TensorRT 8.4.0
Class Hierarchy
This inheritance list is sorted roughly, but not completely, alphabetically:
[detail level 1234]
 Cnvinfer1::plugin::DetectionOutputParametersThe 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 bounding boxes. DetectionOutputParameters defines a set of parameters for creating the DetectionOutput plugin layer. It contains:
 CDimsStructure to define the dimensions of a tensor
 Cnvinfer1::Dims32
 Cnvinfer1::Dims2Descriptor for two-dimensional data
 Cnvinfer1::Dims3Descriptor for three-dimensional data
 Cnvinfer1::Dims4Descriptor for four-dimensional data
 Cnvinfer1::DimsExprs
 Cnvinfer1::DynamicPluginTensorDesc
 Cnvinfer1::impl::EnumMaxImpl< T >Declaration of EnumMaxImpl struct to store maximum number of elements in an enumeration type
 Cnvinfer1::impl::EnumMaxImpl< ActivationType >
 Cnvinfer1::impl::EnumMaxImpl< AllocatorFlag >Maximum number of elements in AllocatorFlag enum
 Cnvinfer1::impl::EnumMaxImpl< DataType >Maximum number of elements in DataType enum
 Cnvinfer1::impl::EnumMaxImpl< ElementWiseOperation >
 Cnvinfer1::impl::EnumMaxImpl< EngineCapability >Maximum number of elements in EngineCapability enum
 Cnvinfer1::impl::EnumMaxImpl< ErrorCode >Maximum number of elements in ErrorCode enum
 Cnvinfer1::impl::EnumMaxImpl< ILogger::Severity >Maximum number of elements in ILogger::Severity enum
 Cnvinfer1::impl::EnumMaxImpl< PaddingMode >
 Cnvinfer1::impl::EnumMaxImpl< PoolingType >
 Cnvinfer1::impl::EnumMaxImpl< ResizeCoordinateTransformation >
 Cnvinfer1::impl::EnumMaxImpl< ResizeMode >
 Cnvinfer1::impl::EnumMaxImpl< ResizeRoundMode >
 Cnvinfer1::impl::EnumMaxImpl< ResizeSelector >
 Cnvinfer1::impl::EnumMaxImpl< TensorFormat >Maximum number of elements in TensorFormat enum
 Cnvinfer1::impl::EnumMaxImpl< TensorLocation >Maximum number of elements in TensorLocation enum
 Cnvuffparser::FieldCollection
 Cnvuffparser::FieldMapAn array of field params used as a layer parameter for plugin layers
 Cnvinfer1::safe::FloatingPointErrorInformationSpace to record information about floating point runtime errors
 Cnvinfer1::plugin::GridAnchorParametersThe 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:
 Cnvinfer1::IAlgorithmSelectorInterface implemented by application for selecting and reporting algorithms of a layer provided by the builder
 Cnvcaffeparser1::IBinaryProtoBlobObject used to store and query data extracted from a binaryproto file using the ICaffeParser
 Cnvcaffeparser1::IBlobNameToTensorObject used to store and query Tensors after they have been extracted from a Caffe model using the ICaffeParser
 Cnvcaffeparser1::ICaffeParserClass used for parsing Caffe models
 Cnvinfer1::consistency::IConsistencyCheckerValidates a serialized engine blob
 Cnvinfer1::safe::ICudaEngineA functionally safe engine for executing inference on a built network
 Cnvinfer1::IErrorRecorderReference counted application-implemented error reporting interface for TensorRT objects
 Cnvinfer1::safe::IExecutionContextFunctionally safe context for executing inference using an engine
 Cnvinfer1::IGpuAllocatorApplication-implemented class for controlling allocation on the GPU
 Cnvinfer1::IInt8CalibratorApplication-implemented interface for calibration
 Cnvinfer1::IInt8EntropyCalibrator
 Cnvinfer1::IInt8EntropyCalibrator2
 Cnvinfer1::IInt8LegacyCalibrator
 Cnvinfer1::IInt8MinMaxCalibrator
 Cnvinfer1::ILoggerApplication-implemented logging interface for the builder, refitter and runtime
 Cnvinfer1::INoCopyForward declaration of IEngineInspector for use by other interfaces
 Cnvinfer1::IAlgorithmDescribes a variation of execution of a layer. An algorithm is represented by IAlgorithmVariant and the IAlgorithmIOInfo for each of its inputs and outputs. An algorithm can be selected or reproduced using AlgorithmSelector::selectAlgorithms()."
