A network definition for input to the builder. More...

#include <NvInfer.h>

Inheritance diagram for nvinfer1::INetworkDefinition:

Public Member Functions
virtual	~INetworkDefinition () noexcept=default

ITensor *	addInput (char const *name, DataType type, Dims const &dimensions) noexcept
	Add an input tensor to the network. More...

void	markOutput (ITensor &tensor) noexcept
	Mark a tensor as a network output. More...

bool	markDebug (ITensor &tensor) noexcept
	Mark a tensor as a debug tensor. More...

bool	unmarkDebug (ITensor &tensor) noexcept
	Unmark a tensor as a debug tensor. More...

bool	isDebugTensor (nvinfer1::ITensor const &tensor) const noexcept
	Check if a tensor is marked as debug tensor. More...

IActivationLayer *	addActivation (ITensor &input, ActivationType type) noexcept
	Add an activation layer to the network. More...

ILRNLayer *	addLRN (ITensor &input, int64_t window, float alpha, float beta, float k) noexcept
	Add a LRN layer to the network. More...

IScaleLayer *	addScale (ITensor &input, ScaleMode mode, Weights shift, Weights scale, Weights power) noexcept
	Add a Scale layer to the network. More...

ISoftMaxLayer *	addSoftMax (ITensor &input) noexcept
	Add a SoftMax layer to the network. More...

IConcatenationLayer *	addConcatenation (ITensor const inputs, int32_t nbInputs) noexcept
	Add a concatenation layer to the network. More...

IElementWiseLayer *	addElementWise (ITensor &input1, ITensor &input2, ElementWiseOperation op) noexcept
	Add an elementwise layer to the network. More...

IUnaryLayer *	addUnary (ITensor &input, UnaryOperation operation) noexcept
	Add a unary layer to the network. More...

IShuffleLayer *	addShuffle (ITensor &input) noexcept
	Add a shuffle layer to the network. More...

IOneHotLayer *	addOneHot (ITensor &indices, ITensor &values, ITensor &depth, int32_t axis) noexcept
	Add a OneHot layer to the network. More...

int32_t	getNbLayers () const noexcept
	Get the number of layers in the network. More...

ILayer *	getLayer (int32_t index) const noexcept
	Get the layer specified by the given index. More...

int32_t	getNbInputs () const noexcept
	Get the number of inputs in the network. More...

ITensor *	getInput (int32_t index) const noexcept
	Get the input tensor specified by the given index. More...

int32_t	getNbOutputs () const noexcept
	Get the number of outputs in the network. More...

ITensor *	getOutput (int32_t index) const noexcept
	Get the output tensor specified by the given index. More...

IReduceLayer *	addReduce (ITensor &input, ReduceOperation operation, uint32_t reduceAxes, bool keepDimensions) noexcept
	Add a reduce layer to the network. More...

ITopKLayer *	addTopK (ITensor &input, TopKOperation op, int32_t k, uint32_t reduceAxes) noexcept
	Add a TopK layer to the network. More...

IGatherLayer *	addGather (ITensor &data, ITensor &indices, int32_t axis) noexcept
	Add gather with mode GatherMode::kDEFAULT and specified axis and nbElementWiseDims=0. More...

IGatherLayer *	addGatherV2 (ITensor &data, ITensor &indices, GatherMode mode) noexcept
	Add gather with specified mode, axis=0 and nbElementWiseDims=0. More...

IRaggedSoftMaxLayer *	addRaggedSoftMax (ITensor &input, ITensor &bounds) noexcept
	Add a RaggedSoftMax layer to the network. More...

IMatrixMultiplyLayer *	addMatrixMultiply (ITensor &input0, MatrixOperation op0, ITensor &input1, MatrixOperation op1) noexcept
	Add a MatrixMultiply layer to the network. More...

INonZeroLayer *	addNonZero (ITensor &input) noexcept
	Add a nonzero layer to the network. More...

IConstantLayer *	addConstant (Dims const &dimensions, Weights weights) noexcept
	Add a constant layer to the network. More...

IIdentityLayer *	addIdentity (ITensor &input) noexcept
	Add an identity layer. More...

ICastLayer *	addCast (ITensor &input, DataType toType) noexcept
	Add a cast layer. More...

void	removeTensor (ITensor &tensor) noexcept
	remove a tensor from the network definition. More...

void	unmarkOutput (ITensor &tensor) noexcept
	unmark a tensor as a network output. More...

TRT_DEPRECATED IPluginV2Layer *	addPluginV2 (ITensor const inputs, int32_t nbInputs, IPluginV2 &plugin) noexcept
	Add a plugin layer to the network using the IPluginV2 interface. More...

IPluginV3Layer *	addPluginV3 (ITensor const inputs, int32_t nbInputs, ITensor const shapeInputs, int32_t nbShapeInputs, IPluginV3 &plugin) noexcept
	Add a plugin layer implementing the IPluginV3 interface to the network. More...

ISliceLayer *	addSlice (ITensor &input, Dims const &start, Dims const &size, Dims const &stride) noexcept
	Add a slice layer to the network. More...

void	setName (char const *name) noexcept
	Sets the name of the network. More...

char const *	getName () const noexcept
	Returns the name associated with the network. More...

IShapeLayer *	addShape (ITensor &input) noexcept
	Add a shape layer to the network. More...

TRT_DEPRECATED bool	hasImplicitBatchDimension () const noexcept
	Query whether the network was created with an implicit batch dimension. More...

NetworkDefinitionCreationFlags	getFlags () const noexcept
	Get the network definition creation flags for this network definition object. Defaults to 0. More...

bool	getFlag (NetworkDefinitionCreationFlag networkDefinitionCreationFlag) const noexcept
	Returns true if the network definition creation flag is set. More...

bool	markOutputForShapes (ITensor &tensor) noexcept
	Enable tensor's value to be computed by IExecutionContext::getShapeBinding. More...

bool	unmarkOutputForShapes (ITensor &tensor) noexcept
	Undo markOutputForShapes. More...

IParametricReLULayer *	addParametricReLU (ITensor &input, ITensor &slope) noexcept
	Add a parametric ReLU layer to the network. More...

IConvolutionLayer *	addConvolutionNd (ITensor &input, int64_t nbOutputMaps, Dims const &kernelSize, Weights kernelWeights, Weights biasWeights) noexcept
	Add a multi-dimension convolution layer to the network. More...

IPoolingLayer *	addPoolingNd (ITensor &input, PoolingType type, Dims const &windowSize) noexcept
	Add a multi-dimension pooling layer to the network. More...

IDeconvolutionLayer *	addDeconvolutionNd (ITensor &input, int64_t nbOutputMaps, Dims kernelSize, Weights kernelWeights, Weights biasWeights) noexcept
	Add a multi-dimension deconvolution layer to the network. More...

IScaleLayer *	addScaleNd (ITensor &input, ScaleMode mode, Weights shift, Weights scale, Weights power, int32_t channelAxis) noexcept
	Add a multi-dimension scale layer to the network. More...

IResizeLayer *	addResize (ITensor &input) noexcept
	Add a resize layer to the network. More...

ILoop *	addLoop () noexcept
	Add a loop to the network. More...

IIfConditional *	addIfConditional () noexcept
	Add an if-then-else to the network. More...

ISelectLayer *	addSelect (ITensor &condition, ITensor &thenInput, ITensor &elseInput) noexcept
	Add a select layer to the network. More...

IAssertionLayer *	addAssertion (ITensor &condition, char const *message) noexcept
	Add an assertion layer to the network. More...

