TensorRT 8.2.1
|
Go to the source code of this file.
Classes | |
struct | nvinfer1::impl::EnumMaxImpl< ActivationType > |
Maximum number of elements in ActivationType enum. More... | |
class | nvinfer1::ITensor |
A tensor in a network definition. More... | |
class | nvinfer1::ILayer |
Base class for all layer classes in a network definition. More... | |
struct | nvinfer1::impl::EnumMaxImpl< PaddingMode > |
Maximum number of elements in PaddingMode enum. More... | |
class | nvinfer1::IConvolutionLayer |
A convolution layer in a network definition. More... | |
class | 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: More... | |
class | nvinfer1::IActivationLayer |
An Activation layer in a network definition. More... | |
struct | nvinfer1::impl::EnumMaxImpl< PoolingType > |
Maximum number of elements in PoolingType enum. More... | |
class | nvinfer1::IPoolingLayer |
A Pooling layer in a network definition. More... | |
class | nvinfer1::ILRNLayer |
A LRN layer in a network definition. More... | |
class | nvinfer1::IScaleLayer |
A Scale layer in a network definition. More... | |
class | nvinfer1::ISoftMaxLayer |
A Softmax layer in a network definition. More... | |
class | nvinfer1::IConcatenationLayer |
A concatenation layer in a network definition. More... | |
class | nvinfer1::IDeconvolutionLayer |
A deconvolution layer in a network definition. More... | |
struct | nvinfer1::impl::EnumMaxImpl< ElementWiseOperation > |
Maximum number of elements in ElementWiseOperation enum. More... | |
class | nvinfer1::IElementWiseLayer |
A elementwise layer in a network definition. More... | |
class | nvinfer1::IGatherLayer |
A Gather layer in a network definition. Supports several kinds of gathering. More... | |
class | nvinfer1::IRNNv2Layer |
An RNN layer in a network definition, version 2. More... | |
class | nvinfer1::IPluginV2Layer |
Layer type for pluginV2. More... | |
class | nvinfer1::IUnaryLayer |
Layer that represents an unary operation. More... | |
class | nvinfer1::IReduceLayer |
Layer that represents a reduction operator across Shape, Int32, Float, Half, and Int8 tensors. More... | |
class | nvinfer1::IPaddingLayer |
Layer that represents a padding operation. More... | |
struct | nvinfer1::Permutation |
class | nvinfer1::IShuffleLayer |
Layer type for shuffling data. More... | |
class | nvinfer1::ISliceLayer |
Slices an input tensor into an output tensor based on the offset and strides. More... | |
class | nvinfer1::IShapeLayer |
Layer type for getting shape of a tensor. More... | |
class | nvinfer1::ITopKLayer |
Layer that represents a TopK reduction. More... | |
class | nvinfer1::IMatrixMultiplyLayer |
Layer that represents a Matrix Multiplication. More... | |
class | nvinfer1::IRaggedSoftMaxLayer |
A RaggedSoftmax layer in a network definition. More... | |
class | nvinfer1::IIdentityLayer |
A layer that represents the identity function. More... | |
class | nvinfer1::IConstantLayer |
Layer that represents a constant value. More... | |
class | nvinfer1::IParametricReLULayer |
Layer that represents a parametric ReLU operation. More... | |
