Class List

Here are the classes, structs, unions and interfaces with brief descriptions:

[detail level 1234]

▼Nnvneural
►Nrefobj
►CDisableLifecycleLogging	Disables log messages when the object refcount changes
CBaseType	No base types are provided by this trait
CImplements	Helper class for RefObjectBase indicating direct inheritance
►CIndirectlyImplements	Helper class for RefObjectBase indicating interface support without direct inheritance
CBaseType	Provide an empty struct as a recommended base type
CPublicBase	Helper class for RefObjectBase indicating direct inheritance without providing interfaces
CRefObjectBase	Parameterized base class implementing common IRefObject operations
CActivationDesc	Structure describing an activation function (IActivationFunction) for tool interfaces and network builders
CActivationDescHostContainer	"Host-native" container for ActivationDesc structures from other modules
CBackendDeviceIdentifier	Standard implementation of IBackendDeviceIdentifier
CBaseLayer	BaseLayer provides common implementations for most of ILayer
CBaseParamTypeDesc	For implementers, this struct needs to be replicated in each xParamTypeDesc right now
CBasePrototypeLayer	Base class for the CUDA prototype layers shipped with NvNeural
CBufferedLogger	BufferedLogger is a default implementation of IBufferedLogger
CClassRegistry	ClassRegistry is the default implementation for IClassRegistry
CDimensionParamTypeDesc	The DimensionParamTypeDesc further describes a parameter for the plugin and is pointed to from the higher level parameter descriptor ParamDesc
CDynamicPluginLoader	Standard IPluginLoader implementation that uses dynamic linking (dlopen/LoadLibrary) to find NvNeural IPlugin objects
CEnumParamTypeDesc	The EnumParamTypeDesc further describes a parameter for the plugin and is pointed to from the higher level parameter descriptor ParamDesc
CFilesystemWeightsLoader	Standard IWeightsLoader interface that loads weights from the local filesystem
CFloat16	Float16 is a CPU-side implementation of half-precision floating point (aka FP16)
CFusingRule	Defines a fusing rule that can be applied during model loading
CIActivationFunction	IActivationFunction represents a functor that can perform a specific activation function
CIActivationPlugin	IActivationPlugin is an optional interface implemented by IPlugin objects that describes generic (non-fused) activation functions implemented inside the plugin
CIApiVersionQuery	The IApiVersionQuery interface provides this object's compiled-in ApiVersion
CIBackendDeviceIdentifier	IBackendDeviceIdentifier is an opaque identifier for an active GPU
CIBatchNormalizationLayer	IBatchNormalizationLayer is an optional interface implemented by layers that marks them as batch normalization layers
CIBufferedLogger	Buffering loggers store log messages during startup
CIBypassLayer	IBypassLayer is an optional interface that marks a layer as one that can potentially forward its input and be skipped
CIClassRegistry	Common class registry for instantiating objects and collecting plugin-provided descriptors
CIConcatenationLayer	IConcatenationLayer is an optional interface implemented by layers that marks them as concatenation layers
CIConvolutionLayer	IConvolutionLayer is an optional interface that marks a layer as a convolution layer
CICppCodeGenerationLayer	Optional layer interface for C++ code generation
CICppCodeGenerationLayerHost	Tool-supplied interface for C++ code generation
CICudaCompiledFunction	Represents a runtime-compiled function object from ICudaRuntimeCompiler
CICudaMemoryAllocator	Generic interface for CUDA device memory allocation
►CICudaRuntimeCompiler	Represents a runtime compiler that can transform CUDA source code into compiled functions
CCompilationDetails	Params struct describing a compilation request
CIFileImage	Defines file I/O operations for IImage objects
CIFilesystemWeightsLoader	Official "public" interface allowing control of FilesystemWeightsLoader from other modules
CIImage	IImage represents a bitmap image in system memory
CIInnerActivationLayer	IInnerActivationLayer is an optional interface implemented by layers that fuse pairs of operations
CIInputLayer	IInputLayer is an optional interface implemented by layers that marks them as input layers
CILayer	ILayer is the base class for neural network layers
CILayerList	ILayerList represents an immutable collection of ILayer pointers
CILayerPlugin	ILayerPlugin is an optional interface implemented by IPlugin objects that describes layers implemented inside the plugin
CILibraryContext	ILibraryContext is a generic library handle wrapper
CILinearBlendLayer	ILinearBlendLayer is an optional interface implemented by layers that perform linear blend operations
CILogger	Logger interface class
CImage	Standard implementation for IFileImage
CImageDescriptor	Defines one image component to load into a tensor
CINetwork	INetwork is the public interface to Network
CINetworkBackend	INetworkBackend is a runtime-specific interface for CUDA, DirectX, or other system- specific operations needed during inference
CINetworkBackendCuda	INetworkBackend companion interface with CUDA-specific functionality
CINetworkDebugger	INetworkDebugger defines a callback interface for network inference