TRT_DEPRECATED IFillLayer *	addFill (Dims const &dimensions, FillOperation op) noexcept
	Add a fill layer to the network. More...

IFillLayer *	addFill (Dims const &dimensions, FillOperation op, DataType outputType) noexcept
	Add a fill layer to the network. More...

IPaddingLayer *	addPaddingNd (ITensor &input, Dims const &prePadding, Dims const &postPadding) noexcept
	Add a padding layer to the network. Only 2D padding is currently supported. More...

bool	setWeightsName (Weights weights, char const *name) noexcept
	Associate a name with all current uses of the given weights. More...

void	setErrorRecorder (IErrorRecorder *recorder) noexcept
	Set the ErrorRecorder for this interface. More...

IErrorRecorder *	getErrorRecorder () const noexcept
	get the ErrorRecorder assigned to this interface. More...

TRT_DEPRECATED IDequantizeLayer *	addDequantize (ITensor &input, ITensor &scale) noexcept
	Add a dequantization layer to the network. More...

IDequantizeLayer *	addDequantize (ITensor &input, ITensor &scale, DataType outputType) noexcept
	Add a dequantization layer to the network. More...

IScatterLayer *	addScatter (ITensor &data, ITensor &indices, ITensor &updates, ScatterMode mode) noexcept
	Add a Scatter layer to the network with specified mode and axis=0. More...

TRT_DEPRECATED IQuantizeLayer *	addQuantize (ITensor &input, ITensor &scale) noexcept
	Add a quantization layer to the network. More...

IQuantizeLayer *	addQuantize (ITensor &input, ITensor &scale, DataType outputType) noexcept
	Add a quantization layer to the network. More...

IDynamicQuantizeLayer *	addDynamicQuantize (ITensor &input, int32_t axis, int32_t blockSize, DataType outputType, DataType scaleType) noexcept
	Add a dynamic quantization layer to the network. More...

IEinsumLayer *	addEinsum (ITensor const inputs, int32_t nbInputs, char const *equation) noexcept
	Add an Einsum layer to the network. More...

IGridSampleLayer *	addGridSample (ITensor &input, ITensor &grid) noexcept
	Add a GridSample layer to the network. More...

INMSLayer *	addNMS (ITensor &boxes, ITensor &scores, ITensor &maxOutputBoxesPerClass) noexcept
	Add a non-maximum suppression layer to the network. More...

IReverseSequenceLayer *	addReverseSequence (ITensor &input, ITensor &sequenceLens) noexcept
	Add a ReverseSequence layer to the network. More...

INormalizationLayer *	addNormalization (ITensor &input, ITensor &scale, ITensor &bias, uint32_t axesMask) noexcept
	Add a normalization layer to the network. More...

ICumulativeLayer *	addCumulative (ITensor &input, ITensor &axis, CumulativeOperation operation, bool exclusive, bool reverse) noexcept
	Add a cumulative layer to the network. More...

virtual IBuilder &	getBuilder () const noexcept
	Return the builder from which this INetworkDefinition was created. More...

bool	markWeightsRefittable (char const *name) noexcept
	Mark weights as refittable when the builder flag kREFIT_INDIVIDUAL is set. More...

bool	unmarkWeightsRefittable (char const *name) noexcept
	Unmark weights as refittable when the builder flag kREFIT_INDIVIDUAL is set. More...

bool	areWeightsMarkedRefittable (char const *name) const noexcept
	Whether the weight has been marked as refittable. More...

ISqueezeLayer *	addSqueeze (ITensor &input, ITensor &axes) noexcept
	Add a squeeze layer to the network. More...

IUnsqueezeLayer *	addUnsqueeze (ITensor &input, ITensor &axes) noexcept
	Add an unsqueeze layer to the network. More...

Protected Attributes
apiv::VNetworkDefinition *	mImpl

Additional Inherited Members
Protected Member Functions inherited from nvinfer1::INoCopy
	INoCopy ()=default

virtual	~INoCopy ()=default

	INoCopy (INoCopy const &other)=delete

INoCopy &	operator= (INoCopy const &other)=delete

	INoCopy (INoCopy &&other)=delete

INoCopy &	operator= (INoCopy &&other)=delete

Detailed Description

A network definition for input to the builder.

A network definition defines the structure of the network, and combined with a IBuilderConfig, is built into an engine using an IBuilder. An INetworkDefinition can have all dimensions explicit, full dims mode, in the network definition. The former mode, i.e. the implicit batch size mode, has been deprecated.

A network with implicit batch dimensions returns the dimensions of a layer without the implicit dimension, and instead the batch is specified at execute/enqueue time. If the network has all dimensions specified, then the first dimension follows elementwise broadcast rules: if it is 1 for some inputs and is some value N for all other inputs, then the first dimension of each output is N, and the inputs with 1 for the first dimension are broadcast. Having divergent batch sizes across inputs to a layer is not supported.

Warning: Do not inherit from this class, as doing so will break forward-compatibility of the API and ABI.

Constructor & Destructor Documentation

◆ ~INetworkDefinition()

virtual nvinfer1::INetworkDefinition::~INetworkDefinition ( )

virtualdefaultnoexcept

Member Function Documentation

◆ addActivation()

IActivationLayer * nvinfer1::INetworkDefinition::addActivation	(	ITensor &	input,
		ActivationType	type
	)

inlinenoexcept

Add an activation layer to the network.

Parameters

input	The input tensor to the layer.
type	The type of activation function to apply.

Note that the setAlpha() and setBeta() methods must be used on the output for activations that require these parameters.

See also: IActivationLayer ActivationType

Warning: Int32 and Int64 are valid only for activation type kRELU.

Returns: The new activation layer, or nullptr if it could not be created.

◆ addAssertion()

IAssertionLayer * nvinfer1::INetworkDefinition::addAssertion	(	ITensor &	condition,
		char const *	message
	)

inlinenoexcept

Add an assertion layer to the network.

Parameters

condition	The input tensor to the layer.
message	A message to print if the assertion fails.

See also: IAssertionLayer

Returns: The new assertion layer, or nullptr if it could not be created.

The input tensor must be a boolean shape tensor.

◆ addCast()

ICastLayer * nvinfer1::INetworkDefinition::addCast	(	ITensor &	input,
		DataType	toType
	)

inlinenoexcept

Add a cast layer.

Parameters

input	The input tensor to the layer.
toType	The DataType of the output tensor

See also: ICastLayer

Returns: The new cast layer, or nullptr if it could not be created.

◆ addConcatenation()

IConcatenationLayer * nvinfer1::INetworkDefinition::addConcatenation	(	ITensor const	inputs,
		int32_t	nbInputs
	)

inlinenoexcept

Add a concatenation layer to the network.

Parameters

inputs	The input tensors to the layer.
nbInputs	The number of input tensors.

See also: IConcatenationLayer

Returns: The new concatenation layer, or nullptr if it could not be created.

Warning: All tensors must have the same dimensions except along the concatenation axis.

◆ addConstant()

IConstantLayer * nvinfer1::INetworkDefinition::addConstant	(	Dims const &	dimensions,
		Weights	weights
	)

inlinenoexcept

Add a constant layer to the network.

Parameters

dimensions	The dimensions of the constant.
weights	The constant value, represented as weights.

See also: IConstantLayer

Returns: The new constant layer, or nullptr if it could not be created.

If weights.type is DataType::kINT32, the output is a tensor of 32-bit indices. Otherwise the output is a tensor of real values and the output type will be follow TensorRT's normal precision rules.

If a wildcard dimension is used, the volume of the runtime dimensions must equal the number of weights specified.

