INetworkDefinition (JavaCPP Presets for TensorRT 10.12-1.5.12 API)

java.lang.Object
- org.bytedeco.javacpp.Pointer
- - org.bytedeco.tensorrt.nvinfer.INoCopy
  - - org.bytedeco.tensorrt.nvinfer.INetworkDefinition

All Implemented Interfaces:

AutoCloseable
```
@Namespace(value="nvinfer1")
 @NoOffset
 @Properties(inherit=nvinfer.class)
public class INetworkDefinition
extends INoCopy
```
\class INetworkDefinition \brief 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.

Nested Class Summary
- Nested classes/interfaces inherited from class org.bytedeco.javacpp.Pointer
  Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator, Pointer.ReferenceCounter

Field Summary
- Fields inherited from class org.bytedeco.javacpp.Pointer
  address, capacity, limit, position

Constructor Summary

Constructors
Constructor and Description
`INetworkDefinition()` Default native constructor.
`INetworkDefinition(long size)` Native array allocator.
`INetworkDefinition(Pointer p)` Pointer cast constructor.

Method Summary

All Methods Instance Methods Concrete Methods Deprecated Methods
Modifier and Type	Method and Description
`IActivationLayer`	`addActivation(ITensor input, int type)`
`IActivationLayer`	`addActivation(ITensor input, nvinfer.ActivationType type)` \brief Add an activation layer to the network.
`IAssertionLayer`	`addAssertion(ITensor condition, BytePointer message)`
`IAssertionLayer`	`addAssertion(ITensor condition, String message)` \brief Add an assertion layer to the network.
`ICastLayer`	`addCast(ITensor input, int toType)`
`ICastLayer`	`addCast(ITensor input, nvinfer.DataType toType)` \brief Add a cast layer.
`IConcatenationLayer`	`addConcatenation(ITensor inputs, int nbInputs)`
`IConcatenationLayer`	`addConcatenation(PointerPointer inputs, int nbInputs)` \brief Add a concatenation layer to the network.
`IConstantLayer`	`addConstant(Dims64 dimensions, Weights weights)` \brief Add a constant layer to the network.
`IConvolutionLayer`	`addConvolutionNd(ITensor input, long nbOutputMaps, Dims64 kernelSize, Weights kernelWeights, Weights biasWeights)` \brief Add a multi-dimension convolution layer to the network.
`ICumulativeLayer`	`addCumulative(ITensor input, ITensor axis, int operation, boolean exclusive, boolean reverse)`
`ICumulativeLayer`	`addCumulative(ITensor input, ITensor axis, nvinfer.CumulativeOperation operation, boolean exclusive, boolean reverse)` \brief Add a cumulative layer to the network.
`IDeconvolutionLayer`	`addDeconvolutionNd(ITensor input, long nbOutputMaps, Dims64 kernelSize, Weights kernelWeights, Weights biasWeights)`
`IDequantizeLayer`	`addDequantize(ITensor input, ITensor scale)` Deprecated. Deprecated in TensorRT 9.0. Superseded by three-argument addDequantize.
`IDequantizeLayer`	`addDequantize(ITensor input, ITensor scale, int outputType)`
`IDequantizeLayer`	`addDequantize(ITensor input, ITensor scale, nvinfer.DataType outputType)` \brief Add a dequantization layer to the network.
`IDynamicQuantizeLayer`	`addDynamicQuantize(ITensor input, int axis, int blockSize, int outputType, int scaleType)`
`IDynamicQuantizeLayer`	`addDynamicQuantize(ITensor input, int axis, int blockSize, nvinfer.DataType outputType, nvinfer.DataType scaleType)` \brief Add a dynamic quantization layer to the network.
`IEinsumLayer`	`addEinsum(ITensor inputs, int nbInputs, BytePointer equation)`
`IEinsumLayer`	`addEinsum(ITensor inputs, int nbInputs, String equation)`
`IEinsumLayer`	`addEinsum(PointerPointer inputs, int nbInputs, String equation)` \brief Add an Einsum layer to the network.
`IElementWiseLayer`	`addElementWise(ITensor input1, ITensor input2, int op)`
`IElementWiseLayer`	`addElementWise(ITensor input1, ITensor input2, nvinfer.ElementWiseOperation op)` \brief Add an elementwise layer to the network.
`IFillLayer`	`addFill(Dims64 dimensions, int op)` Deprecated.
`IFillLayer`	`addFill(Dims64 dimensions, int op, int outputType)`
`IFillLayer`	`addFill(Dims64 dimensions, nvinfer.FillOperation op)` Deprecated. Deprecated in TensorRT 9.0. Superseded by three-argument addFill.
`IFillLayer`	`addFill(Dims64 dimensions, nvinfer.FillOperation op, nvinfer.DataType outputType)` \brief Add a fill layer to the network.
`IGatherLayer`	`addGather(ITensor data, ITensor indices, int axis)` \brief Add gather with mode GatherMode::kDEFAULT and specified axis and nbElementWiseDims=0.
`IGatherLayer`	`addGatherV2(ITensor data, ITensor indices, int mode)`
`IGatherLayer`	`addGatherV2(ITensor data, ITensor indices, nvinfer.GatherMode mode)` \brief Add gather with specified mode, axis=0 and nbElementWiseDims=0.
`IGridSampleLayer`	`addGridSample(ITensor input, ITensor grid)` \brief Add a GridSample layer to the network.
`IIdentityLayer`	`addIdentity(ITensor input)` \brief Add an identity layer.
`IIfConditional`	`addIfConditional()` \brief Add an if-then-else to the network.
`ITensor`	`addInput(BytePointer name, int type, Dims64 dimensions)`
`ITensor`	`addInput(String name, nvinfer.DataType type, Dims64 dimensions)` \brief Add an input tensor to the network.
`ILoop`	`addLoop()` \brief Add a loop to the network.
`ILRNLayer`	`addLRN(ITensor input, long window, float alpha, float beta, float k)` \brief Add a LRN layer to the network.
`IMatrixMultiplyLayer`	`addMatrixMultiply(ITensor input0, int op0, ITensor input1, int op1)`
`IMatrixMultiplyLayer`	`addMatrixMultiply(ITensor input0, nvinfer.MatrixOperation op0, ITensor input1, nvinfer.MatrixOperation op1)` \brief Add a MatrixMultiply layer to the network.
`INMSLayer`	`addNMS(ITensor boxes, ITensor scores, ITensor maxOutputBoxesPerClass)` \brief Add a non-maximum suppression layer to the network.
`INonZeroLayer`	`addNonZero(ITensor input)` \brief Add a nonzero layer to the network.
`INormalizationLayer`	`addNormalization(ITensor input, ITensor scale, ITensor bias, int axesMask)` \brief Add a normalization layer to the network.
`IOneHotLayer`	`addOneHot(ITensor indices, ITensor values, ITensor depth, int axis)` \brief Add a OneHot layer to the network.
`IPaddingLayer`	`addPaddingNd(ITensor input, Dims64 prePadding, Dims64 postPadding)` \brief Add a padding layer to the network.
`IParametricReLULayer`	`addParametricReLU(ITensor input, ITensor slope)` \brief Add a parametric ReLU layer to the network.
`IPluginV2Layer`	`addPluginV2(ITensor inputs, int nbInputs, IPluginV2 plugin)` Deprecated.
`IPluginV2Layer`	`addPluginV2(PointerPointer inputs, int nbInputs, IPluginV2 plugin)` Deprecated. Deprecated in TensorRT 10.8. Superseded by addPluginV3.