CINetworkDebuggerList	INetworkDebuggerList represents an immutable collection of INetworkDebugger pointers
CINetworkLayer	INetworkLayer objects are ILayers that encapsulate an externally defined network graph
CINetworkReshapeDebugger	INetworkReshapeDebugger defines a callback interface for reshape operations
CINetworkRuntime	INetworkRuntime is a subset of the basic network interface that is accessible from layer classes during network evaluation
CInterfaceOf	Helper template to aid retrieval of interface IDs
CIOnnxGenerationActivation	ONNX export interface for IActivationFunction
CIOnnxGenerationGraphAttribute	Tool-provided interface representing an AttributeProto in an ONNX graph node
CIOnnxGenerationGraphNode	Tool-provided interface representing a NodeProto in an ONNX graph
CIOnnxGenerationHost	Tool-provided interface for creating ONNX model graphs in an ABI-stable fashion
CIOnnxGenerationLayer	ONNX export interface for ILayer
CIParameterNode	Represents a serialized parameter block in a model definition
CIPlugin	IPlugin is the general factory interface used by NvNeural's plugin system
CIPluginLoader	Platform-agnostic plugin loader interface
CIPoolingLayer	IPoolingLayer is an optional interface implemented by pooling layers
CIPrototypeLayer	IPrototypeLayer is an optional interface that marks a layer as a prototype layer
CIPrototypePlugin	IPrototypePlugin is an optional interface implemented by IPlugin objects that describes generic prototype layers implemented inside the plugin
CIRefObject	Base class for all objects, similar to COM's IUnknown
CIResourceAggregator	Key-value store for creating IResourceDictionary objects
CIResourceDictionary	Key-value store for binary data such as precompiled kernels
CIRuntimeOptionsHost	IRuntimeOptionsHost is an interface that provides runtime option communication from the layer to the host
CIRuntimeOptionsLayer	IRuntimeOptionsLayer is an optional interface that marks a layer as one that uses runtime options
CIShuffleLayer	IShuffleLayer is a common interface implemented by space-to-depth and depth-to-space layers
CIStandardInputLayer	Defines a standard input layer
CIStatusMessageLayer	IStatusMessageLayer is an optional interface intended for ILayer to provide status messages
CIStringList	IStringList represents an immutable collection of strings
CIWeightsData	IWeightsData represents a binary buffer provided by IWeightsLoader
CIWeightsLoader	IWeightsLoader is an interface that provides weights to layers
CLayerDesc	This structure describes an ILayer for tools and network builders
CLayerDescHostContainer	"Host-native" container for LayerDesc structures from other modules
CLayerInputDesc	Describes a single input terminal for a layer. LayerDesc objects contain arrays of this structure
CLayerList	Simple implementation of ILayerList
CLayerListIterator	Iterator class to enable range-based for loops and similar constructs across any ILayerList
CNetworkDebuggerList	Standard implementation of INetworkDebuggerList wrapping a vector<RefPtr<INetworkDebugger>>
CParamDesc	ParamDesc describes a parameter for the plugin, giving it a name, default value, type, and, if needed, a pointer to greater detail
CPrototypeDesc	This structure represent a prototype layer version (backend, tensor format and kernel type), it should be passed to ClassRegistry using registerPrototype
CPrototypeDescHostContainer	This class is the host side container for the PrototypeDesc structure (see CoreTypes.h)
►CRefPtr	Intrusive pointer using IRefObject's reference counting system
CGenericOutputWrapper	Version of OutputWrapper that presents a generic IRefObject** instead
COutputWrapper	Details type that allows version-safe use of out-pointer parameters without converting through an intermediate raw pointer variable or mismatching fromPointer/fromPointerNoAddRef
CScopedMemoryAllocation	ScopedMemoryAllocation is a helper function for allocating memory blocks from the backend while adding the security and ease of use of the RAII idiom
CSimpleLogger	SimpleLogger is a basic ILogger implementation that displays to stdout
CStringList	Standard implementation of IStringList that can represent a vector<string> type
CStringMapParameterNode	IParameterNode implementation designed to demonstrate loading parameters outside the standard nv-neural-model XML file format
CStringParamTypeDesc	The StringParamTypeDesc further describes a parameter for the plugin and is pointed to from the higher level parameter descriptor ParamDesc
CTensorDimension	TensorDimension describes the dimensions of a four-dimensional image tensor
CTensorFormat	TensorFormat describes a specific tensor shape (element type and layout)
CWeightsData	Standard IWeightsData implementation containing a vector of values in CPU memory
CXmlNetworkBuilder	XML-based network builder
CXmlParameterNode	IParameterNode implementation wrapping a pugi::xml_node
CZlibResourceAggregator	Resource aggregator that compresses payloads using Zlib
CZlibResourceDictionary	Resource dictionary that decompresses payloads using Zlib
▼Nstd	STL namespace
Chash< nvneural::NetworkBackendId >	Specialization of std::hash for strongly typed network backends
Chash< nvneural::RefPtr< TObject > >	Specialize std::hash for RefPtr objects