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

#include <NvInfer.h>

Public Member Functions
virtual ITensor *	addInput (const char *name, DataType type, Dims dimensions)=0
	Add an input tensor to the network. More...

virtual void	markOutput (ITensor &tensor)=0
	Mark a tensor as a network output. More...

virtual IConvolutionLayer *	addConvolution (ITensor &input, int nbOutputMaps, DimsHW kernelSize, Weights kernelWeights, Weights biasWeights)=0
	Add a convolution layer to the network. More...

virtual IFullyConnectedLayer *	addFullyConnected (ITensor &input, int nbOutputs, Weights kernelWeights, Weights biasWeights)=0
	Add a fully connected layer to the network. More...

virtual IActivationLayer *	addActivation (ITensor &input, ActivationType type)=0
	Add an activation layer to the network. More...

virtual IPoolingLayer *	addPooling (ITensor &input, PoolingType type, DimsHW windowSize)=0
	Add a pooling layer to the network. More...

virtual ILRNLayer *	addLRN (ITensor &input, int window, float alpha, float beta, float k)=0
	Add a LRN layer to the network. More...

virtual IScaleLayer *	addScale (ITensor &input, ScaleMode mode, Weights shift, Weights scale, Weights power)=0
	Add a Scale layer to the network. More...

virtual ISoftMaxLayer *	addSoftMax (ITensor &input)=0
	Add a SoftMax layer to the network. More...

virtual IConcatenationLayer *	addConcatenation (ITensor const inputs, int nbInputs)=0
	Add a concatenation layer to the network. More...

virtual IDeconvolutionLayer *	addDeconvolution (ITensor &input, int nbOutputMaps, DimsHW kernelSize, Weights kernelWeights, Weights biasWeights)=0
	Add a deconvolution layer to the network. More...

virtual IElementWiseLayer *	addElementWise (ITensor &input1, ITensor &input2, ElementWiseOperation op)=0
	Add an elementwise layer to the network. More...

virtual IRNNLayer *	addRNN (ITensor &inputs, int layerCount, std::size_t hiddenSize, int maxSeqLen, RNNOperation op, RNNInputMode mode, RNNDirection dir, Weights weights, Weights bias)=0
	Add an `layerCount` deep RNN layer to the network with a sequence length of `maxSeqLen` and `hiddenSize` internal state per layer. More...

virtual IPluginLayer *	addPlugin (ITensor const inputs, int nbInputs, IPlugin &plugin)=0
	Add a plugin layer to the network. More...

virtual IUnaryLayer *	addUnary (ITensor &input, UnaryOperation operation)=0
	Add a unary layer to the network. More...

virtual IPaddingLayer *	addPadding (ITensor &input, DimsHW prePadding, DimsHW postPadding)=0
	Add a padding layer to the network. More...

virtual IShuffleLayer *	addShuffle (ITensor &input)=0
	Add a shuffle layer to the network. More...

virtual void	setPoolingOutputDimensionsFormula (IOutputDimensionsFormula *formula)=0
	Set the pooling output dimensions formula. More...

virtual IOutputDimensionsFormula &	getPoolingOutputDimensionsFormula () const =0
	Get the pooling output dimensions formula. More...

virtual void	setConvolutionOutputDimensionsFormula (IOutputDimensionsFormula *formula)=0
	Set the convolution output dimensions formula. More...

virtual IOutputDimensionsFormula &	getConvolutionOutputDimensionsFormula () const =0
	Get the convolution output dimensions formula. More...

virtual void	setDeconvolutionOutputDimensionsFormula (IOutputDimensionsFormula *formula)=0
	Set the deconvolution output dimensions formula. More...

virtual IOutputDimensionsFormula &	getDeconvolutionOutputDimensionsFormula () const =0
	Get the deconvolution output dimensions formula. More...

virtual int	getNbLayers () const =0
	Get the number of layers in the network. More...

virtual ILayer *	getLayer (int index) const =0
	Get the layer specified by the given index. More...

virtual int	getNbInputs () const =0
	Get the number of inputs in the network. More...

virtual ITensor *	getInput (int index) const =0
	Get the input tensor specified by the given index. More...

virtual int	getNbOutputs () const =0
	Get the number of outputs in the network. More...