`IPluginV3Layer`	`addPluginV3(ITensor inputs, int nbInputs, ITensor shapeInputs, int nbShapeInputs, IPluginV3 plugin)`
`IPluginV3Layer`	`addPluginV3(PointerPointer inputs, int nbInputs, PointerPointer shapeInputs, int nbShapeInputs, IPluginV3 plugin)` \brief Add a plugin layer implementing the IPluginV3 interface to the network.
`IPoolingLayer`	`addPoolingNd(ITensor input, int type, Dims64 windowSize)`
`IPoolingLayer`	`addPoolingNd(ITensor input, nvinfer.PoolingType type, Dims64 windowSize)` \brief Add a multi-dimension pooling layer to the network.
`IQuantizeLayer`	`addQuantize(ITensor input, ITensor scale)` Deprecated. Deprecated in TensorRT 9.0. Superseded by three-argument addQuantize.
`IQuantizeLayer`	`addQuantize(ITensor input, ITensor scale, int outputType)`
`IQuantizeLayer`	`addQuantize(ITensor input, ITensor scale, nvinfer.DataType outputType)` \brief Add a quantization layer to the network.
`IRaggedSoftMaxLayer`	`addRaggedSoftMax(ITensor input, ITensor bounds)` \brief Add a RaggedSoftMax layer to the network.
`IReduceLayer`	`addReduce(ITensor input, int operation, int reduceAxes, boolean keepDimensions)`
`IReduceLayer`	`addReduce(ITensor input, nvinfer.ReduceOperation operation, int reduceAxes, boolean keepDimensions)` \brief Add a reduce layer to the network.
`IResizeLayer`	`addResize(ITensor input)` \brief Add a resize layer to the network.
`IReverseSequenceLayer`	`addReverseSequence(ITensor input, ITensor sequenceLens)` \brief Add a ReverseSequence layer to the network.
`IScaleLayer`	`addScale(ITensor input, int mode, Weights shift, Weights scale, Weights power)`
`IScaleLayer`	`addScale(ITensor input, nvinfer.ScaleMode mode, Weights shift, Weights scale, Weights power)` \brief Add a Scale layer to the network.
`IScaleLayer`	`addScaleNd(ITensor input, int mode, Weights shift, Weights scale, Weights power, int channelAxis)`
`IScaleLayer`	`addScaleNd(ITensor input, nvinfer.ScaleMode mode, Weights shift, Weights scale, Weights power, int channelAxis)` \brief Add a multi-dimension scale layer to the network.
`IScatterLayer`	`addScatter(ITensor data, ITensor indices, ITensor updates, int mode)`
`IScatterLayer`	`addScatter(ITensor data, ITensor indices, ITensor updates, nvinfer.ScatterMode mode)` \brief Add a Scatter layer to the network with specified mode and axis=0.
`ISelectLayer`	`addSelect(ITensor condition, ITensor thenInput, ITensor elseInput)` \brief Add a select layer to the network.
`IShapeLayer`	`addShape(ITensor input)` \brief Add a shape layer to the network.
`IShuffleLayer`	`addShuffle(ITensor input)` \brief Add a shuffle layer to the network.
`ISliceLayer`	`addSlice(ITensor input, Dims64 start, Dims64 size, Dims64 stride)` \brief Add a slice layer to the network.
`ISoftMaxLayer`	`addSoftMax(ITensor input)` \brief Add a SoftMax layer to the network.
`ISqueezeLayer`	`addSqueeze(ITensor input, ITensor axes)` \brief Add a squeeze layer to the network.
`ITopKLayer`	`addTopK(ITensor input, int op, int k, int reduceAxes)`
`ITopKLayer`	`addTopK(ITensor input, nvinfer.TopKOperation op, int k, int reduceAxes)` \brief Add a TopK layer to the network.
`IUnaryLayer`	`addUnary(ITensor input, int operation)`
`IUnaryLayer`	`addUnary(ITensor input, nvinfer.UnaryOperation operation)` \brief Add a unary layer to the network.
`IUnsqueezeLayer`	`addUnsqueeze(ITensor input, ITensor axes)` \brief Add an unsqueeze layer to the network.
`boolean`	`areWeightsMarkedRefittable(BytePointer name)`
`boolean`	`areWeightsMarkedRefittable(String name)` \brief Whether the weight has been marked as refittable.
`IBuilder`	`getBuilder()` \brief Return the builder from which this INetworkDefinition was created.
`IErrorRecorder`	`getErrorRecorder()` \brief get the ErrorRecorder assigned to this interface.
`boolean`	`getFlag(nvinfer.NetworkDefinitionCreationFlag networkDefinitionCreationFlag)` \brief Returns true if the network definition creation flag is set
`int`	`getFlags()` \brief Get the network definition creation flags for this network definition object.
`ITensor`	`getInput(int index)` \brief Get the input tensor specified by the given index.
`ILayer`	`getLayer(int index)` \brief Get the layer specified by the given index.
`String`	`getName()` \brief Returns the name associated with the network.
`int`	`getNbInputs()` \brief Get the number of inputs in the network.
`int`	`getNbLayers()` \brief Get the number of layers in the network.
`int`	`getNbOutputs()` \brief Get the number of outputs in the network.
`ITensor`	`getOutput(int index)` \brief Get the output tensor specified by the given index.
`INetworkDefinition`	`getPointer(long i)`
`boolean`	`hasImplicitBatchDimension()` Deprecated. Deprecated in TensorRT 10.0. Implicit batch is not supported since TensorRT 10.0.
`boolean`	`isDebugTensor(ITensor tensor)` \brief Check if a tensor is marked as debug tensor.
`boolean`	`markDebug(ITensor tensor)` \brief Mark a tensor as a debug tensor.
`void`	`markOutput(ITensor tensor)` \brief Mark a tensor as a network output.
`boolean`	`markOutputForShapes(ITensor tensor)` \brief Enable tensor's value to be computed by IExecutionContext::getShapeBinding.
`boolean`	`markUnfusedTensorsAsDebugTensors()` \brief Mark unfused tensors as debug tensors.
`boolean`	`markWeightsRefittable(BytePointer name)`
`boolean`	`markWeightsRefittable(String name)` \brief Mark weights as refittable when the builder flag kREFIT_INDIVIDUAL is set.
`INetworkDefinition`	`position(long position)`
`void`	`removeTensor(ITensor tensor)` \brief remove a tensor from the network definition.
`void`	`setErrorRecorder(IErrorRecorder recorder)`
`void`	`setName(BytePointer name)`
`void`	`setName(String name)` \brief Sets the name of the network.
`boolean`	`setWeightsName(Weights weights, BytePointer name)`
`boolean`	`setWeightsName(Weights weights, String name)` \brief Associate a name with all current uses of the given weights.
`boolean`	`unmarkDebug(ITensor tensor)` \brief Unmark a tensor as a debug tensor.
`void`	`unmarkOutput(ITensor tensor)` \brief unmark a tensor as a network output.
`boolean`	`unmarkOutputForShapes(ITensor tensor)` \brief Undo markOutputForShapes.
`boolean`	`unmarkUnfusedTensorsAsDebugTensors()` \brief Undo the marking of unfused tensors as debug tensors.
`boolean`	`unmarkWeightsRefittable(BytePointer name)`
`boolean`	`unmarkWeightsRefittable(String name)` \brief Unmark weights as refittable when the builder flag kREFIT_INDIVIDUAL is set.

