| Cnvneural::ActivationDesc | Structure describing an activation function (IActivationFunction) for tool interfaces and network builders |
| Cnvneural::ActivationDescHostContainer | "Host-native" container for ActivationDesc structures from other modules |
| Cnvneural::BaseParamTypeDesc | For implementers, this struct needs to be replicated in each xParamTypeDesc right now |
| Cnvneural::refobj::DisableLifecycleLogging::BaseType | No base types are provided by this trait |
| Cnvneural::refobj::IndirectlyImplements< TInterface, TIntermediateType >::BaseType | Provide an empty struct as a recommended base type |
| ►CParameterList::BaseType | |
| ►Cnvneural::refobj::RefObjectBase< refobj::Implements< IStringList > > | |
| Cnvneural::StringList | Standard implementation of IStringList that can represent a vector<string> type |
| ►Cnvneural::refobj::RefObjectBase< refobj::Implements< IWeightsData > > | |
| Cnvneural::WeightsData< TVectorData > | Standard IWeightsData implementation containing a vector of values in CPU memory |
| Cnvneural::refobj::RefObjectBase< Implements< IPlugin >, Implements< IApiVersionQuery >, Implements< ILayerPlugin >, Implements< IActivationPlugin >, Implements< IPrototypePlugin > > | |
| ►Cnvneural::refobj::RefObjectBase< refobj::Implements< ILayer >, refobj::Implements< IPrototypeLayer >, refobj::Implements< ICppCodeGenerationLayer > > | |
| Cnvneural::BasePrototypeLayer | Base class for the CUDA prototype layers shipped with NvNeural |
| ►Cnvneural::refobj::RefObjectBase< refobj::Implements< IClassRegistry > > | |
| Cnvneural::ClassRegistry | ClassRegistry is the default implementation for IClassRegistry |
| ►Cnvneural::refobj::RefObjectBase< refobj::Implements< IBackendDeviceIdentifier > > | |
| Cnvneural::BackendDeviceIdentifier | Standard implementation of IBackendDeviceIdentifier |
| ►Cnvneural::refobj::RefObjectBase< refobj::Implements< IParameterNode > > | |
| Cnvneural::StringMapParameterNode | IParameterNode implementation designed to demonstrate loading parameters outside the standard nv-neural-model XML file format |
| Cnvneural::XmlParameterNode | IParameterNode implementation wrapping a pugi::xml_node |
| Cnvneural::refobj::RefObjectBase< refobj::Implements< BaseLayer >, refobj::IndirectlyImplements< ILayer, BaseLayer >, refobj::Implements< INetworkLayer >, refobj::Implements< IRuntimeOptionsLayer > > | |
| ►Cnvneural::refobj::RefObjectBase< nvneural::refobj::Implements< nvneural::ILogger > > | |
| Cnvneural::SimpleLogger | SimpleLogger is a basic ILogger implementation that displays to stdout |
| ►Cnvneural::refobj::RefObjectBase< refobj::Implements< INetworkDebuggerList > > | |
| Cnvneural::NetworkDebuggerList | Standard implementation of INetworkDebuggerList wrapping a vector<RefPtr<INetworkDebugger>> |
| ►Cnvneural::refobj::RefObjectBase< refobj::Implements< IResourceDictionary > > | |
| Cnvneural::ZlibResourceDictionary | Resource dictionary that decompresses payloads using Zlib |
| ►Cnvneural::refobj::RefObjectBase< refobj::Implements< IPluginLoader > > | |
| Cnvneural::DynamicPluginLoader | Standard IPluginLoader implementation that uses dynamic linking (dlopen/LoadLibrary) to find NvNeural IPlugin objects |
| ►Cnvneural::refobj::RefObjectBase< refobj::Implements< IResourceAggregator > > | |
| Cnvneural::ZlibResourceAggregator | Resource aggregator that compresses payloads using Zlib |
| ►Cnvneural::refobj::RefObjectBase< refobj::Implements< IFilesystemWeightsLoader >, refobj::Implements< IWeightsLoader > > | |
| Cnvneural::FilesystemWeightsLoader | Standard IWeightsLoader interface that loads weights from the local filesystem |
| ►Cnvneural::refobj::RefObjectBase< refobj::Implements< ILayerList > > | |
