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

#include <NvInfer.h>

Inheritance diagram for nvinfer1::INetworkDefinition:

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

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

TRT_DEPRECATED IConvolutionLayer *	addConvolution (ITensor &input, int32_t nbOutputMaps, DimsHW kernelSize, Weights kernelWeights, Weights biasWeights) noexcept
	Add a convolution layer to the network. More...

IFullyConnectedLayer *	addFullyConnected (ITensor &input, int32_t nbOutputs, Weights kernelWeights, Weights biasWeights) noexcept
	Add a fully connected layer to the network. More...

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

TRT_DEPRECATED IPoolingLayer *	addPooling (ITensor &input, PoolingType type, DimsHW windowSize) noexcept
	Add a pooling layer to the network. More...

ILRNLayer *	addLRN (ITensor &input, int32_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...

TRT_DEPRECATED IDeconvolutionLayer *	addDeconvolution (ITensor &input, int32_t nbOutputMaps, DimsHW kernelSize, Weights kernelWeights, Weights biasWeights) noexcept
	Add a deconvolution 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...

TRT_DEPRECATED IPaddingLayer *	addPadding (ITensor &input, DimsHW prePadding, DimsHW postPadding) noexcept
	Add a padding layer to the network. More...

IShuffleLayer *	addShuffle (ITensor &input) noexcept
	Add a shuffle 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...

TRT_DEPRECATED void	destroy () noexcept
	Destroy this INetworkDefinition object. 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)
	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...

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

TRT_DEPRECATED IRNNv2Layer *	addRNNv2 (ITensor &input, int32_t layerCount, int32_t hiddenSize, int32_t maxSeqLen, RNNOperation op) noexcept
	Add an `layerCount` deep RNN layer to the network with `hiddenSize` internal states that can take a batch with fixed or variable sequence lengths. More...

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

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

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

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

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

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

bool	hasImplicitBatchDimension () const noexcept
	Query whether the network was created with an implicit batch dimension. 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, int32_t nbOutputMaps, Dims kernelSize, Weights kernelWeights, Weights biasWeights) noexcept
	Add a multi-dimension convolution layer to the network. More...

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

IDeconvolutionLayer *	addDeconvolutionNd (ITensor &input, int32_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...

TRT_DEPRECATED bool	hasExplicitPrecision () const noexcept
	True if network is an explicit precision network. More...

ILoop *	addLoop () noexcept
	Add a loop 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, const char *message) noexcept
	Add an assertion layer to the network. More...

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

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

bool	setWeightsName (Weights weights, const char *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...

IDequantizeLayer *	addDequantize (ITensor &input, ITensor &scale) 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...

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

IIfConditional *	addIfConditional () noexcept
	Add an If-conditional layer to the network. More...

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

Protected Attributes
apiv::VNetworkDefinition *	mImpl

Additional Inherited Members
Protected Member Functions inherited from nvinfer1::INoCopy
	INoCopy (const INoCopy &other)=delete

INoCopy &	operator= (const INoCopy &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 either have an implicit batch dimensions, specified at runtime, or all dimensions explicit, full dims mode, in the network definition. When a network has been created using createNetwork(), only implicit batch size mode is supported. The function hasImplicitBatchDimension() is used to query the mode of the network.

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.

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 tensors are not valid input tensors.

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

◆ addAssertion()

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

◆ 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	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 tensors in the network have an implicit batch dimension, the constant is broadcast over that dimension.

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

◆ addConvolution()

TRT_DEPRECATED IConvolutionLayer * nvinfer1::INetworkDefinition::addConvolution	(	ITensor &	input,
		int32_t	nbOutputMaps,
		DimsHW	kernelSize,
		Weights	kernelWeights,
		Weights	biasWeights
	)

inlinenoexcept

Add a 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 HW-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.

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

Deprecated:: Superseded by addConvolutionNd and will be removed in TensorRT 9.0.