Warning: DataType::kUINT8 not supported.

◆ addConvolutionNd()

IConvolutionLayer * nvinfer1::INetworkDefinition::addConvolutionNd	(	ITensor &	input,
		int64_t	nbOutputMaps,
		Dims const &	kernelSize,
		Weights	kernelWeights,
		Weights	biasWeights
	)

inlinenoexcept

Add a multi-dimension convolution layer to the network.

Parameters

input	The input tensor to the convolution.
nbOutputMaps	The number of output feature maps for the convolution.
kernelSize	The multi-dimensions of the convolution kernel.
kernelWeights	The kernel weights for the convolution.
biasWeights	The bias weights for the convolution. Weights{} represents no bias.

See also: IConvolutionLayer

Warning: It is an error to specify a wildcard value for the 'C' dimension of the input tensor.; Int32 tensors are not valid input tensors.; Only 2D or 3D convolution is supported.

Returns: The new convolution layer, or nullptr if it could not be created.

◆ addCumulative()

ICumulativeLayer * nvinfer1::INetworkDefinition::addCumulative	(	ITensor &	input,
		ITensor &	axis,
		CumulativeOperation	operation,
		bool	exclusive,
		bool	reverse
	)

inlinenoexcept

Add a cumulative layer to the network.

Parameters

input	The input tensor to the layer.
axis	The axis tensor to apply the cumulative operation on. Currently, it must be a build-time constant 0D shape tensor and must be in the range [-rank(input), rank(input)-1]. Negative value means counting dimensions from the back.
operation	The reduction operation to perform.
exclusive	The boolean that specifies whether it is an exclusive cumulative or inclusive cumulative.
reverse	The boolean that specifies whether the cumulative operation should be applied backward.

The cumulative layer works by performing the specified cumulative operation to the tensor input on the axis specified by axis.

See also: ICumulativeLayer

Returns: The new cumulative layer, or nullptr if it could not be created.

◆ addDeconvolutionNd()

IDeconvolutionLayer * nvinfer1::INetworkDefinition::addDeconvolutionNd	(	ITensor &	input,
		int64_t	nbOutputMaps,
		Dims	kernelSize,
		Weights	kernelWeights,
		Weights	biasWeights
	)

inlinenoexcept

Add a multi-dimension deconvolution layer to the network.

Parameters

input	The input tensor to the layer.
nbOutputMaps	The number of output feature maps.
kernelSize	The multi-dimensions of the deconvolution kernel.
kernelWeights	The kernel weights for the deconvolution.
biasWeights	The bias weights for the deconvolution. Weights{} represents no bias.

See also: IDeconvolutionLayer

Warning: It is an error to specify a wildcard value for the 'C' dimension of the input tensor.; Int32 tensors are not valid input tensors.; Only 2D or 3D deconvolution is supported.

Returns: The new deconvolution layer, or nullptr if it could not be created.

◆ addDequantize() [1/2]

TRT_DEPRECATED IDequantizeLayer * nvinfer1::INetworkDefinition::addDequantize	(	ITensor &	input,
		ITensor &	scale
	)

inlinenoexcept

Add a dequantization layer to the network.

Parameters

input	The input tensor to be quantized.
scale	A tensor with the scale value.

See also: IDequantizeLayer

input tensor data type must be DataType::kINT8 or DataType::kFP8. scale tensor data type must be DataType::kFLOAT. The subgraph which terminates with the scale tensor must be a build-time constant.

Returns: The new quantization layer, or nullptr if it could not be created.

Deprecated:: Deprecated in TensorRT 9.0. Superseded by three-argument addDequantize.

◆ addDequantize() [2/2]

IDequantizeLayer * nvinfer1::INetworkDefinition::addDequantize	(	ITensor &	input,
		ITensor &	scale,
		DataType	outputType
	)

inlinenoexcept

Add a dequantization layer to the network.

Parameters

input	The input tensor to be dequantized.
scale	A tensor with the scale value.
outputType	Output tensor data type.

See also: IDequantizeLayer

input tensor data type must be DataType::kINT8, DataType::kFP8 or DataType::kINT4. scale tensor data type defaults to DataType::kFLOAT. For strongly typed networks, it must be the same as the output data type. The subgraph which terminates with the scale tensor must be a build-time constant. outputType output tensor data type, default value is DataType::kFLOAT. Future calls to set output type using setToType or setOutputType must be consistent. For strongly typed networks, it must be the same as the scale data type.

Returns: The new quantization layer, or nullptr if it could not be created.

◆ addDynamicQuantize()

IDynamicQuantizeLayer * nvinfer1::INetworkDefinition::addDynamicQuantize	(	ITensor &	input,
		int32_t	axis,
		int32_t	blockSize,
		DataType	outputType,
		DataType	scaleType
	)

inlinenoexcept

Add a dynamic quantization layer to the network.

This layer performs dynamic block quantization of its input tensor and outputs the quantized data and the computed block scale-factors. The block size is currently limited to 16 and the size of the blocked axis must be divisible by 16.

Parameters

input	The input tensor to be quantized. Its data type must be one of DataType::kFLOAT, DataType::kHALF, or DataType::kBF16. Currently only 2D and 3D inputs are supported.
axis	The axis that is sliced into blocks. The axis must be the last or second to last dimension.
blockSize	The number of elements that are quantized using a shared scale factor. Currently only blocks of 16 elements are supported.
outputType	The data type of the quantized output tensor, must be DataType::kFP4. Future calls to set output type using setToType or setOutputType must be consistent.
scaleType	The data type of the scale factor used for quantizing the input data, must be DataType::kFP8.

Returns: The new dynamic quantization layer, or nullptr if it could not be created.

See also: IDynamicQuantizeLayer

◆ addEinsum()

IEinsumLayer * nvinfer1::INetworkDefinition::addEinsum	(	ITensor const	inputs,
		int32_t	nbInputs,
		char const *	equation
	)

inlinenoexcept

Add an Einsum layer to the network.

Parameters

inputs	The input tensors to the layer.
nbInputs	The number of input tensors.
equation	The equation of the layer

See also: IEinsumLayer

Returns: The new Einsum layer, or nullptr if it could not be created.

◆ addElementWise()

IElementWiseLayer * nvinfer1::INetworkDefinition::addElementWise	(	ITensor &	input1,
		ITensor &	input2,
		ElementWiseOperation	op
	)

inlinenoexcept

Add an elementwise layer to the network.

Parameters

input1	The first input tensor to the layer.
input2	The second input tensor to the layer.
op	The binary operation that the layer applies.

The input tensors must have the same rank and compatible type. Two types are compatible if they are the same type or are both in the set {kFLOAT, kHALF}. For each dimension, their lengths must match, or one of them must be one. In the latter case, the tensor is broadcast along that axis.

The output tensor has the same rank as the inputs. For each dimension, its length is the maximum of the lengths of the corresponding input dimension.

The inputs are shape tensors if the output is a shape tensor.

See also: IElementWiseLayer

Returns: The new elementwise layer, or nullptr if it could not be created.

◆ addFill() [1/2]

TRT_DEPRECATED IFillLayer * nvinfer1::INetworkDefinition::addFill	(	Dims const &	dimensions,
		FillOperation	op
	)

inlinenoexcept

Add a fill layer to the network.

Parameters

dimensions	The output tensor dimensions if input 0 is missing.
op	The fill operation that the layer applies.

Warning: For FillOperation::kLINSPACE, dimensions.nbDims must be 1 for static start/delta. If delta is provided as a 1D tensor, the length of delta must match dimensions.nbDims.

