Plugin class for user-implemented layers. More...

Inheritance diagram for nvinfer1::IPluginExt:

Collaboration diagram for nvinfer1::IPluginExt:

Public Member Functions
virtual int32_t	getTensorRTVersion () const
	Return the API version with which this plugin was built. More...

virtual bool	supportsFormat (DataType type, PluginFormat format) const =0
	Check format support. More...

virtual void	configureWithFormat (const Dims inputDims, int32_t nbInputs, const Dims outputDims, int32_t nbOutputs, DataType type, PluginFormat format, int32_t maxBatchSize)=0
	Configure the layer. More...

virtual	~IPluginExt ()

virtual int32_t	getNbOutputs () const =0
	Get the number of outputs from the layer. More...

virtual Dims	getOutputDimensions (int32_t index, const Dims *inputs, int32_t nbInputDims)=0
	Get the dimension of an output tensor. More...

virtual int32_t	initialize ()=0
	Initialize the layer for execution. More...

virtual void	terminate ()=0
	Release resources acquired during plugin layer initialization. More...

virtual size_t	getWorkspaceSize (int32_t maxBatchSize) const =0
	Find the workspace size required by the layer. More...

virtual int32_t	enqueue (int32_t batchSize, const void const inputs, void *outputs, void workspace, cudaStream_t stream)=0
	Execute the layer. More...

virtual size_t	getSerializationSize ()=0
	Find the size of the serialization buffer required. More...

virtual void	serialize (void *buffer)=0
	Serialize the layer. More...

Protected Member Functions
void	configure (const Dims , int32_t, const Dims , int32_t, int32_t)
	Derived classes should not implement this. More...

Detailed Description

Plugin class for user-implemented layers.

Plugins are a mechanism for applications to implement custom layers. Each plugin is owned by the application, and its lifetime must span any use of it by TensorRT.

Constructor & Destructor Documentation

◆ ~IPluginExt()

virtual nvinfer1::IPluginExt::~IPluginExt ( )

inlinevirtual

Member Function Documentation

◆ getTensorRTVersion()

virtual int32_t nvinfer1::IPluginExt::getTensorRTVersion ( ) const

inlinevirtual

Return the API version with which this plugin was built.

Do not override this method as it is used by the TensorRT library to maintain backwards-compatibility with plugins.

◆ supportsFormat()

virtual bool nvinfer1::IPluginExt::supportsFormat	(	DataType	type,
		PluginFormat	format
	)		const

pure virtual

Check format support.

Parameters

type	DataType requested.
format	PluginFormat requested.

Returns: true if the plugin supports the type-format combination.

This function is called by the implementations of INetworkDefinition, IBuilder, and ICudaEngine. In particular, it is called when creating an engine and when deserializing an engine.

Warning: DataType:kBOOL not supported.

Implemented in FCPlugin.

◆ configureWithFormat()

virtual void nvinfer1::IPluginExt::configureWithFormat	(	const Dims *	inputDims,
		int32_t	nbInputs,
		const Dims *	outputDims,
		int32_t	nbOutputs,
		DataType	type,
		PluginFormat	format,
		int32_t	maxBatchSize
	)

pure virtual

Configure the layer.

This function is called by the builder prior to initialize(). It provides an opportunity for the layer to make algorithm choices on the basis of its weights, dimensions, and maximum batch size.

Parameters

inputDims	The input tensor dimensions.
nbInputs	The number of inputs.
outputDims	The output tensor dimensions.
nbOutputs	The number of outputs.
type	The data type selected for the engine.
format	The format selected for the engine.
maxBatchSize	The maximum batch size.

The dimensions passed here do not include the outermost batch size (i.e. for 2-D image networks, they will be 3-dimensional CHW dimensions).

Warning: DataType:kBOOL not supported.

◆ configure()

void nvinfer1::IPluginExt::configure	(	const Dims *	,
		int32_t	,
		const Dims *	,
		int32_t	,
		int32_t
	)

inlineprotectedvirtual

Derived classes should not implement this.

In a C++11 API it would be override final.

Implements nvinfer1::IPlugin.

◆ getNbOutputs()

virtual int32_t nvinfer1::IPlugin::getNbOutputs ( ) const

pure virtualinherited

Get the number of outputs from the layer.

Returns: The number of outputs.

This function is called by the implementations of INetworkDefinition and IBuilder. In particular, it is called prior to any call to initialize().

Implemented in FCPlugin, and nmtSample::DebugUtil::DumpTensorPlugin.

Here is the caller graph for this function:

◆ getOutputDimensions()

virtual Dims nvinfer1::IPlugin::getOutputDimensions	(	int32_t	index,
		const Dims *	inputs,
		int32_t	nbInputDims
	)

pure virtualinherited

Get the dimension of an output tensor.

Parameters

index	The index of the output tensor.
inputs	The input tensors.
nbInputDims	The number of input tensors.

This function is called by the implementations of INetworkDefinition and IBuilder. In particular, it is called prior to any call to initialize().

◆ initialize()

virtual int32_t nvinfer1::IPlugin::initialize ( )

pure virtualinherited

Initialize the layer for execution.

This is called when the engine is created.

Returns: 0 for success, else non-zero (which will cause engine termination).

Implemented in FCPlugin, and nmtSample::DebugUtil::DumpTensorPlugin.

◆ terminate()

virtual void nvinfer1::IPlugin::terminate ( )

pure virtualinherited

Release resources acquired during plugin layer initialization.

This is called when the engine is destroyed.

See also: initialize()

Implemented in FCPlugin, and nmtSample::DebugUtil::DumpTensorPlugin.

◆ getWorkspaceSize()

virtual size_t nvinfer1::IPlugin::getWorkspaceSize ( int32_t maxBatchSize ) const

pure virtualinherited

Find the workspace size required by the layer.

This function is called during engine startup, after initialize(). The workspace size returned should be sufficient for any batch size up to the maximum.

Returns: The workspace size.

◆ enqueue()

virtual int32_t nvinfer1::IPlugin::enqueue	(	int32_t	batchSize,
		const void const	inputs,
		void **	outputs,
		void *	workspace,
		cudaStream_t	stream
	)

pure virtualinherited

Execute the layer.

Parameters

batchSize	The number of inputs in the batch.
inputs	The memory for the input tensors.
outputs	The memory for the output tensors.
workspace	Workspace for execution.
stream	The stream in which to execute the kernels.

Returns: 0 for success, else non-zero (which will cause engine termination).

◆ getSerializationSize()

virtual size_t nvinfer1::IPlugin::getSerializationSize ( )

pure virtualinherited

Find the size of the serialization buffer required.

Returns: The size of the serialization buffer.

Implemented in FCPlugin, and nmtSample::DebugUtil::DumpTensorPlugin.

◆ serialize()

virtual void nvinfer1::IPlugin::serialize ( void * buffer )

pure virtualinherited

Serialize the layer.

Parameters

buffer A pointer to a buffer of size at least that returned by getSerializationSize().

See also: getSerializationSize()

Implemented in FCPlugin, and nmtSample::DebugUtil::DumpTensorPlugin.

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

NvInferRuntime.h

Public Member Functions

Protected Member Functions

Detailed Description

Constructor & Destructor Documentation

◆ ~IPluginExt()

Member Function Documentation

◆ getTensorRTVersion()

◆ supportsFormat()

◆ configureWithFormat()

◆ configure()

◆ getNbOutputs()

◆ getOutputDimensions()

◆ initialize()

◆ terminate()

◆ getWorkspaceSize()

◆ enqueue()

◆ getSerializationSize()

◆ serialize()