struct | nvinfer1::impl::EnumMaxImpl< ResizeMode > |
Maximum number of elements in ResizeMode enum. More... | |
struct | nvinfer1::impl::EnumMaxImpl< ResizeCoordinateTransformation > |
Maximum number of elements in ResizeCoordinateTransformation enum. More... | |
struct | nvinfer1::impl::EnumMaxImpl< ResizeSelector > |
Maximum number of elements in ResizeSelector enum. More... | |
struct | nvinfer1::impl::EnumMaxImpl< ResizeRoundMode > |
Maximum number of elements in ResizeRoundMode enum. More... | |
class | nvinfer1::IResizeLayer |
A resize layer in a network definition. More... | |
class | nvinfer1::ILoopBoundaryLayer |
class | nvinfer1::IIfConditionalBoundaryLayer |
class | nvinfer1::IConditionLayer |
class | nvinfer1::IIfConditionalOutputLayer |
class | nvinfer1::IIfConditionalInputLayer |
class | nvinfer1::IIfConditional |
class | nvinfer1::IRecurrenceLayer |
class | nvinfer1::ILoopOutputLayer |
class | nvinfer1::ITripLimitLayer |
class | nvinfer1::IIteratorLayer |
class | nvinfer1::ILoop |
class | nvinfer1::ISelectLayer |
class | nvinfer1::IAssertionLayer |
An assertion layer in a network. More... | |
class | nvinfer1::IFillLayer |
Generate an output tensor with specified mode. More... | |
class | nvinfer1::IQuantizeLayer |
A Quantize layer in a network definition. More... | |
class | nvinfer1::IDequantizeLayer |
A Dequantize layer in a network definition. More... | |
class | nvinfer1::IEinsumLayer |
An Einsum layer in a network. More... | |
class | nvinfer1::IScatterLayer |
A scatter layer in a network definition. Supports several kinds of scattering. More... | |
class | nvinfer1::INetworkDefinition |
A network definition for input to the builder. More... | |
class | nvinfer1::IInt8Calibrator |
Application-implemented interface for calibration. More... | |
class | nvinfer1::IInt8EntropyCalibrator |
class | nvinfer1::IInt8EntropyCalibrator2 |
class | nvinfer1::IInt8MinMaxCalibrator |
class | nvinfer1::IInt8LegacyCalibrator |
class | nvinfer1::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(). More... | |
class | nvinfer1::IAlgorithmVariant |
provides a 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() More... | |
class | nvinfer1::IAlgorithmContext |
Describes the context and requirements, that could be fulfilled by one or more instances of IAlgorithm. More... | |
class | nvinfer1::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().". More... | |
class | nvinfer1::IAlgorithmSelector |
Interface implemented by application for selecting and reporting algorithms of a layer provided by the builder. More... | |
class | nvinfer1::ITimingCache |
Class to handle tactic timing info collected from builder. More... | |
class | nvinfer1::IBuilderConfig |
Holds properties for configuring a builder to produce an engine. More... | |
class | nvinfer1::IBuilder |
Builds an engine from a network definition. More... | |
Namespaces | |
namespace | nvinfer1 |
The TensorRT API version 1 namespace. | |
Typedefs | |
using | nvinfer1::TensorFormats = uint32_t |