◆ addConvolutionNd()

IConvolutionLayer * nvinfer1::INetworkDefinition::addConvolutionNd	(	ITensor &	input,
		int32_t	nbOutputMaps,
		Dims	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.

◆ addDeconvolution()

TRT_DEPRECATED IDeconvolutionLayer * nvinfer1::INetworkDefinition::addDeconvolution	(	ITensor &	input,
		int32_t	nbOutputMaps,
		DimsHW	kernelSize,
		Weights	kernelWeights,
		Weights	biasWeights
	)

inlinenoexcept

Add a deconvolution layer to the network.

Parameters

input	The input tensor to the layer.
nbOutputMaps	The number of output feature maps.
kernelSize	The HW-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.

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

Deprecated:: Superseded by addDeconvolutionNd and will be removed in TensorRT 9.0.

◆ addDeconvolutionNd()

IDeconvolutionLayer * nvinfer1::INetworkDefinition::addDeconvolutionNd	(	ITensor &	input,
		int32_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()

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::kFLOAT. 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.

◆ addEinsum()

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

See also: IElementWiseLayer

Warning: For shape tensors, ElementWiseOperation::kPOW is not a valid op.

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

◆ addFill()

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

inlinenoexcept

Add a fill layer to the network.

Parameters

dimensions	The output tensor dimensions.
op	The fill operation that the layer applies.

Warning: For FillOperation::kLINSPACE, dimensions.nbDims must be 1.

The network must not have an implicit batch dimension.

See also: IFillLayer

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

◆ addFullyConnected()

IFullyConnectedLayer * nvinfer1::INetworkDefinition::addFullyConnected	(	ITensor &	input,
		int32_t	nbOutputs,
		Weights	kernelWeights,
		Weights	biasWeights
	)

inlinenoexcept

Add a fully connected layer to the network.

Parameters

input	The input tensor to the layer.
nbOutputs	The number of outputs of the layer.
kernelWeights	The kernel weights for the fully connected layer.
biasWeights	The bias weights for the fully connected layer. Weights{} represents no bias.

See also: IFullyConnectedLayer

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.

Returns: The new fully connected 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
	)

inline

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.

◆ 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-conditional layer to the network.

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

See also: IIfConditional

Returns: The new conditional layer, or nullptr if network has an implicit batch dimension or this version of TensorRT does not support conditional execution.

◆ addInput()

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

inlinenoexcept

Add an input tensor to the network.

The name of the input tensor is used to find the index into the buffer array for an engine built from the network. The volume must be less than 2^31 elements.

For networks with an implicit batch dimension, this volume includes the batch dimension with its length set to the maximum batch size. For networks with all explicit dimensions and 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::setBindingDimensions. 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.

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, or nullptr if network has an implicit batch dimension or this version of TensorRT does not support loops.

The network must not have an implicit batch dimension.

◆ addLRN()

ILRNLayer * nvinfer1::INetworkDefinition::addLRN	(	ITensor &	input,
		int32_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.

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.

◆ addPadding()

TRT_DEPRECATED IPaddingLayer * nvinfer1::INetworkDefinition::addPadding	(	ITensor &	input,
		DimsHW	prePadding,
		DimsHW	postPadding
	)

inlinenoexcept

Add a padding layer to the network.

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.

Deprecated:: Superseded by addPaddingNd and will be removed in TensorRT 9.0.

◆ addPaddingNd()

TRT_DEPRECATED IPaddingLayer * nvinfer1::INetworkDefinition::addPaddingNd	(	ITensor &	input,
		Dims	prePadding,
		Dims	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.

Deprecated:: Superseded by addSlice and will be removed in TensorRT 10.0.

◆ 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: Int32 tensors are not valid input tensors.

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

◆ addPluginV2()

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.

◆ addPooling()

TRT_DEPRECATED IPoolingLayer * nvinfer1::INetworkDefinition::addPooling	(	ITensor &	input,
		PoolingType	type,
		DimsHW	windowSize
	)

inlinenoexcept

Add a 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.

