nvinfer1::plugin::BatchedNMSPlugin Class Reference

Inheritance diagram for nvinfer1::plugin::BatchedNMSPlugin:

Collaboration diagram for nvinfer1::plugin::BatchedNMSPlugin:

Public Member Functions
	BatchedNMSPlugin (NMSParameters param)
	BatchedNMSPlugin (const void *data, size_t length)
	~BatchedNMSPlugin () override=default
const char *	getPluginType () const override
	Return the plugin type. More...
const char *	getPluginVersion () const override
	Return the plugin version. More...
int	getNbOutputs () const override
	Get the number of outputs from the layer. More...
Dims	getOutputDimensions (int index, const Dims *inputs, int nbInputDims) override
bool	supportsFormat (DataType type, PluginFormat format) const override
	Check format support. More...
size_t	getWorkspaceSize (int maxBatchSize) const override
int	enqueue (int batchSize, const void *const *inputs, void **outputs, void *workspace, cudaStream_t stream) override
int	initialize () override
	Initialize the layer for execution. More...
void	terminate () override
	Release resources acquired during plugin layer initialization. More...
size_t	getSerializationSize () const override
	Find the size of the serialization buffer required. More...
void	serialize (void *buffer) const override
	Serialize the layer. More...
void	destroy () override
	Destroy the plugin object. More...
void	setPluginNamespace (const char *libNamespace) override
	Set the namespace that this plugin object belongs to. More...
const char *	getPluginNamespace () const override
	Return the namespace of the plugin object. More...
void	setClipParam (bool clip)
nvinfer1::DataType	getOutputDataType (int index, const nvinfer1::DataType *inputType, int nbInputs) const override
bool	isOutputBroadcastAcrossBatch (int outputIndex, const bool *inputIsBroadcasted, int nbInputs) const override
bool	canBroadcastInputAcrossBatch (int inputIndex) const override
void	configurePlugin (const Dims *inputDims, int nbInputs, const Dims *outputDims, int nbOutputs, const DataType *inputTypes, const DataType *outputTypes, const bool *inputIsBroadcast, const bool *outputIsBroadcast, PluginFormat floatFormat, int maxBatchSize) override
IPluginV2Ext *	clone () const override
	Clone the plugin object. More...
virtual nvinfer1::DataType	getOutputDataType (int32_t index, const nvinfer1::DataType *inputTypes, int32_t nbInputs) const =0
	Return the DataType of the plugin output at the requested index. More...
virtual bool	isOutputBroadcastAcrossBatch (int32_t outputIndex, const bool *inputIsBroadcasted, int32_t nbInputs) const =0
	Return true if output tensor is broadcast across a batch. More...
virtual bool	canBroadcastInputAcrossBatch (int32_t inputIndex) const =0
	Return true if plugin can use input that is broadcast across batch without replication. More...
virtual void	configurePlugin (const Dims *inputDims, int32_t nbInputs, const Dims *outputDims, int32_t nbOutputs, const DataType *inputTypes, const DataType *outputTypes, const bool *inputIsBroadcast, const bool *outputIsBroadcast, PluginFormat floatFormat, int32_t maxBatchSize)=0
	Configure the layer with input and output data types. More...
virtual void	attachToContext (cudnnContext *, cublasContext *, IGpuAllocator *)
	Attach the plugin object to an execution context and grant the plugin the access to some context resource. More...
virtual void	detachFromContext ()
	Detach the plugin object from its execution context. More...
virtual Dims	getOutputDimensions (int32_t index, const Dims *inputs, int32_t nbInputDims)=0
	Get the dimension of an output tensor. 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...

Protected Member Functions
int32_t	getTensorRTVersion () const
	Return the API version with which this plugin was built. More...
void	configureWithFormat (const Dims *, int32_t, const Dims *, int32_t, DataType, PluginFormat, int32_t)
	Derived classes should not implement this. More...

Private Attributes
NMSParameters	param {}
int	boxesSize {}
int	scoresSize {}
int	numPriors {}
std::string	mNamespace
bool	mClipBoxes {}
DataType	mPrecision

Constructor & Destructor Documentation

BatchedNMSPlugin() [1/2]

BatchedNMSPlugin::BatchedNMSPlugin

(

NMSParameters

param

)

Here is the caller graph for this function:

BatchedNMSPlugin() [2/2]

BatchedNMSPlugin::BatchedNMSPlugin	(	const void *	data,
		size_t	length
	)

~BatchedNMSPlugin()

nvinfer1::plugin::BatchedNMSPlugin::~BatchedNMSPlugin ( )

overridedefault

Member Function Documentation

getPluginType()

const char * BatchedNMSPlugin::getPluginType ( ) const

overridevirtual

Return the plugin type.