It is capable of representing one or more TensorFormat by binary OR operations, e.g., 1U << TensorFormat::kCHW4 | 1U << TensorFormat::kCHW32. More... | |
using | nvinfer1::QuantizationFlags = uint32_t |
Represents one or more QuantizationFlag values using binary OR operations. More... | |
using | nvinfer1::BuilderFlags = uint32_t |
Represents one or more QuantizationFlag values using binary OR operations, e.g., 1U << BuilderFlag::kFP16 | 1U << BuilderFlag::kDEBUG. More... | |
using | nvinfer1::NetworkDefinitionCreationFlags = uint32_t |
Represents one or more NetworkDefinitionCreationFlag flags using binary OR operations. e.g., 1U << NetworkDefinitionCreationFlag::kEXPLICIT_BATCH. More... | |
Enumerations | |
enum class | nvinfer1::LayerType : int32_t { nvinfer1::kCONVOLUTION = 0 , nvinfer1::kFULLY_CONNECTED = 1 , nvinfer1::kACTIVATION = 2 , nvinfer1::kPOOLING = 3 , nvinfer1::kLRN = 4 , nvinfer1::kSCALE = 5 , nvinfer1::kSOFTMAX = 6 , nvinfer1::kDECONVOLUTION = 7 , nvinfer1::kCONCATENATION = 8 , nvinfer1::kELEMENTWISE = 9 , nvinfer1::kPLUGIN = 10 , nvinfer1::kUNARY = 11 , nvinfer1::kPADDING = 12 , nvinfer1::kSHUFFLE = 13 , nvinfer1::kREDUCE = 14 , nvinfer1::kTOPK = 15 , nvinfer1::kGATHER = 16 , nvinfer1::kMATRIX_MULTIPLY = 17 , nvinfer1::kRAGGED_SOFTMAX = 18 , nvinfer1::kCONSTANT = 19 , nvinfer1::kRNN_V2 = 20 , nvinfer1::kIDENTITY = 21 , nvinfer1::kPLUGIN_V2 = 22 , nvinfer1::kSLICE = 23 , nvinfer1::kSHAPE = 24 , nvinfer1::kPARAMETRIC_RELU = 25 , nvinfer1::kRESIZE = 26 , nvinfer1::kTRIP_LIMIT = 27 , nvinfer1::kRECURRENCE = 28 , nvinfer1::kITERATOR = 29 , nvinfer1::kLOOP_OUTPUT = 30 , nvinfer1::kSELECT = 31 , nvinfer1::kFILL = 32 , nvinfer1::kQUANTIZE = 33 , nvinfer1::kDEQUANTIZE = 34 , nvinfer1::kCONDITION = 35 , nvinfer1::kCONDITIONAL_INPUT = 36 , nvinfer1::kCONDITIONAL_OUTPUT = 37 , nvinfer1::kSCATTER = 38 , nvinfer1::kEINSUM = 39 , nvinfer1::kASSERTION = 40 } |
The type values of layer classes. More... | |
enum class | nvinfer1::ActivationType : int32_t { nvinfer1::kRELU = 0 , nvinfer1::kSIGMOID = 1 , nvinfer1::kTANH = 2 , nvinfer1::kLEAKY_RELU = 3 , nvinfer1::kELU = 4 , nvinfer1::kSELU = 5 , nvinfer1::kSOFTSIGN = 6 , nvinfer1::kSOFTPLUS = 7 , nvinfer1::kCLIP = 8 , nvinfer1::kHARD_SIGMOID = 9 , nvinfer1::kSCALED_TANH = 10 , nvinfer1::kTHRESHOLDED_RELU = 11 } |
Enumerates the types of activation to perform in an activation layer. More... | |
enum class | nvinfer1::PaddingMode : int32_t { nvinfer1::kEXPLICIT_ROUND_DOWN = 0 , nvinfer1::kEXPLICIT_ROUND_UP = 1 , nvinfer1::kSAME_UPPER = 2 , nvinfer1::kSAME_LOWER = 3 , nvinfer1::kCAFFE_ROUND_DOWN = 4 , nvinfer1::kCAFFE_ROUND_UP = 5 } |
Enumerates the modes of padding to perform in convolution, deconvolution and pooling layer, padding mode takes precedence if setPaddingMode() and setPrePadding() are also used. More... | |
enum class | nvinfer1::PoolingType : int32_t { kMAX = 0 , kAVERAGE = 1 , kMAX_AVERAGE_BLEND = 2 } |
The type of pooling to perform in a pooling layer. | |
enum class | nvinfer1::ScaleMode : int32_t { nvinfer1::kUNIFORM = 0 , nvinfer1::kCHANNEL = 1 , nvinfer1::kELEMENTWISE = 2 } |