This layer is non-deterministic across subsequent calls as the same inputs will produce different output tensors if op is either FillOperation::kRANDOM_UNIFORM or FillOperation::kRANDOM_NORMAL due to random state being shared across calls. The output tensors generated are determinstic when starting from the same initial state.

See also: IFillLayer

Returns: The new fill layer, or nullptr if it could not be created.

Deprecated:: Deprecated in TensorRT 9.0. Superseded by three-argument addFill.

◆ addFill() [2/2]

IFillLayer * nvinfer1::INetworkDefinition::addFill	(	Dims const &	dimensions,
		FillOperation	op,
		DataType	outputType
	)

inlinenoexcept

Add a fill layer to the network.

Parameters

dimensions	The output tensor dimensions if input 0 is missing.
op	The fill operation that the layer applies.
outputType	Optional output tensor data type, must be DataType::kFLOAT, DataType::kHALF, DataType::kINT32, or DataType::kINT64. This parameter is only used for static alpha/beta. Future calls to set output type using setToType or setOutputType must be consistent.

Warning: For FillOperation::kLINSPACE, dimensions.nbDims must be 1 for static start/delta. If delta is provided as a 1D tensor, the length of delta must match dimensions.nbDims.

This layer is non-deterministic across subsequent calls as the same inputs will produce different output tensors if op is either FillOperation::kRANDOM_UNIFORM or FillOperation::kRANDOM_NORMAL due to random state being shared across calls. The output tensors generated are deterministic when starting from the same initial state.

See also: IFillLayer

Returns: The new fill layer, or nullptr if it could not be created.

◆ addGather()

IGatherLayer * nvinfer1::INetworkDefinition::addGather	(	ITensor &	data,
		ITensor &	indices,
		int32_t	axis
	)

inlinenoexcept

Add gather with mode GatherMode::kDEFAULT and specified axis and nbElementWiseDims=0.

Parameters

data	The tensor to gather values from.
indices	The tensor to get indices from to populate the output tensor.
axis	The axis in the data tensor to gather on.

See also: IGatherLayer

Returns: The new gather layer, or nullptr if it could not be created.

◆ addGatherV2()

IGatherLayer * nvinfer1::INetworkDefinition::addGatherV2	(	ITensor &	data,
		ITensor &	indices,
		GatherMode	mode
	)

inlinenoexcept

Add gather with specified mode, axis=0 and nbElementWiseDims=0.

Parameters

data	The tensor to gather values from.
indices	The tensor to get indices from to populate the output tensor.
mode	The gather mode.

See also: IGatherLayer

Returns: The new gather layer, or nullptr if it could not be created.

◆ addGridSample()

IGridSampleLayer * nvinfer1::INetworkDefinition::addGridSample	(	ITensor &	input,
		ITensor &	grid
	)

inlinenoexcept

Add a GridSample layer to the network.

Parameters

input	The input tensor to the layer.
grid	The grid tensor to the layer.

See also: IGridSampleLayer

Creates a GridSample layer with a InterpolationMode::kLINEAR, unaligned corners, and SampleMode::kFILL for 4d-shape input tensors.

Returns: The new GridSample layer, or nullptr if it could not be created.

◆ addIdentity()

IIdentityLayer * nvinfer1::INetworkDefinition::addIdentity ( ITensor & input )

inlinenoexcept

Add an identity layer.

Parameters

input The input tensor to the layer.

See also: IIdentityLayer

Returns: The new identity layer, or nullptr if it could not be created.

◆ addIfConditional()

IIfConditional * nvinfer1::INetworkDefinition::addIfConditional ( )

inlinenoexcept

Add an if-then-else to the network.

An IIfConditional provides a way to conditionally execute parts of the network.

Returns: Pointer to the IIfConditional that can be used to add conditional-boundary layers for the if-then-else.

See also: IIfConditional

◆ addInput()

ITensor * nvinfer1::INetworkDefinition::addInput	(	char const *	name,
		DataType	type,
		Dims const &	dimensions
	)

inlinenoexcept

Add an input tensor to the network.

Each input and output tensor must have a unique name.

For networks with wildcard dimensions, the volume is based on the maxima specified by an IOptimizationProfile.Dimensions are normally non-negative integers. The exception is that in networks with all explicit dimensions, -1 can be used as a wildcard for a dimension to be specified at runtime. Input tensors with such a wildcard must have a corresponding entry in the IOptimizationProfiles indicating the permitted extrema, and the input dimensions must be set by IExecutionContext::setInputShape. Different IExecutionContext instances can have different dimensions. Wildcard dimensions are only supported for EngineCapability::kSTANDARD. They are not supported in safety contexts. DLA does not support Wildcard dimensions.

Tensor dimensions are specified independent of format. For example, if a tensor is formatted in "NHWC" or a vectorized format, the dimensions are still specified in the order{N, C, H, W}. For 2D images with a channel dimension, the last three dimensions are always {C,H,W}. For 3D images with a channel dimension, the last four dimensions are always {C,D,H,W}.

Parameters

name	The name of the tensor.
type	The type of the data held in the tensor.
dimensions	The dimensions of the tensor.

Warning: It is an error to specify a wildcard value on a dimension that is determined by trained parameters.; If run on DLA with explicit dimensions, only leading dimension can be a wildcard. And provided profile must have same minimum, optimum, and maximum dimensions.; The string name must be null-terminated, and be at most 4096 bytes including the terminator.

See also: ITensor

Returns: The new tensor or nullptr if there is an error.

◆ addLoop()

ILoop * nvinfer1::INetworkDefinition::addLoop ( )

inlinenoexcept

Add a loop to the network.

An ILoop provides a way to specify a recurrent subgraph.

Returns: Pointer to ILoop that can be used to add loop-boundary layers for the loop.

See also: ILoop

◆ addLRN()

ILRNLayer * nvinfer1::INetworkDefinition::addLRN	(	ITensor &	input,
		int64_t	window,
		float	alpha,
		float	beta,
		float	k
	)

inlinenoexcept

Add a LRN layer to the network.

Parameters

input	The input tensor to the layer.
window	The size of the window.
alpha	The alpha value for the LRN computation.
beta	The beta value for the LRN computation.
k	The k value for the LRN computation.

See also: ILRNLayer

Warning: Int32 tensors are not valid input tensors.

Returns: The new LRN layer, or nullptr if it could not be created.

◆ addMatrixMultiply()

IMatrixMultiplyLayer * nvinfer1::INetworkDefinition::addMatrixMultiply	(	ITensor &	input0,
		MatrixOperation	op0,
		ITensor &	input1,
		MatrixOperation	op1
	)

inlinenoexcept

Add a MatrixMultiply layer to the network.

Parameters

input0	The first input tensor (commonly A).
op0	The operation to apply to input0.
input1	The second input tensor (commonly B).
op1	The operation to apply to input1.

The inputs are shape tensors if the output is a shape tensor.

See also: IMatrixMultiplyLayer

Warning: Int32 tensors are not valid input tensors.

Returns: The new matrix multiply layer, or nullptr if it could not be created.

◆ addNMS()

INMSLayer * nvinfer1::INetworkDefinition::addNMS	(	ITensor &	boxes,
		ITensor &	scores,
		ITensor &	maxOutputBoxesPerClass
	)

inlinenoexcept

Add a non-maximum suppression layer to the network.

Parameters

boxes	The input boxes tensor to the layer.
scores	The input scores tensor to the layer.
maxOutputBoxesPerClass	The input maxOutputBoxesPerClass tensor to the layer.