virtual ITensor *	getOutput (int index) const =0
	Get the output tensor specified by the given index. More...

virtual void	destroy ()=0
	Destroy this INetworkDefinition object.

virtual IReduceLayer *	addReduce (ITensor &input, ReduceOperation operation, uint32_t reduceAxes, bool keepDimensions)=0
	Add a reduce layer to the network. More...

virtual ITopKLayer *	addTopK (ITensor &input, TopKOperation op, int k, uint32_t reduceAxes)=0
	Add a TopK layer to the network. More...

virtual IGatherLayer *	addGather (ITensor &data, ITensor &indices, int axis)=0
	Add a gather layer to the network. More...

virtual IRaggedSoftMaxLayer *	addRaggedSoftMax (ITensor &input, ITensor &bounds)=0
	Add a RaggedSoftMax layer to the network. More...

virtual IMatrixMultiplyLayer *	addMatrixMultiply (ITensor &input0, MatrixOperation op0, ITensor &input1, MatrixOperation op1)=0
	Add a MatrixMultiply layer to the network. More...

virtual IMatrixMultiplyLayer *	addMatrixMultiply (ITensor &input0, bool transpose0, ITensor &input1, bool transpose1)=0
	Add a MatrixMultiply layer to the network. More...

virtual IConstantLayer *	addConstant (Dims dimensions, Weights weights)=0
	Add a constant layer to the network. More...

virtual IRNNv2Layer *	addRNNv2 (ITensor &input, int32_t layerCount, int32_t hiddenSize, int32_t maxSeqLen, RNNOperation op)=0
	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...

virtual IPluginLayer *	addPluginExt (ITensor const inputs, int nbInputs, IPluginExt &plugin)=0
	Add a plugin layer to the network using an IPluginExt interface. More...

virtual IIdentityLayer *	addIdentity (ITensor &input)=0
	Add an identity layer. More...

virtual void	removeTensor (ITensor &tensor)=0
	remove a tensor from the network definition. More...

virtual void	unmarkOutput (ITensor &tensor)=0
	unmark a tensor as a network output. More...

virtual IPluginV2Layer *	addPluginV2 (ITensor const inputs, int nbInputs, IPluginV2 &plugin)=0
	Add a plugin layer to the network using the IPluginV2 interface. More...

virtual ISliceLayer *	addSlice (ITensor &input, Dims start, Dims size, Dims stride)=0
	Add a slice layer to the network. More...

Detailed Description

A network definition for input to the builder.

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

Member Function Documentation

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

pure virtual

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

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

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

pure virtual

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 for all dimensions except for channel.

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

pure virtual

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 FP32, FP16, or quantized INT8 following TensorRT's normal precision rules.

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

pure virtual

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 optional bias weights for the convolution.

See Also: IConvolutionLayer

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

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

pure virtual

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 convolution kernel.
kernelWeights	The kernel weights for the convolution.
biasWeights	The optional bias weights for the convolution.

See Also: IDeconvolutionLayer

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

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

pure virtual

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 number of dimensions. 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 number of dimensions as the inputs. For each dimension, its length is the maximum of the lengths of the corresponding input dimension.

See Also: IElementWiseLayer

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

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

pure virtual

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 convolution.
biasWeights	The optional bias weights for the convolution.

See Also: IFullyConnectedLayer

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

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

pure virtual

Add a gather layer to the network.

Parameters

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

See Also: IGatherLayer

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

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

pure virtual

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.

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

pure virtual

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.

Parameters

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

Only DataType::kFLOAT, DataType::kHALF and DataType::kINT32 are valid input tensor types. The volume of the dimensions, including the maximum batch size, must be less than 2^30 elements.

See Also: ITensor

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

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

pure virtual

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

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

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

pure virtual

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

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

virtual IMatrixMultiplyLayer* nvinfer1::INetworkDefinition::addMatrixMultiply	(	ITensor &	input0,
		bool	transpose0,
		ITensor &	input1,
		bool	transpose1
	)

pure virtual

Add a MatrixMultiply layer to the network.

Parameters

input0	The first input tensor (commonly A).
transpose0	If true, op(input0)=transpose(input0), else op(input0)=input0.
input1	The second input tensor (commonly B).
transpose1	If true, op(input1)=transpose(input1), else op(input1)=input1.