Should match the plugin name returned by the corresponding plugin creator

See also

IPluginCreator::getPluginName()

Implements nvinfer1::IPluginV2.

getPluginVersion()

const char * BatchedNMSPlugin::getPluginVersion ( ) const

overridevirtual

Return the plugin version.

Should match the plugin version returned by the corresponding plugin creator

See also

IPluginCreator::getPluginVersion()

Implements nvinfer1::IPluginV2.

getNbOutputs()

int BatchedNMSPlugin::getNbOutputs ( ) const

overridevirtual

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().

Implements nvinfer1::IPluginV2.

Here is the caller graph for this function:

getOutputDimensions() [1/2]

Dims BatchedNMSPlugin::getOutputDimensions ( int  index, const Dims *  inputs, int  nbInputDims  )

override

Here is the call graph for this function:

supportsFormat()

bool BatchedNMSPlugin::supportsFormat ( DataType  type, PluginFormat  format  ) const

overridevirtual

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 safe::ICudaEngine/ICudaEngine. In particular, it is called when creating an engine and when deserializing an engine.

Warning

for the format field, the values PluginFormat::kCHW4, PluginFormat::kCHW16, and PluginFormat::kCHW32 will not be passed in, this is to keep backward compatibility with TensorRT 5.x series. Use PluginV2IOExt or PluginV2DynamicExt for other PluginFormats.

DataType:kBOOL not supported.

Implements nvinfer1::IPluginV2.

getWorkspaceSize() [1/2]

size_t BatchedNMSPlugin::getWorkspaceSize ( int  maxBatchSize ) const

override

Here is the call graph for this function:

enqueue() [1/2]

int BatchedNMSPlugin::enqueue ( int  batchSize, const void *const *  inputs, void **  outputs, void *  workspace, cudaStream_t  stream  )

override

initialize()

int BatchedNMSPlugin::initialize ( )

overridevirtual

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).

Implements nvinfer1::IPluginV2.

terminate()

void BatchedNMSPlugin::terminate ( )

overridevirtual

Release resources acquired during plugin layer initialization.

This is called when the engine is destroyed.

See also

initialize()

Implements nvinfer1::IPluginV2.

getSerializationSize()

size_t BatchedNMSPlugin::getSerializationSize ( ) const

overridevirtual

Find the size of the serialization buffer required.

Returns

The size of the serialization buffer.

Implements nvinfer1::IPluginV2.

Here is the caller graph for this function:

serialize()

void BatchedNMSPlugin::serialize ( void *  buffer ) const

overridevirtual

Serialize the layer.

Parameters

buffer

A pointer to a buffer to serialize data. Size of buffer must be equal to value returned by getSerializationSize.

See also

getSerializationSize()

Implements nvinfer1::IPluginV2.

Here is the call graph for this function:

destroy()

void BatchedNMSPlugin::destroy ( )

overridevirtual

Destroy the plugin object.

This will be called when the network, builder or engine is destroyed.

Implements nvinfer1::IPluginV2.

setPluginNamespace()

void BatchedNMSPlugin::setPluginNamespace ( const char *  pluginNamespace )

overridevirtual

Set the namespace that this plugin object belongs to.

Ideally, all plugin objects from the same plugin library should have the same namespace.

Implements nvinfer1::IPluginV2.

getPluginNamespace()

const char * BatchedNMSPlugin::getPluginNamespace ( ) const

overridevirtual

Return the namespace of the plugin object.

Implements nvinfer1::IPluginV2.

setClipParam()

void BatchedNMSPlugin::setClipParam

(

bool

clip

)

getOutputDataType() [1/2]

nvinfer1::DataType BatchedNMSPlugin::getOutputDataType ( int  index, const nvinfer1::DataType *  inputType, int  nbInputs  ) const

override

isOutputBroadcastAcrossBatch() [1/2]

bool BatchedNMSPlugin::isOutputBroadcastAcrossBatch ( int  outputIndex, const bool *  inputIsBroadcasted, int  nbInputs  ) const

override

canBroadcastInputAcrossBatch() [1/2]

bool BatchedNMSPlugin::canBroadcastInputAcrossBatch ( int  inputIndex ) const

override

configurePlugin() [1/2]

void BatchedNMSPlugin::configurePlugin ( const Dims *  inputDims, int  nbInputs, const Dims *  outputDims, int  nbOutputs, const DataType *  inputTypes, const DataType *  outputTypes, const bool *  inputIsBroadcast, const bool *  outputIsBroadcast, nvinfer1::PluginFormat  format, int  maxBatchSize  )

override

clone()

IPluginV2Ext * BatchedNMSPlugin::clone ( ) const

overridevirtual

Clone the plugin object.