See also: INMSLayer

Returns: The new NMS layer, or nullptr if it could not be created.

◆ addNonZero()

INonZeroLayer * nvinfer1::INetworkDefinition::addNonZero ( ITensor & input )

inlinenoexcept

Add a nonzero layer to the network.

Parameters

input The input tensor to the layer.

See also: INonZeroLayer

Returns: The new nonzero layer, or nullptr if it could be created.

◆ addNormalization()

INormalizationLayer * nvinfer1::INetworkDefinition::addNormalization	(	ITensor &	input,
		ITensor &	scale,
		ITensor &	bias,
		uint32_t	axesMask
	)

inlinenoexcept

Add a normalization layer to the network.

Parameters

input	The input tensor to the layer.
scale	The scale tensor used to scale the normalized output.
bias	The bias tensor used to scale the normalized output.
axesMask	The axes on which to perform mean calculations. The bit in position i of bitmask axesMask corresponds to explicit dimension i of the result. E.g., the least significant bit corresponds to the first explicit dimension and the next to least significant bit corresponds to the second explicit dimension.

The normalization layer works by performing normalization of the tensor input on the specified axesMask. The result is then scaled by multiplying with scale and adding bias.

The shape of scale and bias are expected the be the same, and must have the same rank and be unidirectionally broadcastable to the shape of input.

See also: INormalizationLayer

Returns: The new normalization layer, or nullptr if it could not be created.

◆ addOneHot()

IOneHotLayer * nvinfer1::INetworkDefinition::addOneHot	(	ITensor &	indices,
		ITensor &	values,
		ITensor &	depth,
		int32_t	axis
	)

inlinenoexcept

Add a OneHot layer to the network.

Parameters

indices	- tensor containing indices where on_value should be set.
values	- a 2-element tensor, consisting of [off_value, on_value].
depth	- a shape tensor containing the width of the added one-hot dimension.
axis	- the axis to add the one-hot encoding to.

See also: IOneHotLayer

Returns: The new OneHot layer, or nullptr if it could not be created.

◆ addPaddingNd()

IPaddingLayer * nvinfer1::INetworkDefinition::addPaddingNd	(	ITensor &	input,
		Dims const &	prePadding,
		Dims const &	postPadding
	)

inlinenoexcept

Add a padding layer to the network. Only 2D padding is currently supported.

Parameters

input	The input tensor to the layer.
prePadding	The padding to apply to the start of the tensor.
postPadding	The padding to apply to the end of the tensor.

See also: IPaddingLayer

Returns: The new padding layer, or nullptr if it could not be created.

◆ addParametricReLU()

IParametricReLULayer * nvinfer1::INetworkDefinition::addParametricReLU	(	ITensor &	input,
		ITensor &	slope
	)

inlinenoexcept

Add a parametric ReLU layer to the network.

Parameters

input	The input tensor to the layer.
slope	The slope tensor to the layer. This tensor should be unidirectionally broadcastable to the input tensor.

See also: IParametricReLULayer

Warning: Tensors of type Int32, Int64, Bool, or UInt8 are not allowed as inputs.

Returns: The new parametric ReLU layer, or nullptr if it could not be created.

◆ addPluginV2()

TRT_DEPRECATED IPluginV2Layer * nvinfer1::INetworkDefinition::addPluginV2	(	ITensor const	inputs,
		int32_t	nbInputs,
		IPluginV2 &	plugin
	)

inlinenoexcept

Add a plugin layer to the network using the IPluginV2 interface.

Parameters

inputs	The input tensors to the layer.
nbInputs	The number of input tensors.
plugin	The layer plugin.

See also: IPluginV2Layer

Warning: Dimension wildcard are only supported with IPluginV2DynamicExt or IPluginV2IOExt plugins.; Int32 tensors are not valid input tensors.

Returns: The new plugin layer, or nullptr if it could not be created.

Deprecated:: Deprecated in TensorRT 10.8. Superseded by addPluginV3.

◆ addPluginV3()

IPluginV3Layer * nvinfer1::INetworkDefinition::addPluginV3	(	ITensor const	inputs,
		int32_t	nbInputs,
		ITensor const	shapeInputs,
		int32_t	nbShapeInputs,
		IPluginV3 &	plugin
	)

inlinenoexcept

Add a plugin layer implementing the IPluginV3 interface to the network.

Parameters

inputs	The input tensors to the layer.
nbInputs	The number of input tensors.
shapeInputs	Shape tensor inputs to the layer.
nbShapeInputs	The number of shape tensor inputs.
plugin	The layer plugin.

See also: IPluginV3Layer

Returns: The new plugin layer, or nullptr if it could not be created.

◆ addPoolingNd()

IPoolingLayer * nvinfer1::INetworkDefinition::addPoolingNd	(	ITensor &	input,
		PoolingType	type,
		Dims const &	windowSize
	)

inlinenoexcept

Add a multi-dimension pooling layer to the network.

Parameters

input	The input tensor to the layer.
type	The type of pooling to apply.
windowSize	The size of the pooling window.

See also: IPoolingLayer PoolingType

Warning: Int32 tensors are not valid input tensors.; Only 2D or 3D pooling is supported.

Returns: The new pooling layer, or nullptr if it could not be created.

◆ addQuantize() [1/2]

TRT_DEPRECATED IQuantizeLayer * nvinfer1::INetworkDefinition::addQuantize	(	ITensor &	input,
		ITensor &	scale
	)

inlinenoexcept

Add a quantization layer to the network.

Parameters

input	The input tensor to be quantized.
scale	A tensor with the scale value.

See also: IQuantizeLayer

input tensor data type must be DataType::kFLOAT or DataType::kHALF. scale tensor data type must be DataType::kFLOAT. The subgraph which terminates with the scale tensor must be a build-time constant.

Returns: The new quantization layer, or nullptr if it could not be created.

Deprecated:: Deprecated in TensorRT 9.0. Superseded by three-argument addQuantize.

◆ addQuantize() [2/2]

IQuantizeLayer * nvinfer1::INetworkDefinition::addQuantize	(	ITensor &	input,
		ITensor &	scale,
		DataType	outputType
	)

inlinenoexcept

Add a quantization layer to the network.

Parameters

input	The input tensor to be quantized.
scale	A tensor with the scale value.
outputType	Output tensor data type.

See also: IQuantizeLayer

input tensor data type must be DataType::kFLOAT, DataType::kHALF or DataType::kBF16. scale tensor data type defaults to DataType::kFLOAT. For strongly typed networks, it must have the same data type as the input. The subgraph which terminates with the scale tensor must be a build-time constant. outputType output tensor data type, must be DataType::kINT8 (default), DataType::kFP8 or DataType::kINT4. Future calls to set output type using setToType or setOutputType must be consistent.

Returns: The new quantization layer, or nullptr if it could not be created.

◆ addRaggedSoftMax()

IRaggedSoftMaxLayer * nvinfer1::INetworkDefinition::addRaggedSoftMax	(	ITensor &	input,
		ITensor &	bounds
	)

inlinenoexcept

Add a RaggedSoftMax layer to the network.

Parameters

input	The ZxS input tensor.
bounds	The Zx1 bounds tensor.

See also: IRaggedSoftMaxLayer

Warning: The bounds tensor cannot have the last dimension be the wildcard character.; Int32 tensors are not valid input tensors.; The input and bounds tensors should be 3D tensors.

Returns: The new RaggedSoftMax layer, or nullptr if it could not be created.