| Cnvneural::LayerList | Simple implementation of ILayerList |
| ►Cnvneural::refobj::RefObjectBase< nvneural::refobj::Implements< nvneural::IFileImage >, nvneural::refobj::Implements< nvneural::IImage > > | |
| Cnvneural::Image | Standard implementation for IFileImage |
| Cnvneural::refobj::RefObjectBase< ParameterList > | Parameterized base class implementing common IRefObject operations |
| Cnvneural::ICudaRuntimeCompiler::CompilationDetails | Params struct describing a compilation request |
| Cnvneural::DimensionParamTypeDesc | The DimensionParamTypeDesc further describes a parameter for the plugin and is pointed to from the higher level parameter descriptor ParamDesc |
| Cnvneural::refobj::DisableLifecycleLogging | Disables log messages when the object refcount changes |
| Cnvneural::EnumParamTypeDesc | The EnumParamTypeDesc further describes a parameter for the plugin and is pointed to from the higher level parameter descriptor ParamDesc |
| Cnvneural::Float16 | Float16 is a CPU-side implementation of half-precision floating point (aka FP16) |
| Cnvneural::FusingRule | Defines a fusing rule that can be applied during model loading |
| Cnvneural::RefPtr< TObject >::GenericOutputWrapper | Version of OutputWrapper that presents a generic IRefObject** instead |
| Cstd::hash< nvneural::NetworkBackendId > | Specialization of std::hash for strongly typed network backends |
| Cstd::hash< nvneural::RefPtr< TObject > > | Specialize std::hash for RefPtr objects |
| Cnvneural::ImageDescriptor | Defines one image component to load into a tensor |
| Cnvneural::refobj::Implements< TInterface > | Helper class for RefObjectBase indicating direct inheritance |
| Cnvneural::refobj::IndirectlyImplements< TInterface, TIntermediateType > | Helper class for RefObjectBase indicating interface support without direct inheritance |
| Cnvneural::InterfaceOf< TInterface > | Helper template to aid retrieval of interface IDs |
| ►Cnvneural::IRefObject | Base class for all objects, similar to COM's IUnknown |
| Cnvneural::IActivationFunction | IActivationFunction represents a functor that can perform a specific activation function |
| Cnvneural::IActivationPlugin | IActivationPlugin is an optional interface implemented by IPlugin objects that describes generic (non-fused) activation functions implemented inside the plugin |
| Cnvneural::IApiVersionQuery | The IApiVersionQuery interface provides this object's compiled-in ApiVersion |
| Cnvneural::IBackendDeviceIdentifier | IBackendDeviceIdentifier is an opaque identifier for an active GPU |
| Cnvneural::IBatchNormalizationLayer | IBatchNormalizationLayer is an optional interface implemented by layers that marks them as batch normalization layers |
| ►Cnvneural::IBufferedLogger | Buffering loggers store log messages during startup |
| Cnvneural::BufferedLogger | BufferedLogger is a default implementation of IBufferedLogger |
| Cnvneural::IBypassLayer | IBypassLayer is an optional interface that marks a layer as one that can potentially forward its input and be skipped |
| Cnvneural::IClassRegistry | Common class registry for instantiating objects and collecting plugin-provided descriptors |
| ►Cnvneural::IConcatenationLayer | IConcatenationLayer is an optional interface implemented by layers that marks them as concatenation layers |
| Cnvneural::IConcatenationLayer2 | IConcatenationLayer2 is an optional interface implemented by layers that marks them as concatenation layers |
| ►Cnvneural::IConvolutionLayer | IConvolutionLayer is an optional interface that marks a layer as a convolution layer |
| Cnvneural::IConvolutionLayer2 | IConvolutionLayer2 is an optional interface that marks a layer as a convolution layer |