Controls how shift, scale and power are applied in a Scale layer. More... | |
enum class | nvinfer1::ElementWiseOperation : int32_t { nvinfer1::kSUM = 0 , nvinfer1::kPROD = 1 , nvinfer1::kMAX = 2 , nvinfer1::kMIN = 3 , nvinfer1::kSUB = 4 , nvinfer1::kDIV = 5 , nvinfer1::kPOW = 6 , nvinfer1::kFLOOR_DIV = 7 , nvinfer1::kAND = 8 , nvinfer1::kOR = 9 , nvinfer1::kXOR = 10 , nvinfer1::kEQUAL = 11 , nvinfer1::kGREATER = 12 , nvinfer1::kLESS = 13 } |
Enumerates the binary operations that may be performed by an ElementWise layer. More... | |
enum class | nvinfer1::GatherMode : int32_t { nvinfer1::kDEFAULT = 0 , nvinfer1::kELEMENT = 1 , nvinfer1::kND = 2 } |
Control form of IGatherLayer. More... | |
enum class | nvinfer1::RNNOperation : int32_t { nvinfer1::kRELU = 0 , nvinfer1::kTANH = 1 , nvinfer1::kLSTM = 2 , nvinfer1::kGRU = 3 } |
Enumerates the RNN operations that may be performed by an RNN layer. More... | |
enum class | nvinfer1::RNNDirection : int32_t { nvinfer1::kUNIDIRECTION = 0 , nvinfer1::kBIDIRECTION = 1 } |
Enumerates the RNN direction that may be performed by an RNN layer. More... | |
enum class | nvinfer1::RNNInputMode : int32_t { nvinfer1::kLINEAR = 0 , nvinfer1::kSKIP = 1 } |
Enumerates the RNN input modes that may occur with an RNN layer. More... | |
enum class | nvinfer1::RNNGateType : int32_t { nvinfer1::kINPUT = 0 , nvinfer1::kOUTPUT = 1 , nvinfer1::kFORGET = 2 , nvinfer1::kUPDATE = 3 , nvinfer1::kRESET = 4 , nvinfer1::kCELL = 5 , nvinfer1::kHIDDEN = 6 } |
Identifies an individual gate within an RNN cell. More... | |
enum class | nvinfer1::UnaryOperation : int32_t { nvinfer1::kEXP = 0 , nvinfer1::kLOG = 1 , nvinfer1::kSQRT = 2 , nvinfer1::kRECIP = 3 , nvinfer1::kABS = 4 , nvinfer1::kNEG = 5 , nvinfer1::kSIN = 6 , nvinfer1::kCOS = 7 , nvinfer1::kTAN = 8 , nvinfer1::kSINH = 9 , nvinfer1::kCOSH = 10 , nvinfer1::kASIN = 11 , nvinfer1::kACOS = 12 , nvinfer1::kATAN = 13 , nvinfer1::kASINH = 14 , nvinfer1::kACOSH = 15 , nvinfer1::kATANH = 16 , nvinfer1::kCEIL = 17 , nvinfer1::kFLOOR = 18 , nvinfer1::kERF = 19 , nvinfer1::kNOT = 20 , nvinfer1::kSIGN = 21 , nvinfer1::kROUND = 22 } |
Enumerates the unary operations that may be performed by a Unary layer. More... | |
enum class | nvinfer1::ReduceOperation : int32_t { kSUM = 0 , kPROD = 1 , kMAX = 2 , kMIN = 3 , kAVG = 4 } |
Enumerates the reduce operations that may be performed by a Reduce layer. More... | |
enum class | nvinfer1::SliceMode : int32_t { nvinfer1::kDEFAULT = 0 , nvinfer1::kWRAP = 1 , nvinfer1::kCLAMP = 2 , nvinfer1::kFILL = 3 , nvinfer1::kREFLECT = 4 } |
Controls how ISliceLayer handles out of bounds coordinates. More... | |
enum class | nvinfer1::TopKOperation : int32_t { nvinfer1::kMAX = 0 , nvinfer1::kMIN = 1 } |
Enumerates the operations that may be performed by a TopK layer. More... | |
enum class | nvinfer1::MatrixOperation : int32_t { nvinfer1::kNONE , nvinfer1::kTRANSPOSE , nvinfer1::kVECTOR } |
Enumerates the operations that may be performed on a tensor by IMatrixMultiplyLayer before multiplication. More... | |