◆ addReduce()

IReduceLayer * nvinfer1::INetworkDefinition::addReduce	(	ITensor &	input,
		ReduceOperation	operation,
		uint32_t	reduceAxes,
		bool	keepDimensions
	)

inlinenoexcept

Add a reduce layer to the network.

Parameters

input	The input tensor to the layer.
operation	The reduction operation to perform.
reduceAxes	The reduction dimensions. The bit in position i of bitmask reduceAxes corresponds to explicit dimension i if result. E.g., the least significant bit corresponds to the first explicit dimension and the next to least significant bit corresponds to the second explicit dimension.
keepDimensions	The boolean that specifies whether or not to keep the reduced dimensions in the output of the layer.

The reduce layer works by performing an operation specified by operation to reduce the tensor input across the axes specified by reduceAxes.

See also: IReduceLayer

Warning: If output is an Int32 or Int64 shape tensor, ReduceOperation::kAVG is unsupported.

Returns: The new reduce layer, or nullptr if it could not be created.

◆ addResize()

IResizeLayer * nvinfer1::INetworkDefinition::addResize ( ITensor & input )

inlinenoexcept

Add a resize layer to the network.

Parameters

input The input tensor to the layer.

See also: IResizeLayer

Warning: Int32 tensors are not valid input tensors.

Returns: The new resize layer, or nullptr if it could not be created.

◆ addReverseSequence()

IReverseSequenceLayer * nvinfer1::INetworkDefinition::addReverseSequence	(	ITensor &	input,
		ITensor &	sequenceLens
	)

inlinenoexcept

Add a ReverseSequence layer to the network.

Parameters

input	The input tensor to the layer. Must have rank >= 2.
sequenceLens	1D tensor specifying lengths of sequences to reverse in a batch. The length of the sequenceLens tensor must be equal to the size of the dimension in input tensor specified by batchAxis.

See also: IReverseSequenceLayer

Returns: The new ReverseSequence layer, or nullptr if it could not be created.

◆ addScale()

IScaleLayer * nvinfer1::INetworkDefinition::addScale	(	ITensor &	input,
		ScaleMode	mode,
		Weights	shift,
		Weights	scale,
		Weights	power
	)

inlinenoexcept

Add a Scale layer to the network.

Parameters

input	The input tensor to the layer. This tensor must have at least 4 dimensions.
mode	The scaling mode.
shift	The shift value.
scale	The scale value.
power	The power value.

If the weights are available, then the size of weights are dependent on the ScaleMode. For ScaleMode::kUNIFORM, the number of weights equals 1. For ScaleMode::kCHANNEL, the number of weights equals the channel dimension. For ScaleMode::kELEMENTWISE, the number of weights equals the product of the last three dimensions of the input.

See also: addScaleNd; IScaleLayer

Warning: Int32 tensors are not valid input tensors.

Returns: The new Scale layer, or nullptr if it could not be created.

◆ addScaleNd()

IScaleLayer * nvinfer1::INetworkDefinition::addScaleNd	(	ITensor &	input,
		ScaleMode	mode,
		Weights	shift,
		Weights	scale,
		Weights	power,
		int32_t	channelAxis
	)

inlinenoexcept

Add a multi-dimension scale layer to the network.

Parameters

input	The input tensor to the layer.
mode	The scaling mode.
shift	The shift value.
scale	The scale value.
power	The power value.
channelAxis	The channel axis.

If the weights are available, then the size of weights are dependent on the ScaleMode. For ScaleMode::kUNIFORM, the number of weights equals 1. For ScaleMode::kCHANNEL, the number of weights equals the channel dimension. For ScaleMode::kELEMENTWISE, the number of weights equals the product of all input dimensions at channelAxis and beyond.

For example, if the inputs dimensions are [A,B,C,D,E,F], and channelAxis=2: For ScaleMode::kUNIFORM, the number of weights is equal to 1. For ScaleMode::kCHANNEL, the number of weights is C. For ScaleMode::kELEMENTWISE, the number of weights is C*D*E*F.

channelAxis can also be set explicitly using setChannelAxis().

See also: IScaleLayer; setChannelAxis()

Warning: Int32 tensors are not valid input tensors.; Only 2D or 3D scale is supported.

Returns: The new Scale layer, or nullptr if it could not be created.

◆ addScatter()

IScatterLayer * nvinfer1::INetworkDefinition::addScatter	(	ITensor &	data,
		ITensor &	indices,
		ITensor &	updates,
		ScatterMode	mode
	)

inlinenoexcept

Add a Scatter layer to the network with specified mode and axis=0.

Parameters

data	The input tensor to be updated with additional values.
indices	indices of the elements to be updated.
updates	values to be used for updates.
mode	scatter mode.

See also: IScatterLayer

indices tensor data type must be DataType::kINT32. updates tensor data type must be the same as data

Returns: The new Scatter layer, or nullptr if it could not be created.

◆ addSelect()

ISelectLayer * nvinfer1::INetworkDefinition::addSelect	(	ITensor &	condition,
		ITensor &	thenInput,
		ITensor &	elseInput
	)

inlinenoexcept

Add a select layer to the network.

Parameters

condition	The condition tensor to the layer. Must have type DataType::kBOOL.
thenInput	The "then" input tensor to the layer.
elseInput	The "else" input tensor to the layer.

All three input tensors must have the same rank, and along each axis must have the same length or a length of one. If the length is one, the tensor is broadcast along that axis. The output tensor has the dimensions of the inputs AFTER the broadcast rule is applied. For example, given:

dimensions of condition: [1,1,5,9] dimensions of thenInput: [1,1,5,9] dimensions of elseInput: [1,3,1,9]

the output dimensions are [1,3,5,9], and the output contents are defined by:

 output[0,i,j,k] = condition[0,0,j,k] ? thenInput[0,0,j,k] : elseInput[0,i,0,k]

The output dimensions are not necessarily the max of the input dimensions if any input is an empty tensor. For example, if in the preceding example, 5 is changed to 0:

dimensions of condition: [1,1,0,9] dimensions of thenInput: [1,1,0,9] dimensions of elseInput: [1,3,1,9]

then the output dimensions are [1,3,0,9].

The inputs are shape tensors if the output is a shape tensor.

See also: ISelectLayer

Returns: The new select layer, or nullptr if it could not be created.

◆ addShape()

IShapeLayer * nvinfer1::INetworkDefinition::addShape ( ITensor & input )

inlinenoexcept

Add a shape layer to the network.

Parameters

input The input tensor to the layer.

See also: IShapeLayer

Warning: addShape is only supported when hasImplicitBatchDimensions is false.

Returns: The new shape layer, or nullptr if it could not be created.

◆ addShuffle()

IShuffleLayer * nvinfer1::INetworkDefinition::addShuffle ( ITensor & input )

inlinenoexcept

Add a shuffle layer to the network.

Parameters

input The input tensor to the layer.

See also: IShuffleLayer

Returns: The new shuffle layer, or nullptr if it could not be created.

◆ addSlice()

ISliceLayer * nvinfer1::INetworkDefinition::addSlice	(	ITensor &	input,
		Dims const &	start,
		Dims const &	size,
		Dims const &	stride
	)

inlinenoexcept

Add a slice layer to the network.

Parameters

input	The input tensor to the layer.
start	The start offset
size	The output dimension
stride	The slicing stride

Positive, negative, zero stride values, and combinations of them in different dimensions are allowed.

See also: ISliceLayer

Returns: The new slice layer, or nullptr if it could not be created.

◆ addSoftMax()

ISoftMaxLayer * nvinfer1::INetworkDefinition::addSoftMax ( ITensor & input )

inlinenoexcept

Add a SoftMax layer to the network.