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

Deprecated:: Superseded by addPoolingNd and will be removed in TensorRT 9.0.

◆ addPoolingNd()

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

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. 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.

◆ 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.

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 a 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.

◆ addRNNv2()

TRT_DEPRECATED IRNNv2Layer * nvinfer1::INetworkDefinition::addRNNv2	(	ITensor &	input,
		int32_t	layerCount,
		int32_t	hiddenSize,
		int32_t	maxSeqLen,
		RNNOperation	op
	)

inlinenoexcept

Add an layerCount deep RNN layer to the network with hiddenSize internal states that can take a batch with fixed or variable sequence lengths.

Parameters

input	The input tensor to the layer (see below).
layerCount	The number of layers in the RNN.
hiddenSize	Size of the internal hidden state for each layer.
maxSeqLen	Maximum sequence length for the input.
op	The type of RNN to execute.

By default, the layer is configured with RNNDirection::kUNIDIRECTION and RNNInputMode::kLINEAR. To change these settings, use IRNNv2Layer::setDirection() and IRNNv2Layer::setInputMode().

Weights and biases for the added layer should be set using IRNNv2Layer::setWeightsForGate() and IRNNv2Layer::setBiasForGate() prior to building an engine using this network.

The input tensors must be of the type DataType::kFLOAT or DataType::kHALF. The layout of the weights is row major and must be the same datatype as the input tensor. weights contain 8 matrices and bias contains 8 vectors.

See IRNNv2Layer::setWeightsForGate() and IRNNv2Layer::setBiasForGate() for details on the required input format for weights and bias.

The input ITensor should contain zero or more index dimensions {N1, ..., Np}, followed by two dimensions, defined as follows:

S_max is the maximum allowed sequence length (number of RNN iterations)
E specifies the embedding length (unless ::kSKIP is set, in which case it should match getHiddenSize()).

By default, all sequences in the input are assumed to be size maxSeqLen. To provide explicit sequence lengths for each input sequence in the batch, use IRNNv2Layer::setSequenceLengths().

The RNN layer outputs up to three tensors.

The first output tensor is the output of the final RNN layer across all timesteps, with dimensions {N1, ..., Np, S_max, H}:

N1..Np are the index dimensions specified by the input tensor
S_max is the maximum allowed sequence length (number of RNN iterations)
H is an output hidden state (equal to getHiddenSize() or 2x getHiddenSize())

The second tensor is the final hidden state of the RNN across all layers, and if the RNN is an LSTM (i.e. getOperation() is ::kLSTM), then the third tensor is the final cell state of the RNN across all layers. Both the second and third output tensors have dimensions {N1, ..., Np, L, H}:

N1..Np are the index dimensions specified by the input tensor
L is the number of layers in the RNN, equal to getLayerCount() if getDirection is ::kUNIDIRECTION, and 2x getLayerCount() if getDirection is ::kBIDIRECTION. In the bi-directional case, layer l's final forward hidden state is stored in L = 2*l, and final backward hidden state is stored in L= 2*l + 1.
H is the hidden state for each layer, equal to getHiddenSize().

See also: IRNNv2Layer

Deprecated:: Superseded by INetworkDefinition::addLoop and will be removed in TensorRT 9.0.

Warning: RNN inputs do not support wildcard dimensions or explicit batch size networks.; Int32 tensors are not valid input tensors, only for sequence lengths.

Returns: The new RNN 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 is required to have a minimum of 3 dimensions in implicit batch mode and a minimum of 4 dimensions in explicit batch mode.
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 ::kUNIFORM, the number of weights equals 1. For ::kCHANNEL, the number of weights equals the channel dimension. For ::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 ::kUNIFORM, the number of weights equals 1. For ::kCHANNEL, the number of weights equals the channel dimension. For ::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 ::kUNIFORM, the number of weights is equal to 1. For ::kCHANNEL, the number of weights is C. For ::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

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

See also: IScatterLayer

input tensor data type must be DataType::kFLOAT. indices tensor data type must be DataType::kINT32. updates tensor data type must be DataType::kFLOAT.

