Cnvinfer1::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 bounding boxes. DetectionOutputParameters defines a set of parameters for creating the DetectionOutput plugin layer. It contains: |
CDims | Structure to define the dimensions of a tensor |
▼Cnvinfer1::Dims32 | |
►Cnvinfer1::Dims2 | Descriptor for two-dimensional data |
Cnvinfer1::DimsHW | Descriptor for two-dimensional spatial data |
Cnvinfer1::Dims3 | Descriptor for three-dimensional data |
Cnvinfer1::Dims4 | Descriptor 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::FieldMap | An array of field params used as a layer parameter for plugin layers |
Cnvinfer1::safe::FloatingPointErrorInformation | Space to record information about floating point runtime errors |
Cnvinfer1::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: |
Cnvinfer1::IAlgorithmSelector | Interface implemented by application for selecting and reporting algorithms of a layer provided by the builder |
Cnvcaffeparser1::IBinaryProtoBlob | Object used to store and query data extracted from a binaryproto file using the ICaffeParser |
Cnvcaffeparser1::IBlobNameToTensor | Object used to store and query Tensors after they have been extracted from a Caffe model using the ICaffeParser |
Cnvcaffeparser1::ICaffeParser | Class used for parsing Caffe models |
Cnvinfer1::consistency::IConsistencyChecker | Validates a serialized engine blob |
Cnvinfer1::safe::ICudaEngine | A functionally safe engine for executing inference on a built network |
Cnvinfer1::IErrorRecorder | Reference counted application-implemented error reporting interface for TensorRT objects |
Cnvinfer1::safe::IExecutionContext | Functionally safe context for executing inference using an engine |
Cnvinfer1::IGpuAllocator | Application-implemented class for controlling allocation on the GPU |
▼Cnvinfer1::IInt8Calibrator | Application-implemented interface for calibration |
Cnvinfer1::IInt8EntropyCalibrator | |
Cnvinfer1::IInt8EntropyCalibrator2 | |
Cnvinfer1::IInt8LegacyCalibrator | |
Cnvinfer1::IInt8MinMaxCalibrator | |
Cnvinfer1::ILogger | Application-implemented logging interface for the builder, refitter and runtime |
▼Cnvinfer1::INoCopy | Forward declaration of IEngineInspector for use by other interfaces |
Cnvinfer1::IAlgorithm | Describes 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::IAlgorithmContext | Describes the context and requirements, that could be fulfilled by one or more instances of IAlgorithm |
Cnvinfer1::IAlgorithmIOInfo | Carries 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::IAlgorithmVariant | Unique 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::IBuilder | Builds an engine from a network definition |
Cnvinfer1::IBuilderConfig | Holds properties for configuring a builder to produce an engine |
Cnvinfer1::ICudaEngine | An engine for executing inference on a built network, with functionally unsafe features |
Cnvinfer1::IDimensionExpr | |
Cnvinfer1::IEngineInspector | An engine inspector which prints out the layer information of an engine or an execution context |
Cnvinfer1::IExecutionContext | Context for executing inference using an engine, with functionally unsafe features |
Cnvinfer1::IExprBuilder | |
Cnvinfer1::IHostMemory | Class to handle library allocated memory that is accessible to the user |
Cnvinfer1::IIfConditional | |
►Cnvinfer1::ILayer | Base class for all layer classes in a network definition |
Cnvinfer1::IActivationLayer | An Activation layer in a network definition |
Cnvinfer1::IAssertionLayer | An assertion layer in a network |
Cnvinfer1::IConcatenationLayer | A concatenation layer in a network definition |
Cnvinfer1::IConstantLayer | Layer that represents a constant value |
Cnvinfer1::IConvolutionLayer | A convolution layer in a network definition |
Cnvinfer1::IDeconvolutionLayer | A deconvolution layer in a network definition |
Cnvinfer1::IDequantizeLayer | A Dequantize layer in a network definition |
Cnvinfer1::IEinsumLayer | An Einsum layer in a network |
Cnvinfer1::IElementWiseLayer | A elementwise layer in a network definition |
Cnvinfer1::IFillLayer | Generate an output tensor with specified mode |
Cnvinfer1::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: |
Cnvinfer1::IGatherLayer | A Gather layer in a network definition. Supports several kinds of gathering |
Cnvinfer1::IIdentityLayer | A layer that represents the identity function |