Methods inherited from class org.bytedeco.javacpp.Pointer
address, asBuffer, asByteBuffer, availablePhysicalBytes, calloc, capacity, capacity, close, deallocate, deallocate, deallocateReferences, deallocator, deallocator, equals, fill, formatBytes, free, getDirectBufferAddress, getPointer, getPointer, getPointer, hashCode, interruptDeallocatorThread, isNull, isNull, limit, limit, malloc, maxBytes, maxPhysicalBytes, memchr, memcmp, memcpy, memmove, memset, offsetAddress, offsetof, offsetof, parseBytes, physicalBytes, physicalBytesInaccurate, position, put, realloc, referenceCount, releaseReference, retainReference, setNull, sizeof, sizeof, toString, totalBytes, totalCount, totalPhysicalBytes, withDeallocator, zero

Methods inherited from class java.lang.Object
clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Constructor Detail
- INetworkDefinition
```
public INetworkDefinition()
```
  Default native constructor.
- INetworkDefinition
```
public INetworkDefinition(long size)
```
  Native array allocator. Access with Pointer.position(long).
- INetworkDefinition
```
public INetworkDefinition(Pointer p)
```
  Pointer cast constructor. Invokes Pointer(Pointer).

Method Detail

position

public INetworkDefinition position(long position)

Overrides:: position in class Pointer

getPointer

public INetworkDefinition getPointer(long i)

Overrides:: getPointer in class Pointer

addInput
```
@NoException(value=true)
public ITensor addInput(String name,
                                                 nvinfer.DataType type,
                                                 @Cast(value="const nvinfer1::Dims*") @ByRef
                                                 Dims64 dimensions)
```
\brief 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. \warning 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. \warning The string name must be null-terminated, and be at most 4096 bytes including the terminator.

Returns:

The new tensor or nullptr if there is an error.

See Also:

ITensor

addInput

@NoException(value=true)
public ITensor addInput(@Cast(value="const char*")
                                                 BytePointer name,
                                                 @Cast(value="nvinfer1::DataType")
                                                 int type,
                                                 @Cast(value="const nvinfer1::Dims*") @ByRef
                                                 Dims64 dimensions)

markOutput
```
@NoException(value=true)
public void markOutput(@ByRef
                                                ITensor tensor)
```
\brief 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. \warning It is an error to mark a tensor inside an ILoop or an IIfConditional as an output.

markDebug
```
@Cast(value="bool")
 @NoException(value=true)
public boolean markDebug(@ByRef
                                                                       ITensor tensor)
```
\brief 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()

unmarkDebug
```
@Cast(value="bool")
 @NoException(value=true)
public boolean unmarkDebug(@ByRef
                                                                         ITensor tensor)
```
\brief 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()

isDebugTensor

@Cast(value="bool")
 @NoException(value=true)
public boolean isDebugTensor(@Const @ByRef
                                                                           ITensor tensor)

\brief Check if a tensor is marked as debug tensor.

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

markUnfusedTensorsAsDebugTensors
```
@Cast(value="bool")
 @NoException(value=true)
public boolean markUnfusedTensorsAsDebugTensors()
```
\brief Mark unfused tensors as debug tensors. Debug tensors can be optionally emitted at runtime. Tensors that are fused by the optimizer will not be emitted. Tensors marked this way will not prevent fusion like markDebug() does, thus preserving performance. \warning Tensors marked this way cannot be detected by isDebugTensor(). \warning DebugListener can only get internal tensor names instead of the original tensor names in the NetworkDefinition for tensors marked this way. But the names correspond to the names obtained by IEngineInspector. \warning There is no guarantee that all unfused tensors are marked.

Returns:

True if tensors were successfully marked (or were already marked), false otherwise.

See Also:

unmarkUnfusedTensorsAsDebugTensors(), markDebug(), IExecutionContext::setDebugListener()

unmarkUnfusedTensorsAsDebugTensors
```
@Cast(value="bool")
 @NoException(value=true)
public boolean unmarkUnfusedTensorsAsDebugTensors()
```
\brief Undo the marking of unfused tensors as debug tensors. This has no effect on tensors marked by markDebug().

Returns:

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

See Also:

markUnfusedTensorsAsDebugTensors(), IExecutionContext::setDebugListener()

addActivation
```
@NoException(value=true)
public IActivationLayer addActivation(@ByRef
                                                               ITensor input,
                                                               nvinfer.ActivationType type)
```
\brief 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.