See also: ISoftMaxLayer

Warning: Int32 tensors are not valid input tensors.

Returns: The new SoftMax layer, or nullptr if it could not be created.

◆ addSqueeze()

ISqueezeLayer * nvinfer1::INetworkDefinition::addSqueeze	(	ITensor &	input,
		ITensor &	axes
	)

inlinenoexcept

Add a squeeze layer to the network.

Parameters

input	The input tensor to the layer.
axes	The axes to remove unit dimensions on.

See also: ISqueezeLayer

Axes must be resolvable to a constant Int32 or Int64 1D shape tensor. Values in axes must be unique and in the range of [-r, r-1], where r is the rank of the input tensor. For each axis value, the corresponding dimension in the input tensor must be one.

Returns: The new Squeeze layer, or nullptr if it could not be created.

◆ addTopK()

ITopKLayer * nvinfer1::INetworkDefinition::addTopK	(	ITensor &	input,
		TopKOperation	op,
		int32_t	k,
		uint32_t	reduceAxes
	)

inlinenoexcept

Add a TopK layer to the network.

The TopK layer has two outputs of the same dimensions. The first contains data values, the second contains index positions for the values. Output values are sorted, largest first for operation kMAX and smallest first for operation kMIN.

Currently only values of K up to 3840 are supported.

Parameters

input	The input tensor to the layer.
op	Operation to perform.
k	The number of elements to keep. For dynamic k, use the setInput() method to pass in k as a tensor instead, which will override the static k value passed here in calculations.
reduceAxes	The reduction dimensions. The bit in position i of bitmask reduceAxes corresponds to explicit dimension i of the result. E.g., the least significant bit corresponds to the first explicit dimension and the next to least significant bit corresponds to the second explicit dimension.

Currently reduceAxes must specify exactly one dimension, and it must be one of the last four dimensions.

See also: ITopKLayer

Returns: The new TopK layer, or nullptr if it could not be created.

◆ addUnary()

IUnaryLayer * nvinfer1::INetworkDefinition::addUnary	(	ITensor &	input,
		UnaryOperation	operation
	)

inlinenoexcept

Add a unary layer to the network.

Parameters

input	The input tensor to the layer.
operation	The operation to apply.

See also: IUnaryLayer

Generally the input must have a floating-point type (or kINT8 as a quantized float), except for the following operations:

kSIGN accepts a floating-point or Int32 tensor.
kNOT requires a Bool tensor.

The input is a shape tensor if the output is a shape tensor.

Returns: The new unary layer, or nullptr if it could not be created

◆ addUnsqueeze()

IUnsqueezeLayer * nvinfer1::INetworkDefinition::addUnsqueeze	(	ITensor &	input,
		ITensor &	axes
	)

inlinenoexcept

Add an unsqueeze layer to the network.

Parameters

input	The input tensor to the layer.
axes	The axes to add unit dimensions.

See also: IUnsqueezeLauyer

Axes must be resolvable to a constant Int32 or Int64 shape tensor. Values in axes must be unique and in the range of [-r_final, r_final-1], where r_final is the sum of rank(input) and len(axes).

r_final must be less than Dims::MAX_DIMS.

Returns: The new Unsqueeze layer, or nullptr if it could not be created

◆ areWeightsMarkedRefittable()

bool nvinfer1::INetworkDefinition::areWeightsMarkedRefittable ( char const * name ) const

inlinenoexcept

Whether the weight has been marked as refittable.

Parameters

name	The name of the weights to check.

Returns: True if the weights are marked as refittable, false if the weights do not exist or are marked as non-refittable.

◆ getBuilder()

virtual IBuilder & nvinfer1::INetworkDefinition::getBuilder ( ) const

inlinevirtualnoexcept

Return the builder from which this INetworkDefinition was created.

See also: IBuilder::createNetworkV2

Returns: the builder

◆ getErrorRecorder()

IErrorRecorder * nvinfer1::INetworkDefinition::getErrorRecorder ( ) const

inlinenoexcept

get the ErrorRecorder assigned to this interface.

Retrieves the assigned error recorder object for the given class. A nullptr will be returned if setErrorRecorder has not been called.

Returns: A pointer to the IErrorRecorder object that has been registered.

See also: setErrorRecorder()

◆ getFlag()

bool nvinfer1::INetworkDefinition::getFlag ( NetworkDefinitionCreationFlag networkDefinitionCreationFlag ) const

inlinenoexcept

Returns true if the network definition creation flag is set.

See also: getFlags()

Returns: True if flag is set, false if unset.

◆ getFlags()

NetworkDefinitionCreationFlags nvinfer1::INetworkDefinition::getFlags ( ) const

inlinenoexcept

Get the network definition creation flags for this network definition object. Defaults to 0.

Returns: The network definition creation options as a bitmask.

◆ getInput()

ITensor * nvinfer1::INetworkDefinition::getInput ( int32_t index ) const

inlinenoexcept

Get the input tensor specified by the given index.

Parameters

index The index of the input tensor.

Returns: The input tensor, or nullptr if the index is out of range.

Note: adding inputs invalidates indexing here

See also: getNbInputs()

◆ getLayer()

ILayer * nvinfer1::INetworkDefinition::getLayer ( int32_t index ) const

inlinenoexcept

Get the layer specified by the given index.

Parameters

index The index of the layer.

Returns: The layer, or nullptr if the index is out of range.

See also: getNbLayers()

◆ getName()

char const * nvinfer1::INetworkDefinition::getName ( ) const

inlinenoexcept

Returns the name associated with the network.

The memory pointed to by getName() is owned by the INetworkDefinition object.

See also: INetworkDefinition::setName()

Returns: A null-terminated C-style string representing the name of the network.

◆ getNbInputs()

int32_t nvinfer1::INetworkDefinition::getNbInputs ( ) const

inlinenoexcept

Get the number of inputs in the network.

Returns: The number of inputs in the network.

See also: getInput()

◆ getNbLayers()

int32_t nvinfer1::INetworkDefinition::getNbLayers ( ) const

inlinenoexcept

Get the number of layers in the network.

Returns: The number of layers in the network.

See also: getLayer()

◆ getNbOutputs()

int32_t nvinfer1::INetworkDefinition::getNbOutputs ( ) const

inlinenoexcept

Get the number of outputs in the network.

The outputs include those marked by markOutput or markOutputForShapes.

Returns: The number of outputs in the network.

See also: getOutput()

◆ getOutput()

ITensor * nvinfer1::INetworkDefinition::getOutput ( int32_t index ) const

inlinenoexcept

Get the output tensor specified by the given index.

Parameters

index The index of the output tensor.

Returns: The output tensor, or nullptr if the index is out of range.

Note: adding inputs invalidates indexing here

See also: getNbOutputs()

◆ hasImplicitBatchDimension()

TRT_DEPRECATED bool nvinfer1::INetworkDefinition::hasImplicitBatchDimension ( ) const

inlinenoexcept

Query whether the network was created with an implicit batch dimension.

Returns: Always false since TensorRT 10.0 does not support an implicit batch dimension.

See also: createNetworkV2

Deprecated:: Deprecated in TensorRT 10.0. Implicit batch is not supported since TensorRT 10.0.

◆ isDebugTensor()

bool nvinfer1::INetworkDefinition::isDebugTensor ( nvinfer1::ITensor const & tensor ) const

inlinenoexcept

Check if a tensor is marked as debug tensor.

Returns: true if tensor is marked as debug tensor, false otherwise.