This copies over internal plugin parameters as well and returns a new plugin object with these parameters. If the source plugin is pre-configured with configurePlugin(), the returned object should also be pre-configured. The returned object should allow attachToContext() with a new execution context. Cloned plugin objects can share the same per-engine immutable resource (e.g. weights) with the source object (e.g. via ref-counting) to avoid duplication.

Implements nvinfer1::IPluginV2Ext.

Here is the call graph for this function:

getOutputDataType() [2/2]

virtual nvinfer1::DataType nvinfer1::IPluginV2Ext::getOutputDataType ( int32_t  index, const nvinfer1::DataType *  inputTypes, int32_t  nbInputs  ) const

pure virtualinherited

Return the DataType of the plugin output at the requested index.

The default behavior should be to return the type of the first input, or DataType::kFLOAT if the layer has no inputs. The returned data type must have a format that is supported by the plugin.

See also

supportsFormat()

Warning

DataType:kBOOL not supported.

isOutputBroadcastAcrossBatch() [2/2]

virtual bool nvinfer1::IPluginV2Ext::isOutputBroadcastAcrossBatch ( int32_t  outputIndex, const bool *  inputIsBroadcasted, int32_t  nbInputs  ) const

pure virtualinherited

Return true if output tensor is broadcast across a batch.

Parameters

outputIndex	The index of the output
inputIsBroadcasted	The ith element is true if the tensor for the ith input is broadcast across a batch.
nbInputs	The number of inputs

The values in inputIsBroadcasted refer to broadcasting at the semantic level, i.e. are unaffected by whether method canBroadcastInputAcrossBatch requests physical replication of the values.

canBroadcastInputAcrossBatch() [2/2]

virtual bool nvinfer1::IPluginV2Ext::canBroadcastInputAcrossBatch ( int32_t  inputIndex ) const

pure virtualinherited

Return true if plugin can use input that is broadcast across batch without replication.

Parameters

inputIndex

Index of input that could be broadcast.

For each input whose tensor is semantically broadcast across a batch, TensorRT calls this method before calling configurePlugin. If canBroadcastInputAcrossBatch returns true, TensorRT will not replicate the input tensor; i.e., there will be a single copy that the plugin should share across the batch. If it returns false, TensorRT will replicate the input tensor so that it appears like a non-broadcasted tensor.

This method is called only for inputs that can be broadcast.

configurePlugin() [2/2]

virtual void nvinfer1::IPluginV2Ext::configurePlugin ( const Dims *  inputDims, int32_t  nbInputs, const Dims *  outputDims, int32_t  nbOutputs, const DataType *  inputTypes, const DataType *  outputTypes, const bool *  inputIsBroadcast, const bool *  outputIsBroadcast, PluginFormat  floatFormat, int32_t  maxBatchSize  )

pure virtualinherited

Configure the layer with input and output data types.

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, data types 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.
inputTypes	The data types selected for the plugin inputs.
outputTypes	The data types selected for the plugin outputs.
inputIsBroadcast	True for each input that the plugin must broadcast across the batch.
outputIsBroadcast	True for each output that TensorRT will broadcast across the batch.
floatFormat	The format selected for the engine for the floating point inputs/outputs.
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). When inputIsBroadcast or outputIsBroadcast is true, the outermost batch size for that input or output should be treated as if it is one. inputIsBroadcast[i] is true only if the input is semantically broadcast across the batch and canBroadcastInputAcrossBatch(i) returned true. outputIsBroadcast[i] is true only if isOutputBroadcastAcrossBatch(i) returned true.

Warning

for the floatFormat field, the values PluginFormat::kCHW4, PluginFormat::kCHW16, and PluginFormat::kCHW32 will not be passed in, this is to keep backward compatibility with TensorRT 5.x series. Use PluginV2IOExt or PluginV2DynamicExt for other PluginFormats.

attachToContext()

virtual void nvinfer1::IPluginV2Ext::attachToContext ( cudnnContext *  , cublasContext *  , IGpuAllocator *    )

inlinevirtualinherited

Attach the plugin object to an execution context and grant the plugin the access to some context resource.