See Also: IMatrixMultiplyLayer

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

Deprecated:: This interface is superseded by the overload that replaces bool with MatrixOperation.

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

pure virtual

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.

virtual IPluginLayer* nvinfer1::INetworkDefinition::addPlugin	(	ITensor const	inputs,
		int	nbInputs,
		IPlugin &	plugin
	)

pure virtual

Add a plugin layer to the network.

Parameters

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

See Also: IPluginLayer

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

virtual IPluginLayer* nvinfer1::INetworkDefinition::addPluginExt	(	ITensor const	inputs,
		int	nbInputs,
		IPluginExt &	plugin
	)

pure virtual

Add a plugin layer to the network using an IPluginExt interface.

Parameters

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

See Also: IPluginLayer

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

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

pure virtual

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

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

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

pure virtual

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

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

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

pure virtual

Add a RaggedSoftMax layer to the network.

Parameters

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

See Also: IRaggedSoftMaxLayer

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

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

pure virtual

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. Bit 0 of the uint32_t type corresponds to the non-batch dimension 0 boolean and so on. If a bit is set, then the corresponding dimension will be reduced. Let's say we have an NCHW tensor as input (three non-batch dimensions). Bit 0 corresponds to the C dimension boolean. Bit 1 corresponds to the H dimension boolean. Bit 2 corresponds to the W dimension boolean. Note that reduction is not permitted over the batch size dimension.
keepDimensions	The boolean that specifies whether or not to keep the reduced dimensions in the output of the layer.

See Also: IReduceLayer

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

virtual IRNNLayer* nvinfer1::INetworkDefinition::addRNN	(	ITensor &	inputs,
		int	layerCount,
		std::size_t	hiddenSize,
		int	maxSeqLen,
		RNNOperation	op,
		RNNInputMode	mode,
		RNNDirection	dir,
		Weights	weights,
		Weights	bias
	)

pure virtual

Add an layerCount deep RNN layer to the network with a sequence length of maxSeqLen and hiddenSize internal state per layer.

Parameters

inputs	The input tensor to the layer.
layerCount	The number of layers in the RNN.
hiddenSize	The size of the internal hidden state for each layer.
maxSeqLen	The maximum length of the time sequence.
op	The type of RNN to execute.
mode	The input mode for the RNN.
dir	The direction to run the RNN.
weights	The weights for the weight matrix parameters of the RNN.
bias	The weights for the bias vectors parameters of the RNN.

The input tensors must be of the type DataType::kFLOAT or DataType::kHALF.

See IRNNLayer::setWeights() and IRNNLayer::setBias() for details on the required input format for weights and bias.

The layout for the input tensor should be {1, S_max, N, E}, where:

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

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

S_max is the maximum allowed sequence length (number of RNN iterations)
N is the batch size
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 {L, N, H}:

L is equal to getLayerCount() if getDirection is kUNIDIRECTION, and 2*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.
N is the batch size
H is getHiddenSize().

Note that in bidirectional RNNs, the full "hidden state" for a layer l is the concatenation of its forward hidden state and its backward hidden state, and its size is 2*H.

Deprecated:: IRNNLayer is superseded by IRNNv2Layer. Use addRNNv2() instead.

See Also: IRNNLayer

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

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

pure virtual

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

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

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

pure virtual

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.
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 on the ScaleMode. For kUNIFORM, the number of weights is equal to 1. For kCHANNEL, the number of weights is equal to the channel dimension. For kELEMENTWISE, the number of weights is equal to the volume of the input.

See Also: IScaleLayer

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

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

pure virtual

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.

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

pure virtual

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.

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

pure virtual

Add a SoftMax layer to the network.

See Also: ISoftMaxLayer

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

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

pure virtual

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. Bit 0 of the uint32_t type corresponds to the non-batch dimension 0 boolean and so on. If a bit is set, then the corresponding dimension will be reduced. Let's say we have an NCHW tensor as input (three non-batch dimensions). Bit 0 corresponds to the C dimension boolean. Bit 1 corresponds to the H dimension boolean. Bit 2 corresponds to the W dimension boolean. Note that TopK reduction is currently only permitted over one dimension.

