TensorRT  5.1.5.0
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Macros Pages
Class List
Here are the classes, structs, unions and interfaces with brief descriptions:
[detail level 123]
oNnvcaffeparser1
|oCIBlobNameToTensorObject used to store and query Tensors after they have been extracted from a Caffe model using the ICaffeParser
|oCIBinaryProtoBlobObject used to store and query data extracted from a binaryproto file using the ICaffeParser
|oCIPluginFactoryPlugin factory used to configure plugins
|oCIPluginFactoryExtPlugin factory used to configure plugins with added support for TRT versioning
|oCIPluginFactoryV2Plugin factory used to configure plugins
|\CICaffeParserClass used for parsing Caffe models
oNnvinfer1The TensorRT API version 1 namespace
|oNplugin
||oCINvPluginCommon interface for the Nvidia created plugins
||oCQuadrupleThe 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
||oCPriorBoxParametersThe 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:
||oCGridAnchorParametersThe 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:
||oCDetectionOutputParametersThe 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:
||oCsoftmaxTreeThe 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
||oCRegionParameters
||\CNMSParametersThe NMSParameters are used by the BatchedNMSPlugin for performing the non_max_suppression operation over boxes for object detection networks
|oCDimsStructure to define the dimensions of a tensor
|oCDims2Descriptor for two-dimensional data
|oCDimsHWDescriptor for two-dimensional spatial data
|oCDims3Descriptor for three-dimensional data
|oCDimsCHWDescriptor for data with one channel dimension and two spatial dimensions
|oCDims4Descriptor for four-dimensional data
|oCDimsNCHWDescriptor for data with one index dimension, one channel dimension and two spatial dimensions
|oCWeightsAn array of weights used as a layer parameter
|oCIHostMemoryClass to handle library allocated memory that is accessible to the user
|oCITensorA tensor in a network definition
|oCILayerBase class for all layer classes in a network definition
|oCIConvolutionLayerA convolution layer in a network definition
|oCIFullyConnectedLayerA 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:
|oCIActivationLayerAn Activation layer in a network definition
|oCIPoolingLayerA Pooling layer in a network definition
|oCILRNLayerA LRN layer in a network definition
|oCIScaleLayerA Scale layer in a network definition
|oCISoftMaxLayerA Softmax layer in a network definition
|oCIConcatenationLayerA concatenation layer in a network definition
|oCIDeconvolutionLayerA deconvolution layer in a network definition
|oCIElementWiseLayerA elementwise layer in a network definition
|oCIGatherLayer
|oCIRNNLayerA RNN layer in a network definition
|oCIRNNv2LayerAn RNN layer in a network definition, version 2
|oCIOutputDimensionsFormulaApplication-implemented interface to compute layer output sizes
|oCIPluginPlugin class for user-implemented layers
|oCIPluginExtPlugin class for user-implemented layers
|oCIPluginV2Plugin class for user-implemented layers
|oCIPluginV2ExtPlugin class for user-implemented layers
|oCIPluginLayerLayer type for plugins
|oCIPluginV2LayerLayer type for pluginV2
|oCPluginFieldStructure containing plugin attribute field names and associated data This information can be parsed to decode necessary plugin metadata
|oCPluginFieldCollection
|oCIPluginCreatorPlugin creator class for user implemented layers
|oCIPluginRegistrySingle 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
|oCIUnaryLayerLayer that represents an unary operation
|oCIReduceLayerLayer that represents a reduction operator
|oCIPaddingLayerLayer that represents a padding operation
|oCPermutation
|oCIShuffleLayerLayer type for shuffling data
|oCISliceLayer
|oCITopKLayerLayer that represents a TopK reduction
|oCIMatrixMultiplyLayerLayer that represents a Matrix Multiplication
|oCIRaggedSoftMaxLayerA RaggedSoftmax layer in a network definition
|oCIIdentityLayerA layer that represents the identity function
|oCIConstantLayerLayer that represents a constant value
|oCINetworkDefinitionA network definition for input to the builder
|oCIProfilerApplication-implemented interface for profiling
|oCIExecutionContextContext for executing inference using an engine
|oCICudaEngineAn engine for executing inference on a built network
|oCIInt8CalibratorApplication-implemented interface for calibration
|oCIInt8EntropyCalibrator
|oCIInt8EntropyCalibrator2
|oCIInt8LegacyCalibrator
|oCIGpuAllocatorApplication-implemented class for controlling allocation on the GPU
|oCIBuilderBuilds an engine from a network definition
|oCIRefitterUpdates weights in an engine
|oCIPluginFactoryPlugin factory for deserialization
|oCIRuntimeAllows a serialized engine to be deserialized
|oCILoggerApplication-implemented logging interface for the builder, engine and runtime
|\CPluginRegistrarRegister 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
oNnvonnxparser
|\CIOnnxConfigConfiguration Manager Class
\Nnvuffparser
 oCFieldMapAn array of field params used as a layer parameter for plugin layers
 oCFieldCollection
 oCIPluginFactoryPlugin factory used to configure plugins
 oCIPluginFactoryExtPlugin factory used to configure plugins with added support for TRT versioning
 \CIUffParserClass used for parsing models described using the UFF format