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 network must not have an implicit batch dimension.

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.; input to addShape cannot contain wildcard dimension values.

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	start,
		Dims	size,
		Dims	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.

◆ 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 1024 are supported.

Parameters

input	The input tensor to the layer.
op	Operation to perform.
k	Number of elements to keep.
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

Warning: Int32 tensors are not valid input tensors.

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

Warning: Int32 tensors are only valid for kSIGN.; Bool tensors are only valid for kNOT.; Shape tensors are not supported as outputs.

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

◆ destroy()

TRT_DEPRECATED void nvinfer1::INetworkDefinition::destroy ( )

inlinenoexcept

Destroy this INetworkDefinition object.

Deprecated:: Deprecated interface will be removed in TensorRT 10.0.

Warning: Calling destroy on a managed pointer will result in a double-free error.

◆ 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()

◆ 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()

const char * 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()

◆ hasExplicitPrecision()

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

inlinenoexcept

True if network is an explicit precision network.

Deprecated:: Will be removed in TensorRT 10.0.

hasExplicitPrecision() is true if and only if this INetworkDefinition was created with createNetworkV2() with NetworkDefinitionCreationFlag::kEXPLICIT_PRECISION set.

See also: createNetworkV2

Returns: True if network has explicit precision, false otherwise.

◆ hasImplicitBatchDimension()

bool nvinfer1::INetworkDefinition::hasImplicitBatchDimension ( ) const

inlinenoexcept

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

Returns: True if tensors have implicit batch dimension, false otherwise.

This is a network-wide property. Either all tensors in the network have an implicit batch dimension or none of them do.

hasImplicitBatchDimension() is true if and only if this INetworkDefinition was created with createNetwork() or createNetworkV2() without NetworkDefinitionCreationFlag::kEXPLICIT_BATCH flag.

See also: createNetworkV2

◆ 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.

See also: isShapeBinding(), getShapeBinding()

◆ 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 ( const char * 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.

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

Returns: none

◆ setWeightsName()

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

◆ 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.

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

NvInfer.h

Public Member Functions

Protected Attributes

Additional Inherited Members

Detailed Description

Member Function Documentation

◆ addActivation()

◆ addAssertion()

◆ addConcatenation()

◆ addConstant()

◆ addConvolution()

◆ addConvolutionNd()

◆ addDeconvolution()

◆ addDeconvolutionNd()

◆ addDequantize()

◆ addEinsum()

◆ addElementWise()

◆ addFill()

◆ addFullyConnected()

◆ addGather()

◆ addGatherV2()

◆ addIdentity()

◆ addIfConditional()

◆ addInput()

◆ addLoop()

◆ addLRN()

◆ addMatrixMultiply()

◆ addPadding()

◆ addPaddingNd()

◆ addParametricReLU()

◆ addPluginV2()

◆ addPooling()

◆ addPoolingNd()

◆ addQuantize()

◆ addRaggedSoftMax()

◆ addReduce()

◆ addResize()

◆ addRNNv2()

◆ addScale()

◆ addScaleNd()

◆ addScatter()

◆ addSelect()

◆ addShape()

◆ addShuffle()

◆ addSlice()

◆ addSoftMax()

◆ addTopK()

◆ addUnary()

◆ destroy()

◆ getErrorRecorder()

◆ getInput()

◆ getLayer()

◆ getName()

◆ getNbInputs()

◆ getNbLayers()

◆ getNbOutputs()

◆ getOutput()

◆ hasExplicitPrecision()

◆ hasImplicitBatchDimension()

◆ markOutput()

◆ markOutputForShapes()

◆ removeTensor()

◆ setErrorRecorder()

◆ setName()

◆ setWeightsName()

◆ unmarkOutput()

◆ unmarkOutputForShapes()