See Also: ITopKLayer

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

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

pure virtual

Add a unary layer to the network.

Parameters

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

See Also: IUnaryLayer

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

virtual IOutputDimensionsFormula& nvinfer1::INetworkDefinition::getConvolutionOutputDimensionsFormula ( ) const

pure virtual

Get the convolution output dimensions formula.

Deprecated:: This method does not currently work reliably and will be removed in a future release.

Returns: The formula from computing the convolution output dimensions.

See Also: IOutputDimensionsFormula setConvolutionOutputDimensionsFormula()

virtual IOutputDimensionsFormula& nvinfer1::INetworkDefinition::getDeconvolutionOutputDimensionsFormula ( ) const

pure virtual

Get the deconvolution output dimensions formula.

Returns: The formula from computing the deconvolution output dimensions.

Deprecated:: This method does not currently work reliably and will be removed in a future release.

See Also: IOutputDimensionsFormula setDeconvolutionOutputDimensionsFormula()

virtual ITensor* nvinfer1::INetworkDefinition::getInput ( int index ) const

pure virtual

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.

See Also: getNbInputs()

virtual ILayer* nvinfer1::INetworkDefinition::getLayer ( int index ) const

pure virtual

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()

virtual int nvinfer1::INetworkDefinition::getNbInputs ( ) const

pure virtual

Get the number of inputs in the network.

Returns: The number of inputs in the network.

See Also: getInput()

virtual int nvinfer1::INetworkDefinition::getNbLayers ( ) const

pure virtual

Get the number of layers in the network.

Returns: The number of layers in the network.

See Also: getLayer()

virtual int nvinfer1::INetworkDefinition::getNbOutputs ( ) const

pure virtual

Get the number of outputs in the network.

Returns: The number of outputs in the network.

See Also: getOutput()

virtual ITensor* nvinfer1::INetworkDefinition::getOutput ( int index ) const

pure virtual

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.

See Also: getNbOutputs()

virtual IOutputDimensionsFormula& nvinfer1::INetworkDefinition::getPoolingOutputDimensionsFormula ( ) const

pure virtual

Get the pooling output dimensions formula.

Returns: The formula from computing the pooling output dimensions.

See Also: IOutputDimensionsFormula setPoolingOutputDimensionsFormula()

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

pure virtual

Mark a tensor as a network output.

Parameters

tensor The tensor to mark as an output tensor.

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

pure virtual

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().

virtual void nvinfer1::INetworkDefinition::setConvolutionOutputDimensionsFormula ( IOutputDimensionsFormula * formula )

pure virtual

Set the convolution output dimensions formula.

Deprecated:: This method does not currently work reliably and will be removed in a future release.

Parameters

formula The formula from computing the convolution output dimensions. If null is passed, the default formula is used.

The default formula in each dimension is (inputDim + padding * 2 - kernelSize) / stride + 1.

See Also: IOutputDimensionsFormula getConvolutionOutputDimensionsFormula()

virtual void nvinfer1::INetworkDefinition::setDeconvolutionOutputDimensionsFormula ( IOutputDimensionsFormula * formula )

pure virtual

Set the deconvolution output dimensions formula.

Deprecated:: This method does not currently work reliably and will be removed in a future release.

Parameters

formula The formula from computing the deconvolution output dimensions. If null is passed, the default formula is used.

The default formula in each dimension is (inputDim - 1) * stride + kernelSize - 2 * padding.

See Also: IOutputDimensionsFormula getDevonvolutionOutputDimensionsFormula()

virtual void nvinfer1::INetworkDefinition::setPoolingOutputDimensionsFormula ( IOutputDimensionsFormula * formula )

pure virtual

Set the pooling output dimensions formula.

Parameters

formula The formula from computing the pooling output dimensions. If null is passed, the default formula is used.

The default formula in each dimension is (inputDim + padding * 2 - kernelSize) / stride + 1.

See Also: IOutputDimensionsFormula getPoolingOutputDimensionsFormula()

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

pure virtual

unmark a tensor as a network output.

Parameters

tensor The tensor to unmark as an output tensor.

see markOutput()

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

NvInfer.h

Public Member Functions

Detailed Description

Member Function Documentation