Returns:

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

See Also:

ActivationType \warning Int32 and Int64 are valid only for activation type kRELU.

addActivation

@NoException(value=true)
public IActivationLayer addActivation(@ByRef
                                                               ITensor input,
                                                               @Cast(value="nvinfer1::ActivationType")
                                                               int type)

addLRN

@NoException(value=true)
public ILRNLayer addLRN(@ByRef
                                                 ITensor input,
                                                 @Cast(value="int64_t")
                                                 long window,
                                                 float alpha,
                                                 float beta,
                                                 float k)

\brief 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.
Returns:: The new LRN layer, or nullptr if it could not be created.
See Also:: \warning Int32 tensors are not valid input tensors.

addScale

@NoException(value=true)
public IScaleLayer addScale(@ByRef
                                                     ITensor input,
                                                     nvinfer.ScaleMode mode,
                                                     @ByVal
                                                     Weights shift,
                                                     @ByVal
                                                     Weights scale,
                                                     @ByVal
                                                     Weights power)

\brief 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.
Returns:: The new Scale layer, or nullptr if it could not be created.
See Also:: addScaleNd, \warning Int32 tensors are not valid input tensors.

addScale

@NoException(value=true)
public IScaleLayer addScale(@ByRef
                                                     ITensor input,
                                                     @Cast(value="nvinfer1::ScaleMode")
                                                     int mode,
                                                     @ByVal
                                                     Weights shift,
                                                     @ByVal
                                                     Weights scale,
                                                     @ByVal
                                                     Weights power)

addSoftMax

@NoException(value=true)
public ISoftMaxLayer addSoftMax(@ByRef
                                                         ITensor input)

\brief Add a SoftMax layer to the network.

Returns:: The new SoftMax layer, or nullptr if it could not be created.
See Also:: \warning Int32 tensors are not valid input tensors.

addConcatenation

@NoException(value=true)
public IConcatenationLayer addConcatenation(@Cast(value="nvinfer1::ITensor*const*")
                                                                     PointerPointer inputs,
                                                                     int nbInputs)

\brief Add a concatenation layer to the network.

Parameters:: inputs - The input tensors to the layer.; nbInputs - The number of input tensors.
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.
See Also:: IConcatenationLayer

addConcatenation

@NoException(value=true)
public IConcatenationLayer addConcatenation(@ByPtrPtr
                                                                     ITensor inputs,
                                                                     int nbInputs)

addElementWise
```
@NoException(value=true)
public IElementWiseLayer addElementWise(@ByRef
                                                                 ITensor input1,
                                                                 @ByRef
                                                                 ITensor input2,
                                                                 nvinfer.ElementWiseOperation op)
```
\brief 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.

Returns:

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

See Also:

IElementWiseLayer

addElementWise

@NoException(value=true)
public IElementWiseLayer addElementWise(@ByRef
                                                                 ITensor input1,
                                                                 @ByRef
                                                                 ITensor input2,
                                                                 @Cast(value="nvinfer1::ElementWiseOperation")
                                                                 int op)

addUnary
```
@NoException(value=true)
public IUnaryLayer addUnary(@ByRef
                                                     ITensor input,
                                                     nvinfer.UnaryOperation operation)
```
\brief Add a unary layer to the network.

Parameters:

input - The input tensor to the layer.

operation - The operation to apply.

Returns:

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

See Also:

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.

addUnary

@NoException(value=true)
public IUnaryLayer addUnary(@ByRef
                                                     ITensor input,
                                                     @Cast(value="nvinfer1::UnaryOperation")
                                                     int operation)

addShuffle

@NoException(value=true)
public IShuffleLayer addShuffle(@ByRef
                                                         ITensor input)

\brief Add a shuffle layer to the network.

Parameters:: input - The input tensor to the layer.
Returns:: The new shuffle layer, or nullptr if it could not be created.
See Also:: IShuffleLayer

addOneHot

@NoException(value=true)
public IOneHotLayer addOneHot(@ByRef
                                                       ITensor indices,
                                                       @ByRef
                                                       ITensor values,
                                                       @ByRef
                                                       ITensor depth,
                                                       int axis)

\brief 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.
Returns:: The new OneHot layer, or nullptr if it could not be created.
See Also:: IOneHotLayer

getNbLayers
```
@NoException(value=true)
public int getNbLayers()
```
\brief Get the number of layers in the network.

Returns:

The number of layers in the network.

See Also:

getLayer()

getLayer
```
@NoException(value=true)
public ILayer getLayer(int index)
```
\brief 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()

getNbInputs
```
@NoException(value=true)
public int getNbInputs()
```
\brief Get the number of inputs in the network.

Returns:

The number of inputs in the network.

See Also:

getInput()

getInput
```
@NoException(value=true)
public ITensor getInput(int index)
```
\brief 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()

getNbOutputs
```
@NoException(value=true)
public int getNbOutputs()
```
\brief 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
```
@NoException(value=true)
public ITensor getOutput(int index)
```
\brief 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()

addReduce
```
@NoException(value=true)
public IReduceLayer addReduce(@ByRef
                                                       ITensor input,
                                                       nvinfer.ReduceOperation operation,
                                                       @Cast(value="uint32_t")
                                                       int reduceAxes,
                                                       @Cast(value="bool")
                                                       boolean keepDimensions)
```
\brief 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 \p operation to reduce the tensor \p input across the axes specified by \p reduceAxes.

Returns:

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

See Also:

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

addReduce

@NoException(value=true)
public IReduceLayer addReduce(@ByRef
                                                       ITensor input,
                                                       @Cast(value="nvinfer1::ReduceOperation")
                                                       int operation,
                                                       @Cast(value="uint32_t")
                                                       int reduceAxes,
                                                       @Cast(value="bool")
                                                       boolean keepDimensions)

addTopK
```
@NoException(value=true)
public ITopKLayer addTopK(@ByRef
                                                   ITensor input,
                                                   nvinfer.TopKOperation op,
                                                   int k,
                                                   @Cast(value="uint32_t")
                                                   int reduceAxes)
```
\brief 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.

Returns:

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

See Also:

ITopKLayer

addTopK

@NoException(value=true)
public ITopKLayer addTopK(@ByRef
                                                   ITensor input,
                                                   @Cast(value="nvinfer1::TopKOperation")
                                                   int op,
                                                   int k,
                                                   @Cast(value="uint32_t")
                                                   int reduceAxes)

addGather

@NoException(value=true)
public IGatherLayer addGather(@ByRef
                                                       ITensor data,
                                                       @ByRef
                                                       ITensor indices,
                                                       int axis)

\brief 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.
Returns:: The new gather layer, or nullptr if it could not be created.
See Also:: IGatherLayer

addGatherV2

@NoException(value=true)
public IGatherLayer addGatherV2(@ByRef
                                                         ITensor data,
                                                         @ByRef
                                                         ITensor indices,
                                                         nvinfer.GatherMode mode)

\brief 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.
Returns:: The new gather layer, or nullptr if it could not be created.
See Also:: IGatherLayer

addGatherV2

@NoException(value=true)
public IGatherLayer addGatherV2(@ByRef
                                                         ITensor data,
                                                         @ByRef
                                                         ITensor indices,
                                                         @Cast(value="nvinfer1::GatherMode")
                                                         int mode)

addRaggedSoftMax

@NoException(value=true)
public IRaggedSoftMaxLayer addRaggedSoftMax(@ByRef
                                                                     ITensor input,
                                                                     @ByRef
                                                                     ITensor bounds)

\brief Add a RaggedSoftMax layer to the network.