►Cnvinfer1::IIfConditionalBoundaryLayer | |
Cnvinfer1::IConditionLayer | |
Cnvinfer1::IIfConditionalInputLayer | |
Cnvinfer1::IIfConditionalOutputLayer | |
Cnvinfer1::ILRNLayer | A LRN layer in a network definition |
►Cnvinfer1::ILoopBoundaryLayer | |
Cnvinfer1::IIteratorLayer | |
Cnvinfer1::ILoopOutputLayer | |
Cnvinfer1::IRecurrenceLayer | |
Cnvinfer1::ITripLimitLayer | |
Cnvinfer1::IMatrixMultiplyLayer | Layer that represents a Matrix Multiplication |
Cnvinfer1::IPaddingLayer | Layer that represents a padding operation |
Cnvinfer1::IParametricReLULayer | Layer that represents a parametric ReLU operation |
Cnvinfer1::IPluginV2Layer | Layer type for pluginV2 |
Cnvinfer1::IPoolingLayer | A Pooling layer in a network definition |
Cnvinfer1::IQuantizeLayer | A Quantize layer in a network definition |
Cnvinfer1::IRNNv2Layer | An RNN layer in a network definition, version 2 |
Cnvinfer1::IRaggedSoftMaxLayer | A RaggedSoftmax layer in a network definition |
Cnvinfer1::IReduceLayer | Layer that represents a reduction across a non-bool tensor |
Cnvinfer1::IResizeLayer | A resize layer in a network definition |
Cnvinfer1::IScaleLayer | A Scale layer in a network definition |
Cnvinfer1::IScatterLayer | A scatter layer in a network definition. Supports several kinds of scattering |
Cnvinfer1::ISelectLayer | |
Cnvinfer1::IShapeLayer | Layer type for getting shape of a tensor |
Cnvinfer1::IShuffleLayer | Layer type for shuffling data |
Cnvinfer1::ISliceLayer | Slices an input tensor into an output tensor based on the offset and strides |
Cnvinfer1::ISoftMaxLayer | A Softmax layer in a network definition |
Cnvinfer1::ITopKLayer | Layer that represents a TopK reduction |
Cnvinfer1::IUnaryLayer | Layer that represents an unary operation |
Cnvinfer1::ILoop | |
Cnvinfer1::INetworkDefinition | A network definition for input to the builder |
Cnvinfer1::IOptimizationProfile | Optimization profile for dynamic input dimensions and shape tensors |
Cnvinfer1::IRefitter | Updates weights in an engine |
Cnvinfer1::IRuntime | Allows a serialized functionally unsafe engine to be deserialized |
Cnvinfer1::ITensor | A tensor in a network definition |
Cnvinfer1::ITimingCache | Class to handle tactic timing info collected from builder |
Cnvonnxparser::IOnnxConfig | Configuration Manager Class |
Cnvonnxparser::IParser | Object for parsing ONNX models into a TensorRT network definition |
Cnvonnxparser::IParserError | Object containing information about an error |
▼Cnvinfer1::IPluginCreator | Plugin creator class for user implemented layers |
Cnvinfer1::consistency::IPluginChecker | Consistency Checker plugin class for user implemented Plugins |
Cnvcaffeparser1::IPluginFactoryV2 | Plugin factory used to configure plugins |
Cnvinfer1::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 |
▼Cnvinfer1::IPluginV2 | Plugin class for user-implemented layers |
►Cnvinfer1::IPluginV2Ext | Plugin class for user-implemented layers |
Cnvinfer1::IPluginV2DynamicExt | |
Cnvinfer1::IPluginV2IOExt | Plugin class for user-implemented layers |
Cnvinfer1::IProfiler | Application-implemented interface for profiling |
Cnvinfer1::safe::IRuntime | Allows a serialized functionally safe engine to be deserialized |
Cnvuffparser::IUffParser | Class used for parsing models described using the UFF format |
Cnvinfer1::plugin::NMSParameters | The NMSParameters are used by the BatchedNMSPlugin for performing the non_max_suppression operation over boxes for object detection networks |
Cnvinfer1::Permutation | |
Cnvinfer1::PluginField | Structure containing plugin attribute field names and associated data This information can be parsed to decode necessary plugin metadata |
Cnvinfer1::PluginFieldCollection | Plugin 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::PluginTensorDesc | Fields that a plugin might see for an input or output |
CPluginVersion | Definition of plugin versions |
Cnvinfer1::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: |
Cnvinfer1::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 |
Cnvinfer1::plugin::RegionParameters | 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 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::RPROIParams | RPROIParams is used to create the RPROIPlugin instance. It contains: |
Cnvinfer1::plugin::softmaxTree | 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 |
Cnvinfer1::Weights | An array of weights used as a layer parameter |