Parameters

cudnn	The cudnn context handle of the execution context
cublas	The cublas context handle of the execution context
allocator	The allocator used by the execution context

This function is called automatically for each plugin when a new execution context is created. If the plugin needs per-context resource, it can be allocated here. The plugin can also get context-owned CUDNN and CUBLAS context here.

Reimplemented in nvinfer1::plugin::ProposalPlugin, nvinfer1::plugin::CropAndResizePlugin, nvinfer1::plugin::SpecialSlice, nvinfer1::plugin::FlattenConcat, nvinfer1::plugin::ProposalLayer, nvinfer1::plugin::GenerateDetection, nvinfer1::plugin::MultilevelCropAndResize, nvinfer1::plugin::PyramidROIAlign, nvinfer1::plugin::DetectionLayer, nvinfer1::plugin::MultilevelProposeROI, nvinfer1::plugin::Normalize, nvinfer1::plugin::ResizeNearest, nvinfer1::plugin::DetectionOutput, nvinfer1::plugin::RPROIPlugin, nvinfer1::plugin::PriorBox, nvinfer1::plugin::Region, nvinfer1::plugin::Reorg, nvinfer1::plugin::GridAnchorGenerator, nvinfer1::plugin::GroupNormalizationPlugin, nvinfer1::plugin::InstanceNormalizationPlugin, and nvinfer1::plugin::SplitPlugin.

detachFromContext()

virtual void nvinfer1::IPluginV2Ext::detachFromContext ( )

inlinevirtualinherited

Detach the plugin object from its execution context.

This function is called automatically for each plugin when a execution context is destroyed. If the plugin owns per-context resource, it can be released here.

Reimplemented in nvinfer1::plugin::SplitPlugin, nvinfer1::plugin::ProposalPlugin, nvinfer1::plugin::CropAndResizePlugin, nvinfer1::plugin::SpecialSlice, nvinfer1::plugin::ProposalLayer, nvinfer1::plugin::GenerateDetection, nvinfer1::plugin::MultilevelCropAndResize, nvinfer1::plugin::PyramidROIAlign, nvinfer1::plugin::DetectionLayer, nvinfer1::plugin::MultilevelProposeROI, nvinfer1::plugin::Normalize, nvinfer1::plugin::ResizeNearest, nvinfer1::plugin::DetectionOutput, nvinfer1::plugin::RPROIPlugin, nvinfer1::plugin::GroupNormalizationPlugin, nvinfer1::plugin::PriorBox, nvinfer1::plugin::Region, nvinfer1::plugin::InstanceNormalizationPlugin, nvinfer1::plugin::Reorg, nvinfer1::plugin::GridAnchorGenerator, and nvinfer1::plugin::FlattenConcat.

getTensorRTVersion()

int32_t nvinfer1::IPluginV2Ext::getTensorRTVersion ( ) const

inlineprotectedvirtualinherited

Return the API version with which this plugin was built.

The upper byte reserved by TensorRT and is used to differentiate this from IPlguinV2.

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

Reimplemented from nvinfer1::IPluginV2.

configureWithFormat()

void nvinfer1::IPluginV2Ext::configureWithFormat ( const Dims *  , int32_t  , const Dims *  , int32_t  , DataType  , PluginFormat  , int32_t    )

inlineprotectedvirtualinherited

Derived classes should not implement this.

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

Implements nvinfer1::IPluginV2.

getOutputDimensions() [2/2]

virtual Dims nvinfer1::IPluginV2::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().

getWorkspaceSize() [2/2]

virtual size_t nvinfer1::IPluginV2::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() [2/2]

virtual int32_t nvinfer1::IPluginV2::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).

Member Data Documentation

param

NMSParameters nvinfer1::plugin::BatchedNMSPlugin::param {}

private

boxesSize

int nvinfer1::plugin::BatchedNMSPlugin::boxesSize {}

private

scoresSize

int nvinfer1::plugin::BatchedNMSPlugin::scoresSize {}

private

numPriors

int nvinfer1::plugin::BatchedNMSPlugin::numPriors {}

private

mNamespace

std::string nvinfer1::plugin::BatchedNMSPlugin::mNamespace

private

mClipBoxes

bool nvinfer1::plugin::BatchedNMSPlugin::mClipBoxes {}

private

mPrecision

DataType nvinfer1::plugin::BatchedNMSPlugin::mPrecision

private

---

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

• batchedNMSPlugin.h
• batchedNMSPlugin.cpp