Parameters:: input - The ZxS input tensor.; bounds - The Zx1 bounds tensor.
Returns:: The new RaggedSoftMax layer, or nullptr if it could not be created.
See Also:: \warning The bounds tensor cannot have the last dimension be the wildcard character. \warning Int32 tensors are not valid input tensors. \warning The input and bounds tensors should be 3D tensors.

addMatrixMultiply

@NoException(value=true)
public IMatrixMultiplyLayer addMatrixMultiply(@ByRef
                                                                       ITensor input0,
                                                                       nvinfer.MatrixOperation op0,
                                                                       @ByRef
                                                                       ITensor input1,
                                                                       nvinfer.MatrixOperation op1)

\brief 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.
Returns:: The new matrix multiply layer, or nullptr if it could not be created.
See Also:: \warning Int32 tensors are not valid input tensors.

addMatrixMultiply

@NoException(value=true)
public IMatrixMultiplyLayer addMatrixMultiply(@ByRef
                                                                       ITensor input0,
                                                                       @Cast(value="nvinfer1::MatrixOperation")
                                                                       int op0,
                                                                       @ByRef
                                                                       ITensor input1,
                                                                       @Cast(value="nvinfer1::MatrixOperation")
                                                                       int op1)

addNonZero

@NoException(value=true)
public INonZeroLayer addNonZero(@ByRef
                                                         ITensor input)

\brief Add a nonzero layer to the network.

Parameters:: input - The input tensor to the layer.
Returns:: The new nonzero layer, or nullptr if it could be created.
See Also:: INonZeroLayer

addConstant
```
@NoException(value=true)
public IConstantLayer addConstant(@Cast(value="const nvinfer1::Dims*") @ByRef
                                                           Dims64 dimensions,
                                                           @ByVal
                                                           Weights weights)
```
\brief Add a constant layer to the network.

Parameters:

dimensions - The dimensions of the constant.

weights - The constant value, represented as weights.

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.

See Also:

IConstantLayer

addIdentity

@NoException(value=true)
public IIdentityLayer addIdentity(@ByRef
                                                           ITensor input)

\brief Add an identity layer.

Parameters:: input - The input tensor to the layer.
Returns:: The new identity layer, or nullptr if it could not be created.
See Also:: IIdentityLayer

addCast

@NoException(value=true)
public ICastLayer addCast(@ByRef
                                                   ITensor input,
                                                   nvinfer.DataType toType)

\brief Add a cast layer.

Parameters:: input - The input tensor to the layer.; toType - The DataType of the output tensor
Returns:: The new cast layer, or nullptr if it could not be created.
See Also:: ICastLayer

addCast

@NoException(value=true)
public ICastLayer addCast(@ByRef
                                                   ITensor input,
                                                   @Cast(value="nvinfer1::DataType")
                                                   int toType)

removeTensor
```
@NoException(value=true)
public void removeTensor(@ByRef
                                                  ITensor tensor)
```
\brief 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().

unmarkOutput

@NoException(value=true)
public void unmarkOutput(@ByRef
                                                  ITensor tensor)

\brief unmark a tensor as a network output.

Parameters:: tensor - The tensor to unmark as an output tensor. see markOutput()

addPluginV2

@Deprecated
 @NoException(value=true)
public IPluginV2Layer addPluginV2(@Cast(value="nvinfer1::ITensor*const*")
                                                                        PointerPointer inputs,
                                                                        int nbInputs,
                                                                        @ByRef
                                                                        IPluginV2 plugin)

Deprecated. Deprecated in TensorRT 10.8. Superseded by addPluginV3.

\brief 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.
Returns:: The new plugin layer, or nullptr if it could not be created.
See Also:: \warning Dimension wildcard are only supported with IPluginV2DynamicExt or IPluginV2IOExt plugins. \warning Int32 tensors are not valid input tensors.

addPluginV2

@Deprecated
 @NoException(value=true)
public IPluginV2Layer addPluginV2(@ByPtrPtr
                                                                        ITensor inputs,
                                                                        int nbInputs,
                                                                        @ByRef
                                                                        IPluginV2 plugin)

Deprecated.

addPluginV3

@NoException(value=true)
public IPluginV3Layer addPluginV3(@Cast(value="nvinfer1::ITensor*const*")
                                                           PointerPointer inputs,
                                                           int nbInputs,
                                                           @Cast(value="nvinfer1::ITensor*const*")
                                                           PointerPointer shapeInputs,
                                                           int nbShapeInputs,
                                                           @ByRef
                                                           IPluginV3 plugin)

\brief 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.
Returns:: The new plugin layer, or nullptr if it could not be created.
See Also:: IPluginV3Layer

addPluginV3

@NoException(value=true)
public IPluginV3Layer addPluginV3(@ByPtrPtr
                                                           ITensor inputs,
                                                           int nbInputs,
                                                           @ByPtrPtr
                                                           ITensor shapeInputs,
                                                           int nbShapeInputs,
                                                           @ByRef
                                                           IPluginV3 plugin)

addSlice

@NoException(value=true)
public ISliceLayer addSlice(@ByRef
                                                     ITensor input,
                                                     @Cast(value="const nvinfer1::Dims*") @ByRef
                                                     Dims64 start,
                                                     @Cast(value="const nvinfer1::Dims*") @ByRef
                                                     Dims64 size,
                                                     @Cast(value="const nvinfer1::Dims*") @ByRef
                                                     Dims64 stride)

\brief 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.
Returns:: The new slice layer, or nullptr if it could not be created.
See Also:: ISliceLayer

setName
```
@NoException(value=true)
public void setName(String name)
```
\brief 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 \p 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()

setName

@NoException(value=true)
public void setName(@Cast(value="const char*")
                                             BytePointer name)

getName
```
@NoException(value=true)
public String getName()
```
\brief Returns the name associated with the network. The memory pointed to by getName() is owned by the INetworkDefinition object.

Returns:

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

See Also:

INetworkDefinition::setName()

addShape
```
@NoException(value=true)
public IShapeLayer addShape(@ByRef
                                                     ITensor input)
```
\brief Add a shape layer to the network.

Parameters:

input - The input tensor to the layer.

Returns:

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

See Also:

\warning addShape is only supported when hasImplicitBatchDimensions is false.

hasImplicitBatchDimension
```
@Cast(value="bool")
 @Deprecated
 @NoException(value=true)
public boolean hasImplicitBatchDimension()
```
Deprecated. Deprecated in TensorRT 10.0. Implicit batch is not supported since TensorRT 10.0.

\brief 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

getFlags
```
@Cast(value="nvinfer1::NetworkDefinitionCreationFlags")
 @NoException(value=true)
public int getFlags()
```
\brief Get the network definition creation flags for this network definition object. Defaults to 0.

