nvonnxparser Namespace Reference

The TensorRT ONNX parser API namespace. More...

Classes
class	IOnnxConfig
	Configuration Manager Class. More...
class	IParser
	an object for parsing ONNX models into a TensorRT network definition More...
class	IParserError
	an object containing information about an error More...

Typedefs
using	OnnxParserFlags = uint32_t
	Represents one or more OnnxParserFlag values using binary OR operations, e.g., 1U << OnnxParserFlag::kNATIVE_INSTANCENORM. More...

Enumerations
enum class	ErrorCode : int {   kSUCCESS = 0 , kINTERNAL_ERROR = 1 , kMEM_ALLOC_FAILED = 2 , kMODEL_DESERIALIZE_FAILED = 3 ,   kINVALID_VALUE = 4 , kINVALID_GRAPH = 5 , kINVALID_NODE = 6 , kUNSUPPORTED_GRAPH = 7 ,   kUNSUPPORTED_NODE = 8 }
	The type of error that the parser may return. More...
enum class	OnnxParserFlag : int32_t { kNATIVE_INSTANCENORM = 0 }

Functions
IOnnxConfig *	createONNXConfig ()
template<typename T >
constexpr int32_t	EnumMax ()
template<>
constexpr int32_t	EnumMax< ErrorCode > ()
template<>
constexpr int32_t	EnumMax< OnnxParserFlag > ()

Detailed Description

The TensorRT ONNX parser API namespace.

Typedef Documentation

OnnxParserFlags

using nvonnxparser::OnnxParserFlags = typedef uint32_t

Represents one or more OnnxParserFlag values using binary OR operations, e.g., 1U << OnnxParserFlag::kNATIVE_INSTANCENORM.

See also

IParser::setFlags() and IParser::getFlags()

Enumeration Type Documentation

ErrorCode

enum class nvonnxparser::ErrorCode : int

strong

The type of error that the parser may return.

Enumerator
kSUCCESS
kINTERNAL_ERROR
kMEM_ALLOC_FAILED
kMODEL_DESERIALIZE_FAILED
kINVALID_VALUE
kINVALID_GRAPH
kINVALID_NODE
kUNSUPPORTED_GRAPH
kUNSUPPORTED_NODE

OnnxParserFlag

enum class nvonnxparser::OnnxParserFlag : int32_t

strong

Enumerator

kNATIVE_INSTANCENORM

Parse the ONNX model into the INetworkDefinition with the intention of using TensorRT's native layer implementation over the plugin implementation for InstanceNormalization nodes. This flag is planned to be deprecated in TensorRT 8.7 and removed in TensorRT 9.0. This flag is required when building version-compatible or hardware-compatible engines. There may be performance degradations when this flag is enabled.

Function Documentation

createONNXConfig()

IOnnxConfig * nvonnxparser::createONNXConfig

(

)

EnumMax()

template<typename T >

constexpr int32_t nvonnxparser::EnumMax ( )

inlineconstexpr

EnumMax< ErrorCode >()

template<>

constexpr int32_t nvonnxparser::EnumMax< ErrorCode > ( )

inlineconstexpr

Maximum number of flags in the ErrorCode enum.

See also

ErrorCode

EnumMax< OnnxParserFlag >()

template<>

constexpr int32_t nvonnxparser::EnumMax< OnnxParserFlag > ( )

inlineconstexpr

Maximum number of flags in the OnnxParserFlag enum.

See also

OnnxParserFlag