enum class | nvinfer1::ResizeMode : int32_t { nvinfer1::kNEAREST = 0 , nvinfer1::kLINEAR = 1 } |
Enumerates various modes of resize in the resize layer. Resize mode set using setResizeMode(). More... | |
enum class | nvinfer1::ResizeCoordinateTransformation : int32_t { nvinfer1::kALIGN_CORNERS = 0 , nvinfer1::kASYMMETRIC = 1 , nvinfer1::kHALF_PIXEL = 2 } |
The resize coordinate transformation function. More... | |
enum class | nvinfer1::ResizeSelector : int32_t { nvinfer1::kFORMULA = 0 , nvinfer1::kUPPER = 1 } |
The coordinate selector when resize to single pixel output. More... | |
enum class | nvinfer1::ResizeRoundMode : int32_t { nvinfer1::kHALF_UP = 0 , nvinfer1::kHALF_DOWN = 1 , nvinfer1::kFLOOR = 2 , nvinfer1::kCEIL = 3 } |
The rounding mode for nearest neighbor resize. More... | |
enum class | nvinfer1::LoopOutput : int32_t { nvinfer1::kLAST_VALUE = 0 , nvinfer1::kCONCATENATE = 1 , nvinfer1::kREVERSE = 2 } |
Enum that describes kinds of loop outputs. More... | |
enum class | nvinfer1::TripLimit : int32_t { nvinfer1::kCOUNT = 0 , nvinfer1::kWHILE = 1 } |
Enum that describes kinds of trip limits. More... | |
enum class | nvinfer1::FillOperation : int32_t { nvinfer1::kLINSPACE = 0 , nvinfer1::kRANDOM_UNIFORM = 1 } |
Enumerates the tensor fill operations that may performed by a fill layer. More... | |
enum class | nvinfer1::ScatterMode : int32_t { nvinfer1::kELEMENT = 0 , nvinfer1::kND = 1 } |
Control form of IScatterLayer. More... | |
enum class | nvinfer1::CalibrationAlgoType : int32_t { kLEGACY_CALIBRATION = 0 , kENTROPY_CALIBRATION = 1 , kENTROPY_CALIBRATION_2 = 2 , kMINMAX_CALIBRATION = 3 } |
Version of calibration algorithm to use. More... | |
enum class | nvinfer1::QuantizationFlag : int32_t { nvinfer1::kCALIBRATE_BEFORE_FUSION = 0 } |
List of valid flags for quantizing the network to int8. More... | |
enum class | nvinfer1::BuilderFlag : int32_t { nvinfer1::kFP16 = 0 , nvinfer1::kINT8 = 1 , nvinfer1::kDEBUG = 2 , nvinfer1::kGPU_FALLBACK = 3 , nvinfer1::kSTRICT_TYPES = 4 , nvinfer1::kREFIT = 5 , nvinfer1::kDISABLE_TIMING_CACHE = 6 , nvinfer1::kTF32 = 7 , nvinfer1::kSPARSE_WEIGHTS = 8 , nvinfer1::kSAFETY_SCOPE = 9 , nvinfer1::kOBEY_PRECISION_CONSTRAINTS = 10 , nvinfer1::kPREFER_PRECISION_CONSTRAINTS = 11 , nvinfer1::kDIRECT_IO = 12 , nvinfer1::kREJECT_EMPTY_ALGORITHMS = 13 } |
List of valid modes that the builder can enable when creating an engine from a network definition. More... | |
enum class | nvinfer1::NetworkDefinitionCreationFlag : int32_t { nvinfer1::kEXPLICIT_BATCH = 0 , nvinfer1::kEXPLICIT_PRECISION = 1 } |
List of immutable network properties expressed at network creation time. NetworkDefinitionCreationFlag is used with createNetworkV2 to specify immutable properties of the network. The createNetwork() function always had an implicit batch dimension being specified by the maxBatchSize builder parameter. createNetworkV2 with kDEFAULT flag mimics that behaviour. More... | |
Functions | |
template<> | |
constexpr int32_t | nvinfer1::EnumMax< LayerType > () noexcept |
Maximum number of elements in LayerType enum. More... | |
template<> | |
