org.bytedeco.tensorrt.nvonnxparser

Class IParser

java.lang.Object

org.bytedeco.javacpp.Pointer

org.bytedeco.tensorrt.nvonnxparser.IParser

All Implemented Interfaces:

AutoCloseable

@Namespace(value="nvonnxparser")
 @Properties(inherit=nvonnxparser.class)
public class IParser
extends Pointer

\class IParser \brief an object for parsing ONNX models into a TensorRT network definition \warning If the ONNX model has a graph output with the same name as a graph input, the output will be renamed by prepending "__". \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
IParser(Pointer p) Pointer cast constructor.

Method Summary

Modifier and Type	Method and Description
void	clearErrors() \brief Clear errors from prior calls to \p parse
void	clearFlag(int onnxParserFlag)
void	clearFlag(nvonnxparser.OnnxParserFlag onnxParserFlag) \brief clear a parser flag.
IParserError	getError(int index) \brief Get an error that occurred during prior calls to \p parse
boolean	getFlag(int onnxParserFlag)
boolean	getFlag(nvonnxparser.OnnxParserFlag onnxParserFlag) \brief Returns true if the parser flag is set
int	getFlags() \brief Get the parser flags.
ITensor	getLayerOutputTensor(BytePointer name, long i)
ITensor	getLayerOutputTensor(String name, long i) \brief Return the i-th output ITensor object for the ONNX layer "name".
int	getNbErrors() \brief Get the number of errors that occurred during prior calls to \p parse
long	getNbSubgraphs() \brief Get the number of subgraphs.
long[]	getSubgraphNodes(long index, long[] subgraphLength)
LongBuffer	getSubgraphNodes(long index, LongBuffer subgraphLength)
LongPointer	getSubgraphNodes(long index, LongPointer subgraphLength) \brief Get the nodes of the specified subgraph.
PointerPointer	getUsedVCPluginLibraries(long[] nbPluginLibs) \brief Query the plugin libraries needed to implement operations used by the parser in a version-compatible engine.
boolean	isSubgraphSupported(long index) \brief Returns whether the subgraph is supported.
boolean	parse(Pointer serialized_onnx_model, long serialized_onnx_model_size)
boolean	parse(Pointer serialized_onnx_model, long serialized_onnx_model_size, BytePointer model_path)
boolean	parse(Pointer serialized_onnx_model, long serialized_onnx_model_size, String model_path) \brief Parse a serialized ONNX model into the TensorRT network.
boolean	parseFromFile(BytePointer onnxModelFile, int verbosity)
boolean	parseFromFile(String onnxModelFile, int verbosity) \brief Parse an onnx model file, which can be a binary protobuf or a text onnx model calls parse method inside.
boolean	parseWithWeightDescriptors(Pointer serialized_onnx_model, long serialized_onnx_model_size) \brief Parse a serialized ONNX model into the TensorRT network with consideration of user provided weights
void	setFlag(int onnxParserFlag)
void	setFlag(nvonnxparser.OnnxParserFlag onnxParserFlag) \brief Set a single parser flag.
void	setFlags(int onnxParserFlags) \brief Set the parser flags.
boolean	supportsModel(Pointer serialized_onnx_model, long serialized_onnx_model_size, SubGraphCollection_t sub_graph_collection) Deprecated.
boolean	supportsModel(Pointer serialized_onnx_model, long serialized_onnx_model_size, SubGraphCollection_t sub_graph_collection, BytePointer model_path) Deprecated.
boolean	supportsModel(Pointer serialized_onnx_model, long serialized_onnx_model_size, SubGraphCollection_t sub_graph_collection, String model_path) Deprecated.
boolean	supportsModelV2(Pointer serializedOnnxModel, long serializedOnnxModelSize)
boolean	supportsModelV2(Pointer serializedOnnxModel, long serializedOnnxModelSize, BytePointer modelPath)
boolean	supportsModelV2(Pointer serializedOnnxModel, long serializedOnnxModelSize, String modelPath) \brief Check whether TensorRT supports a particular ONNX model.
boolean	supportsOperator(BytePointer op_name)
boolean	supportsOperator(String op_name) \brief Returns whether the specified operator may be supported by the parser.