Returns:

The network definition creation options as a bitmask.

getFlag

@Cast(value="bool")
 @NoException(value=true)
public boolean getFlag(@ByVal
                                                                     nvinfer.NetworkDefinitionCreationFlag networkDefinitionCreationFlag)

\brief Returns true if the network definition creation flag is set

Returns:: True if flag is set, false if unset.
See Also:: getFlags()

markOutputForShapes
```
@Cast(value="bool")
 @NoException(value=true)
public boolean markOutputForShapes(@ByRef
                                                                                 ITensor tensor)
```
\brief 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. \warning It is an error to mark a network input as a shape output.

unmarkOutputForShapes

@Cast(value="bool")
 @NoException(value=true)
public boolean unmarkOutputForShapes(@ByRef
                                                                                   ITensor tensor)

\brief Undo markOutputForShapes. \warning inputs to addShape cannot contain wildcard dimension values.

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

addParametricReLU

@NoException(value=true)
public IParametricReLULayer addParametricReLU(@ByRef
                                                                       ITensor input,
                                                                       @ByRef
                                                                       ITensor slope)

\brief 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.
Returns:: The new parametric ReLU layer, or nullptr if it could not be created.
See Also:: \warning Tensors of type Int32, Int64, Bool, or UInt8 are not allowed as inputs.

addConvolutionNd

@NoException(value=true)
public IConvolutionLayer addConvolutionNd(@ByRef
                                                                   ITensor input,
                                                                   @Cast(value="int64_t")
                                                                   long nbOutputMaps,
                                                                   @Cast(value="const nvinfer1::Dims*") @ByRef
                                                                   Dims64 kernelSize,
                                                                   @ByVal
                                                                   Weights kernelWeights,
                                                                   @ByVal
                                                                   Weights biasWeights)

\brief 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.
Returns:: The new convolution layer, or nullptr if it could not be created.
See Also:: \warning It is an error to specify a wildcard value for the 'C' dimension of the input tensor. \warning Int32 tensors are not valid input tensors. \warning Only 2D or 3D convolution is supported.

addPoolingNd

@NoException(value=true)
public IPoolingLayer addPoolingNd(@ByRef
                                                           ITensor input,
                                                           nvinfer.PoolingType type,
                                                           @Cast(value="const nvinfer1::Dims*") @ByRef
                                                           Dims64 windowSize)

\brief 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.
Returns:: The new pooling layer, or nullptr if it could not be created.
See Also:: PoolingType \warning Int32 tensors are not valid input tensors. \warning Only 2D or 3D pooling is supported.

addPoolingNd

@NoException(value=true)
public IPoolingLayer addPoolingNd(@ByRef
                                                           ITensor input,
                                                           @Cast(value="nvinfer1::PoolingType")
                                                           int type,
                                                           @Cast(value="const nvinfer1::Dims*") @ByRef
                                                           Dims64 windowSize)

addDeconvolutionNd

@NoException(value=true)
public IDeconvolutionLayer addDeconvolutionNd(@ByRef
                                                                       ITensor input,
                                                                       @Cast(value="int64_t")
                                                                       long nbOutputMaps,
                                                                       @ByVal @Cast(value="nvinfer1::Dims*")
                                                                       Dims64 kernelSize,
                                                                       @ByVal
                                                                       Weights kernelWeights,
                                                                       @ByVal
                                                                       Weights biasWeights)

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

addScaleNd

@NoException(value=true)
public IScaleLayer addScaleNd(@ByRef
                                                       ITensor input,
                                                       nvinfer.ScaleMode mode,
                                                       @ByVal
                                                       Weights shift,
                                                       @ByVal
                                                       Weights scale,
                                                       @ByVal
                                                       Weights power,
                                                       int channelAxis)

\brief 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().
Returns:: The new Scale layer, or nullptr if it could not be created.
See Also:: IScaleLayer, \warning Int32 tensors are not valid input tensors. \warning Only 2D or 3D scale is supported.

addScaleNd

@NoException(value=true)
public IScaleLayer addScaleNd(@ByRef
                                                       ITensor input,
                                                       @Cast(value="nvinfer1::ScaleMode")
                                                       int mode,
                                                       @ByVal
                                                       Weights shift,
                                                       @ByVal
                                                       Weights scale,
                                                       @ByVal
                                                       Weights power,
                                                       int channelAxis)

addResize
```
@NoException(value=true)
public IResizeLayer addResize(@ByRef
                                                       ITensor input)
```
\brief Add a resize layer to the network.

Parameters:

input - The input tensor to the layer.

Returns:

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

See Also:

\warning Int32 tensors are not valid input tensors.

addLoop
```
@NoException(value=true)
public ILoop addLoop()
```
\brief 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

addIfConditional
```
@NoException(value=true)
public IIfConditional addIfConditional()
```
\brief 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

addSelect
```
@NoException(value=true)
public ISelectLayer addSelect(@ByRef
                                                       ITensor condition,
                                                       @ByRef
                                                       ITensor thenInput,
                                                       @ByRef
                                                       ITensor elseInput)
```
\brief 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.

Returns:

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

See Also:

ISelectLayer

addAssertion

@NoException(value=true)
public IAssertionLayer addAssertion(@ByRef
                                                             ITensor condition,
                                                             String message)

\brief Add an assertion layer to the network.

Parameters:: condition - The input tensor to the layer.; message - A message to print if the assertion fails.
Returns:: The new assertion layer, or nullptr if it could not be created. The input tensor must be a boolean shape tensor.
See Also:: IAssertionLayer

addAssertion

@NoException(value=true)
public IAssertionLayer addAssertion(@ByRef
                                                             ITensor condition,
                                                             @Cast(value="const char*")
                                                             BytePointer message)

addFill
```
@Deprecated
 @NoException(value=true)
public IFillLayer addFill(@Cast(value="const nvinfer1::Dims*") @ByRef
                                                                Dims64 dimensions,
                                                                nvinfer.FillOperation op)
```
Deprecated. Deprecated in TensorRT 9.0. Superseded by three-argument addFill.

\brief 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 \p 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.

Returns:

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

See Also:

IFillLayer

addFill

@Deprecated
 @NoException(value=true)
public IFillLayer addFill(@Cast(value="const nvinfer1::Dims*") @ByRef
                                                                Dims64 dimensions,
                                                                @Cast(value="nvinfer1::FillOperation")
                                                                int op)

Deprecated.

addFill
```
@NoException(value=true)
public IFillLayer addFill(@Cast(value="const nvinfer1::Dims*") @ByRef
                                                   Dims64 dimensions,
                                                   nvinfer.FillOperation op,
                                                   nvinfer.DataType outputType)
```
\brief 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 \p 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.