constexpr int32_t | nvinfer1::EnumMax< ScaleMode > () noexcept |
Maximum number of elements in ScaleMode enum. More... | |
template<> | |
constexpr int32_t | nvinfer1::EnumMax< GatherMode > () noexcept |
Maximum number of elements in GatherMode enum. More... | |
template<> | |
constexpr int32_t | nvinfer1::EnumMax< RNNOperation > () noexcept |
Maximum number of elements in RNNOperation enum. More... | |
template<> | |
constexpr int32_t | nvinfer1::EnumMax< RNNDirection > () noexcept |
Maximum number of elements in RNNDirection enum. More... | |
template<> | |
constexpr int32_t | nvinfer1::EnumMax< RNNInputMode > () noexcept |
Maximum number of elements in RNNInputMode enum. More... | |
template<> | |
constexpr int32_t | nvinfer1::EnumMax< RNNGateType > () noexcept |
Maximum number of elements in RNNGateType enum. More... | |
template<> | |
constexpr int32_t | nvinfer1::EnumMax< UnaryOperation > () noexcept |
Maximum number of elements in UnaryOperation enum. More... | |
template<> | |
constexpr int32_t | nvinfer1::EnumMax< ReduceOperation > () noexcept |
Maximum number of elements in ReduceOperation enum. More... | |
template<> | |
constexpr int32_t | nvinfer1::EnumMax< SliceMode > () noexcept |
Maximum number of elements in SliceMode enum. More... | |
template<> | |
constexpr int32_t | nvinfer1::EnumMax< TopKOperation > () noexcept |
Maximum number of elements in TopKOperation enum. More... | |
template<> | |
constexpr int32_t | nvinfer1::EnumMax< MatrixOperation > () noexcept |
Maximum number of elements in MatrixOperation enum. More... | |
template<> | |
constexpr int32_t | nvinfer1::EnumMax< LoopOutput > () noexcept |
Maximum number of elements in LoopOutput enum. More... | |
template<> | |
constexpr int32_t | nvinfer1::EnumMax< TripLimit > () noexcept |
Maximum number of elements in TripLimit enum. More... | |
template<> | |
constexpr int32_t | nvinfer1::EnumMax< FillOperation > () noexcept |
Maximum number of elements in FillOperation enum. More... | |
template<> | |
constexpr int32_t | nvinfer1::EnumMax< ScatterMode > () noexcept |
Maximum number of elements in ScatterMode enum. More... | |
template<> | |
constexpr int32_t | nvinfer1::EnumMax< CalibrationAlgoType > () noexcept |
Maximum number of elements in CalibrationAlgoType enum. More... | |
template<> | |
constexpr int32_t | nvinfer1::EnumMax< QuantizationFlag > () noexcept |
Maximum number of quantization flags in QuantizationFlag enum. More... | |
template<> | |
constexpr int32_t | nvinfer1::EnumMax< BuilderFlag > () noexcept |
Maximum number of builder flags in BuilderFlag enum. More... | |
template<> | |
constexpr int32_t | nvinfer1::EnumMax< NetworkDefinitionCreationFlag > () noexcept |
Maximum number of elements in NetworkDefinitionCreationFlag enum. More... | |
IBuilder * | nvinfer1::anonymous_namespace{NvInfer.h}::createInferBuilder (ILogger &logger) noexcept |
Create an instance of an IBuilder class. More... | |
TensorRT Versioning follows Semantic Versioning Guidelines specified here: https://semver.org/
This is the top-level API file for TensorRT.