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, getPointer, hashCode, interruptDeallocatorThread, isNull, isNull, limit, limit, malloc, maxBytes, maxPhysicalBytes, memchr, memcmp, memcpy, memmove, memset, offsetAddress, offsetof, offsetof, parseBytes, physicalBytes, physicalBytesInaccurate, position, 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

IParser

public IParser(Pointer p)

Pointer cast constructor. Invokes Pointer(Pointer).

Method Detail

parse

@Cast(value="bool")
 @NoException(value=true)
public boolean parse(@Const
                                                                   Pointer serialized_onnx_model,
                                                                   @Cast(value="size_t")
                                                                   long serialized_onnx_model_size,
                                                                   String model_path)

\brief Parse a serialized ONNX model into the TensorRT network. This method has very limited diagnostics. If parsing the serialized model fails for any reason (e.g. unsupported IR version, unsupported opset, etc.) it the user responsibility to intercept and report the error. To obtain a better diagnostic, use the parseFromFile method below.

Parameters:

serialized_onnx_model - Pointer to the serialized ONNX model

serialized_onnx_model_size - Size of the serialized ONNX model in bytes

model_path - Absolute path to the model file for loading external weights if required

Returns:

true if the model was parsed successfully

See Also:

getError()

parse

@Cast(value="bool")
 @NoException(value=true)
public boolean parse(@Const
                                                                   Pointer serialized_onnx_model,
                                                                   @Cast(value="size_t")
                                                                   long serialized_onnx_model_size)

parse

@Cast(value="bool")
 @NoException(value=true)
public boolean parse(@Const
                                                                   Pointer serialized_onnx_model,
                                                                   @Cast(value="size_t")
                                                                   long serialized_onnx_model_size,
                                                                   @Cast(value="const char*")
                                                                   BytePointer model_path)

parseFromFile

@Cast(value="bool")
 @NoException(value=true)
public boolean parseFromFile(String onnxModelFile,
                                                                           int verbosity)

\brief Parse an onnx model file, which can be a binary protobuf or a text onnx model calls parse method inside.

Parameters:

onnxModelFile - name

verbosity - Level

Returns:

true if the model was parsed successfully

parseFromFile

@Cast(value="bool")
 @NoException(value=true)
public boolean parseFromFile(@Cast(value="const char*")
                                                                           BytePointer onnxModelFile,
                                                                           int verbosity)

supportsModel

@Cast(value="bool")
 @Deprecated
 @NoException(value=true)
public boolean supportsModel(@Const
                                                                                        Pointer serialized_onnx_model,
                                                                                        @Cast(value="size_t")
                                                                                        long serialized_onnx_model_size,
                                                                                        @ByRef
                                                                                        SubGraphCollection_t sub_graph_collection,
                                                                                        String model_path)

Deprecated.

[DEPRECATED] Deprecated in TensorRT 10.1. See supportsModelV2. \brief Check whether TensorRT supports a particular ONNX model. If the function returns True, one can proceed to engine building without having to call \p parse or \p parseFromFile.

Parameters:

serialized_onnx_model - Pointer to the serialized ONNX model

serialized_onnx_model_size - Size of the serialized ONNX model in bytes

sub_graph_collection - Container to hold supported subgraphs

model_path - Absolute path to the model file for loading external weights if required

Returns:

true if the model is supported

supportsModel

@Cast(value="bool")
 @Deprecated
 @NoException(value=true)
public boolean supportsModel(@Const
                                                                                        Pointer serialized_onnx_model,
                                                                                        @Cast(value="size_t")
                                                                                        long serialized_onnx_model_size,
                                                                                        @ByRef
                                                                                        SubGraphCollection_t sub_graph_collection)

Deprecated.

supportsModel

@Cast(value="bool")
 @Deprecated
 @NoException(value=true)
public boolean supportsModel(@Const
                                                                                        Pointer serialized_onnx_model,
                                                                                        @Cast(value="size_t")
                                                                                        long serialized_onnx_model_size,
                                                                                        @ByRef
                                                                                        SubGraphCollection_t sub_graph_collection,
                                                                                        @Cast(value="const char*")
                                                                                        BytePointer model_path)

Deprecated.