 Cnvinfer1::IAlgorithmContextDescribes the context and requirements, that could be fulfilled by one or more instances of IAlgorithm
 Cnvinfer1::IAlgorithmIOInfoCarries information about input or output of the algorithm. IAlgorithmIOInfo for all the input and output along with IAlgorithmVariant denotes the variation of algorithm and can be used to select or reproduce an algorithm using IAlgorithmSelector::selectAlgorithms()
 Cnvinfer1::IAlgorithmVariantUnique 128-bit identifier, which along with the input and output information denotes the variation of algorithm and can be used to select or reproduce an algorithm, using IAlgorithmSelector::selectAlgorithms()
 Cnvinfer1::IBuilderBuilds an engine from a network definition
 Cnvinfer1::IBuilderConfigHolds properties for configuring a builder to produce an engine
 Cnvinfer1::ICudaEngineAn engine for executing inference on a built network, with functionally unsafe features
 Cnvinfer1::IDimensionExpr
 Cnvinfer1::IEngineInspectorAn engine inspector which prints out the layer information of an engine or an execution context
 Cnvinfer1::IExecutionContextContext for executing inference using an engine, with functionally unsafe features
 Cnvinfer1::IExprBuilder
 Cnvinfer1::IHostMemoryClass to handle library allocated memory that is accessible to the user
 Cnvinfer1::IIfConditional
 Cnvinfer1::ILayerBase class for all layer classes in a network definition
 Cnvinfer1::ILoop
 Cnvinfer1::INetworkDefinitionA network definition for input to the builder
 Cnvinfer1::IOptimizationProfileOptimization profile for dynamic input dimensions and shape tensors
 Cnvinfer1::IRefitterUpdates weights in an engine
 Cnvinfer1::IRuntimeAllows a serialized functionally unsafe engine to be deserialized
 Cnvinfer1::ITensorA tensor in a network definition
 Cnvinfer1::ITimingCacheClass to handle tactic timing info collected from builder
 Cnvonnxparser::IOnnxConfigConfiguration Manager Class
 Cnvonnxparser::IParserObject for parsing ONNX models into a TensorRT network definition
 Cnvonnxparser::IParserErrorObject containing information about an error
 Cnvinfer1::IPluginCreatorPlugin creator class for user implemented layers
 Cnvinfer1::consistency::IPluginCheckerConsistency Checker plugin class for user implemented Plugins
 Cnvcaffeparser1::IPluginFactoryV2Plugin factory used to configure plugins
 Cnvinfer1::IPluginRegistrySingle 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
 Cnvinfer1::IPluginV2Plugin class for user-implemented layers
 Cnvinfer1::IPluginV2ExtPlugin class for user-implemented layers
 Cnvinfer1::IProfilerApplication-implemented interface for profiling
 Cnvinfer1::safe::IRuntimeAllows a serialized functionally safe engine to be deserialized
 Cnvuffparser::IUffParserClass used for parsing models described using the UFF format
 Cnvinfer1::plugin::NMSParametersThe NMSParameters are used by the BatchedNMSPlugin for performing the non_max_suppression operation over boxes for object detection networks
 Cnvinfer1::Permutation
 Cnvinfer1::PluginFieldStructure containing plugin attribute field names and associated data This information can be parsed to decode necessary plugin metadata
 Cnvinfer1::PluginFieldCollectionPlugin field collection struct
 Cnvinfer1::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
 Cnvinfer1::safe::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
 Cnvinfer1::PluginTensorDescFields that a plugin might see for an input or output
 CPluginVersionDefinition of plugin versions
 Cnvinfer1::plugin::PriorBoxParametersThe 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:
 Cnvinfer1::plugin::QuadrupleThe 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
 Cnvinfer1::plugin::RegionParametersThe 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 9418 pre-defined classifications, and these 9418 items are organized as work-tree structure). RegionParameters defines a set of parameters for creating the Region plugin layer
 Cnvinfer1::plugin::RPROIParamsRPROIParams is used to create the RPROIPlugin instance. It contains:
 Cnvinfer1::plugin::softmaxTreeWhen performing yolo9000, softmaxTree is helping to do softmax on confidence scores, for element to get the precise classification through word-tree structured classification definition
 Cnvinfer1::WeightsAn array of weights used as a layer parameter