Returns:

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

See Also:

IFillLayer

addFill

@NoException(value=true)
public IFillLayer addFill(@Cast(value="const nvinfer1::Dims*") @ByRef
                                                   Dims64 dimensions,
                                                   @Cast(value="nvinfer1::FillOperation")
                                                   int op,
                                                   @Cast(value="nvinfer1::DataType")
                                                   int outputType)

addPaddingNd

@NoException(value=true)
public IPaddingLayer addPaddingNd(@ByRef
                                                           ITensor input,
                                                           @Cast(value="const nvinfer1::Dims*") @ByRef
                                                           Dims64 prePadding,
                                                           @Cast(value="const nvinfer1::Dims*") @ByRef
                                                           Dims64 postPadding)

\brief 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.
Returns:: The new padding layer, or nullptr if it could not be created.
See Also:: IPaddingLayer

setWeightsName
```
@Cast(value="bool")
 @NoException(value=true)
public boolean setWeightsName(@ByVal
                                                                            Weights weights,
                                                                            String name)
```
\brief 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.

setWeightsName

@Cast(value="bool")
 @NoException(value=true)
public boolean setWeightsName(@ByVal
                                                                            Weights weights,
                                                                            @Cast(value="const char*")
                                                                            BytePointer name)

setErrorRecorder

@NoException(value=true)
public void setErrorRecorder(IErrorRecorder recorder)

See Also:: /**

getErrorRecorder
```
@NoException(value=true)
public IErrorRecorder getErrorRecorder()
```
\brief 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()

addDequantize

@Deprecated
 @NoException(value=true)
public IDequantizeLayer addDequantize(@ByRef
                                                                            ITensor input,
                                                                            @ByRef
                                                                            ITensor scale)

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

\brief Add a dequantization layer to the network.

Parameters:: input - The input tensor to be quantized.; scale - A tensor with the scale value.
Returns:: The new quantization layer, or nullptr if it could not be created.
See Also:: \p input tensor data type must be DataType::kINT8 or DataType::kFP8. \p scale tensor data type must be DataType::kFLOAT. The subgraph which terminates with the \p scale tensor must be a build-time constant.

addDequantize
```
@NoException(value=true)
public IDequantizeLayer addDequantize(@ByRef
                                                               ITensor input,
                                                               @ByRef
                                                               ITensor scale,
                                                               nvinfer.DataType outputType)
```
\brief 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.

Returns:

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

See Also:

\p input tensor data type must be DataType::kINT8, DataType::kFP8 or DataType::kINT4. \p 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 \p scale tensor must be a build-time constant. \p 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.

addDequantize

@NoException(value=true)
public IDequantizeLayer addDequantize(@ByRef
                                                               ITensor input,
                                                               @ByRef
                                                               ITensor scale,
                                                               @Cast(value="nvinfer1::DataType")
                                                               int outputType)

addScatter

@NoException(value=true)
public IScatterLayer addScatter(@ByRef
                                                         ITensor data,
                                                         @ByRef
                                                         ITensor indices,
                                                         @ByRef
                                                         ITensor updates,
                                                         nvinfer.ScatterMode mode)

\brief 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.
Returns:: The new Scatter layer, or nullptr if it could not be created.
See Also:: \p indices tensor data type must be DataType::kINT32. \p updates tensor data type must be the same as \p data

addScatter

@NoException(value=true)
public IScatterLayer addScatter(@ByRef
                                                         ITensor data,
                                                         @ByRef
                                                         ITensor indices,
                                                         @ByRef
                                                         ITensor updates,
                                                         @Cast(value="nvinfer1::ScatterMode")
                                                         int mode)

addQuantize

@Deprecated
 @NoException(value=true)
public IQuantizeLayer addQuantize(@ByRef
                                                                        ITensor input,
                                                                        @ByRef
                                                                        ITensor scale)

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

\brief Add a quantization layer to the network.

Parameters:: input - The input tensor to be quantized.; scale - A tensor with the scale value.
Returns:: The new quantization layer, or nullptr if it could not be created.
See Also:: \p input tensor data type must be DataType::kFLOAT or DataType::kHALF. \p scale tensor data type must be DataType::kFLOAT. The subgraph which terminates with the \p scale tensor must be a build-time constant.

addQuantize
```
@NoException(value=true)
public IQuantizeLayer addQuantize(@ByRef
                                                           ITensor input,
                                                           @ByRef
                                                           ITensor scale,
                                                           nvinfer.DataType outputType)
```
\brief 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.

Returns:

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

See Also:

\p input tensor data type must be DataType::kFLOAT, DataType::kHALF or DataType::kBF16. \p 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 \p scale tensor must be a build-time constant. \p 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.

addQuantize

@NoException(value=true)
public IQuantizeLayer addQuantize(@ByRef
                                                           ITensor input,
                                                           @ByRef
                                                           ITensor scale,
                                                           @Cast(value="nvinfer1::DataType")
                                                           int outputType)

addDynamicQuantize
```
@NoException(value=true)
public IDynamicQuantizeLayer addDynamicQuantize(@ByRef
                                                                         ITensor input,
                                                                         int axis,
                                                                         int blockSize,
                                                                         nvinfer.DataType outputType,
                                                                         nvinfer.DataType scaleType)
```
\brief 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. Valid values are 16 (NVFP4 quantization) and 32 (MXFP8 quantization).

outputType - The data type of the quantized output tensor, must be DataType::kFP4 (NVFP4 quantization) or DataType::kFP8 (MXFP8 quantization). 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 (NVFP4 quantization) or DataType::kE8M0 (MXFP8 quantization).

Returns:

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

See Also:

IDynamicQuantizeLayer

addDynamicQuantize

@NoException(value=true)
public IDynamicQuantizeLayer addDynamicQuantize(@ByRef
                                                                         ITensor input,
                                                                         int axis,
                                                                         int blockSize,
                                                                         @Cast(value="nvinfer1::DataType")
                                                                         int outputType,
                                                                         @Cast(value="nvinfer1::DataType")
                                                                         int scaleType)

addEinsum

@NoException(value=true)
public IEinsumLayer addEinsum(@Cast(value="nvinfer1::ITensor*const*")
                                                       PointerPointer inputs,
                                                       int nbInputs,
                                                       String equation)

\brief 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
Returns:: The new Einsum layer, or nullptr if it could not be created.
See Also:: IEinsumLayer

addEinsum

@NoException(value=true)
public IEinsumLayer addEinsum(@ByPtrPtr
                                                       ITensor inputs,
                                                       int nbInputs,
                                                       String equation)

addEinsum

@NoException(value=true)
public IEinsumLayer addEinsum(@ByPtrPtr
                                                       ITensor inputs,
                                                       int nbInputs,
                                                       @Cast(value="const char*")
                                                       BytePointer equation)

addGridSample

@NoException(value=true)
public IGridSampleLayer addGridSample(@ByRef
                                                               ITensor input,
                                                               @ByRef
                                                               ITensor grid)

\brief Add a GridSample layer to the network.