◆ markDebug()

bool nvinfer1::INetworkDefinition::markDebug ( ITensor & tensor )

inlinenoexcept

Mark a tensor as a debug tensor.

A debug tensor can be optionally emitted at runtime. Note that tensor names are required to specify debug tensors at runtime.

Parameters

tensor Tensor to be marked as debug

Returns: True if tensor successfully marked (or was already marked), false otherwise.

See also: unmarkDebug(), IExecutionContext::setDebugListener(), ITensor::setName()

◆ markOutput()

void nvinfer1::INetworkDefinition::markOutput ( ITensor & tensor )

inlinenoexcept

Mark a tensor as a network output.

Parameters

tensor The tensor to mark as an output tensor.

Warning: It is an error to mark a network input as an output.; It is an error to mark a tensor inside an ILoop or an IIfConditional as an output.

◆ markOutputForShapes()

bool nvinfer1::INetworkDefinition::markOutputForShapes ( ITensor & tensor )

inlinenoexcept

Enable tensor's value to be computed by IExecutionContext::getShapeBinding.

Returns: True if successful, false if tensor is already marked as an output.

The tensor must be of type DataType::kINT32 and have no more than one dimension.

Warning: The tensor must have dimensions that can be determined to be constants at build time.; It is an error to mark a network input as a shape output.

◆ markWeightsRefittable()

bool nvinfer1::INetworkDefinition::markWeightsRefittable ( char const * name )

inlinenoexcept

Mark weights as refittable when the builder flag kREFIT_INDIVIDUAL is set.

Parameters

name	The name of the weights.

Returns: True if the weights were successfully marked as refittable, false if the weights do not exist or cannot be refitted.

◆ removeTensor()

void nvinfer1::INetworkDefinition::removeTensor ( ITensor & tensor )

inlinenoexcept

remove a tensor from the network definition.

Parameters

tensor the tensor to remove

It is illegal to remove a tensor that is the input or output of a layer. if this method is called with such a tensor, a warning will be emitted on the log and the call will be ignored. Its intended use is to remove detached tensors after e.g. concatenating two networks with Layer::setInput().

◆ setErrorRecorder()

void nvinfer1::INetworkDefinition::setErrorRecorder ( IErrorRecorder * recorder )

inlinenoexcept

Set the ErrorRecorder for this interface.

Assigns the ErrorRecorder to this interface. The ErrorRecorder will track all errors during execution. This function will call incRefCount of the registered ErrorRecorder at least once. Setting recorder to nullptr unregisters the recorder with the interface, resulting in a call to decRefCount if a recorder has been registered.

If an error recorder is not set, messages will be sent to the global log stream.

Parameters

recorder The error recorder to register with this interface.

See also: getErrorRecorder()

◆ setName()

void nvinfer1::INetworkDefinition::setName ( char const * name )

inlinenoexcept

Sets the name of the network.

Parameters

name	The name to assign to this network.

Set the name of the network so that it can be associated with a built engine. The name must be a null-terminated C-style string. TensorRT makes no use of this string except storing it as part of the engine so that it may be retrieved at runtime. A name unique to the builder will be generated by default.

This method copies the name string.

Warning: The string name must be null-terminated, and be at most 4096 bytes including the terminator.

See also: INetworkDefinition::getName(), ISafeCudaEngine::getName()

Returns: none

◆ setWeightsName()

bool nvinfer1::INetworkDefinition::setWeightsName	(	Weights	weights,
		char const *	name
	)

inlinenoexcept

Associate a name with all current uses of the given weights.

The name must be set after the Weights are used in the network. Lookup is associative. The name applies to all Weights with matching type, value pointer, and count. If Weights with a matching value pointer, but different type or count exists in the network, an error message is issued, the name is rejected, and return false. If the name has already been used for other weights, return false. A nullptr causes the weights to become unnamed, i.e. clears any previous name.

Parameters

weights	The weights to be named.
name	The name to associate with the weights.

Returns: true on success.

Warning: The string name must be null-terminated, and be at most 4096 bytes including the terminator.

◆ unmarkDebug()

bool nvinfer1::INetworkDefinition::unmarkDebug ( ITensor & tensor )

inlinenoexcept

Unmark a tensor as a debug tensor.

Remove the marking of a tensor as a debug tensor.

Parameters

tensor Tensor to be unmarked as debug.

Returns: True if tensor successfully unmarked (or was already unmarked), false otherwise.

See also: markDebug(), IExecutionContext::setDebugListener()

◆ unmarkOutput()

void nvinfer1::INetworkDefinition::unmarkOutput ( ITensor & tensor )

inlinenoexcept

unmark a tensor as a network output.

Parameters

tensor The tensor to unmark as an output tensor.

see markOutput()

◆ unmarkOutputForShapes()

bool nvinfer1::INetworkDefinition::unmarkOutputForShapes ( ITensor & tensor )

inlinenoexcept

Undo markOutputForShapes.

Warning: inputs to addShape cannot contain wildcard dimension values.

Returns: True if successful, false if tensor is not marked as an output.

◆ unmarkWeightsRefittable()

bool nvinfer1::INetworkDefinition::unmarkWeightsRefittable ( char const * name )

inlinenoexcept

Unmark weights as refittable when the builder flag kREFIT_INDIVIDUAL is set.

Parameters

name	The name of the weights.

Returns: True if the weights were successfully marked as unrefittable, false if the weights do not exist.

Member Data Documentation

◆ mImpl

apiv::VNetworkDefinition* nvinfer1::INetworkDefinition::mImpl

protected

The documentation for this class was generated from the following file:

NvInfer.h

Public Member Functions

Protected Attributes

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ ~INetworkDefinition()

Member Function Documentation

◆ addActivation()

◆ addAssertion()

◆ addCast()

◆ addConcatenation()

◆ addConstant()

◆ addConvolutionNd()

◆ addCumulative()

◆ addDeconvolutionNd()

◆ addDequantize() [1/2]

◆ addDequantize() [2/2]

◆ addDynamicQuantize()

◆ addEinsum()

◆ addElementWise()

◆ addFill() [1/2]

◆ addFill() [2/2]

◆ addGather()

◆ addGatherV2()

◆ addGridSample()

◆ addIdentity()

◆ addIfConditional()

◆ addInput()

◆ addLoop()

◆ addLRN()

◆ addMatrixMultiply()

◆ addNMS()

◆ addNonZero()

◆ addNormalization()

◆ addOneHot()

◆ addPaddingNd()

◆ addParametricReLU()

◆ addPluginV2()

◆ addPluginV3()

◆ addPoolingNd()

◆ addQuantize() [1/2]

◆ addQuantize() [2/2]

◆ addRaggedSoftMax()

◆ addReduce()

◆ addResize()

◆ addReverseSequence()

◆ addScale()

◆ addScaleNd()

◆ addScatter()

◆ addSelect()

◆ addShape()

◆ addShuffle()

◆ addSlice()

◆ addSoftMax()

◆ addSqueeze()

◆ addTopK()

◆ addUnary()

◆ addUnsqueeze()

◆ areWeightsMarkedRefittable()

◆ getBuilder()

◆ getErrorRecorder()

◆ getFlag()

◆ getFlags()

◆ getInput()

◆ getLayer()

◆ getName()

◆ getNbInputs()

◆ getNbLayers()

◆ getNbOutputs()

◆ getOutput()

◆ hasImplicitBatchDimension()

◆ isDebugTensor()

◆ markDebug()

◆ markOutput()

◆ markOutputForShapes()

◆ markWeightsRefittable()

◆ removeTensor()

◆ setErrorRecorder()

◆ setName()

◆ setWeightsName()