layer that represents the identity function
nvinfer1::ILRNLayer	A LRN layer in a network definition
nvinfer1::IMatrixMultiplyLayer	Layer that represents a Matrix Multiplication
nvinfer1::IPaddingLayer	Layer that represents a padding operation
nvinfer1::IPluginLayer	Layer type for plugins
nvinfer1::IPluginV2Layer	Layer type for pluginV2
nvinfer1::IPoolingLayer	A Pooling layer in a network definition
nvinfer1::IRaggedSoftMaxLayer	A RaggedSoftmax layer in a network definition
nvinfer1::IReduceLayer	Layer that represents a reduction operator
nvinfer1::IRNNLayer	A RNN layer in a network definition
nvinfer1::IRNNv2Layer	An RNN layer in a network definition, version 2
nvinfer1::IScaleLayer	A Scale layer in a network definition
nvinfer1::IShuffleLayer	Layer type for shuffling data
nvinfer1::ISliceLayer
nvinfer1::ISoftMaxLayer	A Softmax layer in a network definition
nvinfer1::ITopKLayer	Layer that represents a TopK reduction
nvinfer1::IUnaryLayer	Layer that represents an unary operation
nvinfer1::ILogger	Application-implemented logging interface for the builder, engine and runtime
nvinfer1::INetworkDefinition	A network definition for input to the builder
nvonnxparser::IOnnxConfig	Configuration Manager Class
nvinfer1::IOutputDimensionsFormula	Application-implemented interface to compute layer output sizes
nvinfer1::IPlugin	Plugin class for user-implemented layers
nvinfer1::IPluginExt	Plugin class for user-implemented layers
nvinfer1::plugin::INvPlugin	Common interface for the Nvidia created plugins
nvinfer1::IPluginCreator	Plugin creator class for user implemented layers
nvinfer1::IPluginFactory	Plugin factory for deserialization
nvuffparser::IPluginFactory	Plugin factory used to configure plugins
nvuffparser::IPluginFactoryExt	Plugin factory used to configure plugins with added support for TRT versioning
nvcaffeparser1::IPluginFactory	Plugin factory used to configure plugins
nvcaffeparser1::IPluginFactoryExt	Plugin factory used to configure plugins with added support for TRT versioning
nvcaffeparser1::IPluginFactoryV2	Plugin factory used to configure plugins
nvinfer1::IPluginRegistry	Single registration point for all plugins in an application. It is used to find plugin implementations during engine deserialization. Internally, the plugin registry is considered to be a singleton so all plugins in an application are part of the same global registry. Note that the plugin registry is only supported for plugins of type IPluginV2 and should also have a corresponding IPluginCreator implementation
nvinfer1::IPluginV2	Plugin class for user-implemented layers
nvinfer1::IPluginV2Ext	Plugin class for user-implemented layers
nvinfer1::IProfiler	Application-implemented interface for profiling
nvinfer1::IRefitter	Updates weights in an engine
nvinfer1::IRuntime	Allows a serialized engine to be deserialized
nvinfer1::ITensor	A tensor in a network definition
nvuffparser::IUffParser	Class used for parsing models described using the UFF format
nvinfer1::plugin::NMSParameters	The NMSParameters are used by the BatchedNMSPlugin for performing the non_max_suppression operation over boxes for object detection networks
nvinfer1::Permutation
nvinfer1::PluginField	Structure containing plugin attribute field names and associated data This information can be parsed to decode necessary plugin metadata
nvinfer1::PluginFieldCollection
nvinfer1::PluginRegistrar< T >	Register the plugin creator to the registry The static registry object will be instantiated when the plugin library is loaded. This static object will register all creators available in the library to the registry
nvinfer1::plugin::PriorBoxParameters	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:
nvinfer1::plugin::Quadruple	The Permute plugin layer permutes the input tensor by changing the memory order of the data. Quadruple defines a structure that contains an array of 4 integers. They can represent the permute orders or the strides in each dimension
nvinfer1::plugin::RegionParameters
nvinfer1::plugin::softmaxTree	The Region plugin layer performs region proposal calculation: generate 5 bounding boxes per cell (for yolo9000, generate 3 bounding boxes per cell). For each box, calculating its probablities of objects detections from 80 pre-defined classifications (yolo9000 has 9416 pre-defined classifications, and these 9416 items are organized as work-tree structure). RegionParameters defines a set of parameters for creating the Region plugin layer
nvinfer1::Weights	An array of weights used as a layer parameter