parseWithWeightDescriptors

@Cast(value="bool")
 @NoException(value=true)
public boolean parseWithWeightDescriptors(@Const
                                                                                        Pointer serialized_onnx_model,
                                                                                        @Cast(value="size_t")
                                                                                        long serialized_onnx_model_size)

\brief Parse a serialized ONNX model into the TensorRT network with consideration of user provided weights

Parameters:

serialized_onnx_model - Pointer to the serialized ONNX model

serialized_onnx_model_size - Size of the serialized ONNX model in bytes

Returns:

true if the model was parsed successfully

See Also:

getError()

supportsOperator

@Cast(value="bool")
 @NoException(value=true)
public boolean supportsOperator(String op_name)

\brief Returns whether the specified operator may be supported by the parser. Note that a result of true does not guarantee that the operator will be supported in all cases (i.e., this function may return false-positives).

Parameters:

op_name - The name of the ONNX operator to check for support

supportsOperator

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

getNbErrors

@NoException(value=true)
public int getNbErrors()

\brief Get the number of errors that occurred during prior calls to \p parse

See Also:

clearErrors() IParserError

getError

@Const
 @NoException(value=true)
public IParserError getError(int index)

\brief Get an error that occurred during prior calls to \p parse

See Also:

clearErrors() IParserError

clearErrors

@NoException(value=true)
public void clearErrors()

\brief Clear errors from prior calls to \p parse

See Also:

getError() IParserError

getUsedVCPluginLibraries

@Cast(value="const char**")
 @NoException(value=true)
public PointerPointer getUsedVCPluginLibraries(@Cast(value="int64_t*") @ByRef
                                                                                                     long[] nbPluginLibs)

\brief Query the plugin libraries needed to implement operations used by the parser in a version-compatible engine. This provides a list of plugin libraries on the filesystem needed to implement operations in the parsed network. If you are building a version-compatible engine using this network, provide this list to IBuilderConfig::setPluginsToSerialize to serialize these plugins along with the version-compatible engine, or, if you want to ship these plugin libraries externally to the engine, ensure that IPluginRegistry::loadLibrary is used to load these libraries in the appropriate runtime before deserializing the corresponding engine.

Parameters:

nbPluginLibs - [out] Returns the number of plugin libraries in the array, or -1 if there was an error.

Returns:

Array of nbPluginLibs C-strings describing plugin library paths on the filesystem if nbPluginLibs > 0, or nullptr otherwise. This array is owned by the IParser, and the pointers in the array are only valid until the next call to parse(), supportsModel(), parseFromFile(), or parseWithWeightDescriptors().

setFlags

@NoException(value=true)
public void setFlags(@Cast(value="nvonnxparser::OnnxParserFlags")
                                              int onnxParserFlags)

\brief Set the parser flags. The flags are listed in the OnnxParserFlag enum.

Parameters:

OnnxParserFlags - The flags used when parsing an ONNX model. \note This function will override the previous set flags, rather than bitwise ORing the new flag.

See Also:

getFlags()

getFlags

@Cast(value="nvonnxparser::OnnxParserFlags")
 @NoException(value=true)
public int getFlags()

\brief Get the parser flags. Defaults to 0.

Returns:

The parser flags as a bitmask.

See Also:

setFlags()

clearFlag

@NoException(value=true)
public void clearFlag(nvonnxparser.OnnxParserFlag onnxParserFlag)

\brief clear a parser flag. clears the parser flag from the enabled flags.

See Also:

setFlags()

clearFlag

@NoException(value=true)
public void clearFlag(@Cast(value="nvonnxparser::OnnxParserFlag")
                                               int onnxParserFlag)

setFlag

@NoException(value=true)
public void setFlag(nvonnxparser.OnnxParserFlag onnxParserFlag)

\brief Set a single parser flag. Add the input parser flag to the already enabled flags.

See Also:

setFlags()

setFlag

@NoException(value=true)
public void setFlag(@Cast(value="nvonnxparser::OnnxParserFlag")
                                             int onnxParserFlag)

getFlag

@Cast(value="bool")
 @NoException(value=true)
public boolean getFlag(nvonnxparser.OnnxParserFlag onnxParserFlag)

\brief Returns true if the parser flag is set

Returns:

True if flag is set, false if unset.