Parameters:: input - The input tensor to the layer.; grid - The grid tensor to the layer.
Returns:: The new GridSample layer, or nullptr if it could not be created.
See Also:: Creates a GridSample layer with a InterpolationMode::kLINEAR, unaligned corners, and SampleMode::kFILL for 4d-shape input tensors.

addNMS

@NoException(value=true)
public INMSLayer addNMS(@ByRef
                                                 ITensor boxes,
                                                 @ByRef
                                                 ITensor scores,
                                                 @ByRef
                                                 ITensor maxOutputBoxesPerClass)

\brief 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.
Returns:: The new NMS layer, or nullptr if it could not be created.
See Also:: INMSLayer

addReverseSequence

@NoException(value=true)
public IReverseSequenceLayer addReverseSequence(@ByRef
                                                                         ITensor input,
                                                                         @ByRef
                                                                         ITensor sequenceLens)

\brief 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.
Returns:: The new ReverseSequence layer, or nullptr if it could not be created.
See Also:: IReverseSequenceLayer

addNormalization

@NoException(value=true)
public INormalizationLayer addNormalization(@ByRef
                                                                     ITensor input,
                                                                     @ByRef
                                                                     ITensor scale,
                                                                     @ByRef
                                                                     ITensor bias,
                                                                     @Cast(value="uint32_t")
                                                                     int axesMask)

\brief 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 \p input on the specified \p axesMask. The result is then scaled by multiplying with \p scale and adding \p bias. The shape of \p scale and \p bias are expected the be the same, and must have the same rank and be unidirectionally broadcastable to the shape of \p input.
Returns:: The new normalization layer, or nullptr if it could not be created.
See Also:: INormalizationLayer

addCumulative

@NoException(value=true)
public ICumulativeLayer addCumulative(@ByRef
                                                               ITensor input,
                                                               @ByRef
                                                               ITensor axis,
                                                               nvinfer.CumulativeOperation operation,
                                                               @Cast(value="bool")
                                                               boolean exclusive,
                                                               @Cast(value="bool")
                                                               boolean reverse)

\brief 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. @param operation The reduction operation to perform. @param exclusive The boolean that specifies whether it is an exclusive cumulative or inclusive cumulative. @param reverse The boolean that specifies whether the cumulative operation should be applied backward. The cumulative layer works by performing the specified cumulative \p operation to the tensor \p input on the axis specified by \p axis.
Returns:: The new cumulative layer, or nullptr if it could not be created.
See Also:: ICumulativeLayer

addCumulative

@NoException(value=true)
public ICumulativeLayer addCumulative(@ByRef
                                                               ITensor input,
                                                               @ByRef
                                                               ITensor axis,
                                                               @Cast(value="nvinfer1::CumulativeOperation")
                                                               int operation,
                                                               @Cast(value="bool")
                                                               boolean exclusive,
                                                               @Cast(value="bool")
                                                               boolean reverse)

getBuilder
```
@ByRef
 @NoException(value=true)
public IBuilder getBuilder()
```
\brief Return the builder from which this INetworkDefinition was created.

Returns:

the builder

See Also:

IBuilder::createNetworkV2

markWeightsRefittable
```
@Cast(value="bool")
 @NoException(value=true)
public boolean markWeightsRefittable(String name)
```
\brief 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.

markWeightsRefittable

@Cast(value="bool")
 @NoException(value=true)
public boolean markWeightsRefittable(@Cast(value="const char*")
                                                                                   BytePointer name)

unmarkWeightsRefittable
```
@Cast(value="bool")
 @NoException(value=true)
public boolean unmarkWeightsRefittable(String name)
```
\brief 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.

unmarkWeightsRefittable

@Cast(value="bool")
 @NoException(value=true)
public boolean unmarkWeightsRefittable(@Cast(value="const char*")
                                                                                     BytePointer name)

areWeightsMarkedRefittable
```
@Cast(value="bool")
 @NoException(value=true)
public boolean areWeightsMarkedRefittable(String name)
```
\brief 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.

areWeightsMarkedRefittable

@Cast(value="bool")
 @NoException(value=true)
public boolean areWeightsMarkedRefittable(@Cast(value="const char*")
                                                                                        BytePointer name)

addSqueeze
```
@NoException(value=true)
public ISqueezeLayer addSqueeze(@ByRef
                                                         ITensor input,
                                                         @ByRef
                                                         ITensor axes)
```
\brief Add a squeeze layer to the network.

Parameters:

input - The input tensor to the layer.

axes - The axes to remove unit dimensions on.

Returns:

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

See Also:

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.

addUnsqueeze

@NoException(value=true)
public IUnsqueezeLayer addUnsqueeze(@ByRef
                                                             ITensor input,
                                                             @ByRef
                                                             ITensor axes)

\brief Add an unsqueeze layer to the network.

Parameters:: input - The input tensor to the layer.; axes - The axes to add unit dimensions.
Returns:: The new Unsqueeze layer, or nullptr if it could not be created
See Also:: 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.

Class INetworkDefinition

Nested Class Summary

Nested classes/interfaces inherited from class org.bytedeco.javacpp.Pointer

Field Summary

Fields inherited from class org.bytedeco.javacpp.Pointer

Constructor Summary

Method Summary

Methods inherited from class org.bytedeco.javacpp.Pointer

Methods inherited from class java.lang.Object

Constructor Detail

INetworkDefinition

INetworkDefinition

INetworkDefinition

Method Detail

position

getPointer

addInput

addInput

markOutput

markDebug

unmarkDebug

isDebugTensor

markUnfusedTensorsAsDebugTensors

unmarkUnfusedTensorsAsDebugTensors

addActivation

addActivation

addLRN

addScale

addScale

addSoftMax

addConcatenation

addConcatenation

addElementWise

addElementWise

addUnary

addUnary

addShuffle

addOneHot

getNbLayers

getLayer

getNbInputs

getInput

getNbOutputs

getOutput

addReduce

addReduce

addTopK

addTopK

addGather

addGatherV2

addGatherV2

addRaggedSoftMax

addMatrixMultiply

addMatrixMultiply

addNonZero

addConstant

addIdentity

addCast

addCast

removeTensor

unmarkOutput

addPluginV2

addPluginV2

addPluginV3

addPluginV3

addSlice

setName

setName

getName

addShape

hasImplicitBatchDimension

getFlags

getFlag

markOutputForShapes

unmarkOutputForShapes

addParametricReLU

addConvolutionNd

addPoolingNd

addPoolingNd

addDeconvolutionNd