See Also:

getFlags()

getFlag

@Cast(value="bool")
 @NoException(value=true)
public boolean getFlag(@Cast(value="nvonnxparser::OnnxParserFlag")
                                                                     int onnxParserFlag)

getLayerOutputTensor

@Const
 @NoException(value=true)
public ITensor getLayerOutputTensor(String name,
                                                                     @Cast(value="int64_t")
                                                                     long i)

\brief Return the i-th output ITensor object for the ONNX layer "name". Return the i-th output ITensor object for the ONNX layer "name". If "name" is not found or i is out of range, return nullptr. In the case of multiple nodes sharing the same name this function will return the output tensors of the first instance of the node in the ONNX graph.

Parameters:

name - The name of the ONNX layer.

i - The index of the output. i must be in range [0, layer.num_outputs).

getLayerOutputTensor

@Const
 @NoException(value=true)
public ITensor getLayerOutputTensor(@Cast(value="const char*")
                                                                     BytePointer name,
                                                                     @Cast(value="int64_t")
                                                                     long i)

supportsModelV2

@Cast(value="bool")
 @NoException(value=true)
public boolean supportsModelV2(@Const
                                                                             Pointer serializedOnnxModel,
                                                                             @Cast(value="size_t")
                                                                             long serializedOnnxModelSize,
                                                                             String modelPath)

\brief Check whether TensorRT supports a particular ONNX model. If the function returns True, one can proceed to engine building without having to call \p parse or \p parseFromFile. Results can be queried through \p getNbSubgraphs, \p isSubgraphSupported, \p getSubgraphNodes.

Parameters:

serializedOnnxModel - Pointer to the serialized ONNX model

serializedOnnxModelSize - Size of the serialized ONNX model in bytes

modelPath - Absolute path to the model file for loading external weights if required

Returns:

true if the model is supported

supportsModelV2

@Cast(value="bool")
 @NoException(value=true)
public boolean supportsModelV2(@Const
                                                                             Pointer serializedOnnxModel,
                                                                             @Cast(value="size_t")
                                                                             long serializedOnnxModelSize)

supportsModelV2

@Cast(value="bool")
 @NoException(value=true)
public boolean supportsModelV2(@Const
                                                                             Pointer serializedOnnxModel,
                                                                             @Cast(value="size_t")
                                                                             long serializedOnnxModelSize,
                                                                             @Cast(value="const char*")
                                                                             BytePointer modelPath)

getNbSubgraphs

@Cast(value="int64_t")
 @NoException(value=true)
public long getNbSubgraphs()

\brief Get the number of subgraphs. Calling this function before calling \p supportsModelV2 results in undefined behavior.

Returns:

Number of subgraphs.

isSubgraphSupported

@Cast(value="bool")
 @NoException(value=true)
public boolean isSubgraphSupported(@Cast(value="const int64_t")
                                                                                 long index)

\brief Returns whether the subgraph is supported. Calling this function before calling \p supportsModelV2 results in undefined behavior.

Parameters:

index - Index of the subgraph.

Returns:

Whether the subgraph is supported.

getSubgraphNodes

@Cast(value="int64_t*")
 @NoException(value=true)
public LongPointer getSubgraphNodes(@Cast(value="const int64_t")
                                                                                      long index,
                                                                                      @Cast(value="int64_t*") @ByRef
                                                                                      LongPointer subgraphLength)

\brief Get the nodes of the specified subgraph. Calling this function before calling \p supportsModelV2 results in undefined behavior.

Parameters:

index - Index of the subgraph.

subgraphLength - Returns the length of the subgraph as reference.

Returns:

Pointer to the subgraph nodes array. This pointer is owned by the Parser.

getSubgraphNodes

@Cast(value="int64_t*")
 @NoException(value=true)
public LongBuffer getSubgraphNodes(@Cast(value="const int64_t")
                                                                                     long index,
                                                                                     @Cast(value="int64_t*") @ByRef
                                                                                     LongBuffer subgraphLength)

getSubgraphNodes

@Cast(value="int64_t*")
 @NoException(value=true)
public long[] getSubgraphNodes(@Cast(value="const int64_t")
                                                                                 long index,
                                                                                 @Cast(value="int64_t*") @ByRef
                                                                                 long[] subgraphLength)