| Cnvneural::ICppCodeGenerationLayer | Optional layer interface for C++ code generation |
| Cnvneural::ICppCodeGenerationLayerHost | Tool-supplied interface for C++ code generation |
| Cnvneural::ICudaCompiledFunction | Represents a runtime-compiled function object from ICudaRuntimeCompiler |
| Cnvneural::ICudaInputLayer | Defines an input layer that accepts data from CUDA device memory |
| ►Cnvneural::ICudaMemoryAllocator | Generic interface for CUDA device memory allocation |
| Cnvneural::ICudaMemoryAllocator2 | Generic interface for CUDA device memory allocation |
| Cnvneural::ICudaRuntimeCompiler | Represents a runtime compiler that can transform CUDA source code into compiled functions |
| Cnvneural::IFileImage | Defines file I/O operations for IImage objects |
| Cnvneural::IFilesystemWeightsLoader | Official "public" interface allowing control of FilesystemWeightsLoader from other modules |
| Cnvneural::IImage | IImage represents a bitmap image in system memory |
| Cnvneural::IInnerActivationLayer | IInnerActivationLayer is an optional interface implemented by layers that fuse pairs of operations |
| Cnvneural::IInputLayer | IInputLayer is an optional interface implemented by layers that marks them as input layers |
| ►Cnvneural::ILayer | ILayer is the base class for neural network layers |
| Cnvneural::BaseLayer | BaseLayer provides common implementations for most of ILayer |
| Cnvneural::ILayerList | ILayerList represents an immutable collection of ILayer pointers |
| Cnvneural::ILayerPlugin | ILayerPlugin is an optional interface implemented by IPlugin objects that describes layers implemented inside the plugin |
| Cnvneural::ILibraryContext | ILibraryContext is a generic library handle wrapper |
| Cnvneural::ILinearBlendLayer | ILinearBlendLayer is an optional interface implemented by layers that perform linear blend operations |
| ►Cnvneural::ILogger | Logger interface class |
| Cnvneural::BufferedLogger | BufferedLogger is a default implementation of IBufferedLogger |
| ►Cnvneural::INetworkBackend | INetworkBackend is a runtime-specific interface for CUDA, DirectX, or other system- specific operations needed during inference |
| Cnvneural::INetworkBackend2 | INetworkBackend2 is a revision of INetworkBackend |
| Cnvneural::INetworkBackendCuda | INetworkBackend companion interface with CUDA-specific functionality |
| Cnvneural::INetworkDebugger | INetworkDebugger defines a callback interface for network inference |
| Cnvneural::INetworkDebuggerList | INetworkDebuggerList represents an immutable collection of INetworkDebugger pointers |
| Cnvneural::INetworkLayer | INetworkLayer objects are ILayers that encapsulate an externally defined network graph |
| Cnvneural::INetworkReshapeDebugger | INetworkReshapeDebugger defines a callback interface for reshape operations |
| ►Cnvneural::INetworkRuntime | INetworkRuntime is a subset of the basic network interface that is accessible from layer classes during network evaluation |
| ►Cnvneural::INetwork | INetwork is the public interface to Network |
| ►Cnvneural::INetwork2 | INetwork2 is the public interface for the revision 2 of the Network interface |
| Cnvneural::INetwork3 | INetwork3 is the public interface for the revision 3 of the Network interface |
| Cnvneural::IOnnxGenerationActivation | ONNX export interface for IActivationFunction |
| Cnvneural::IOnnxGenerationGraphAttribute | Tool-provided interface representing an AttributeProto in an ONNX graph node |
| Cnvneural::IOnnxGenerationGraphNode | Tool-provided interface representing a NodeProto in an ONNX graph |
| Cnvneural::IOnnxGenerationHost | Tool-provided interface for creating ONNX model graphs in an ABI-stable fashion |
| Cnvneural::IOnnxGenerationLayer | ONNX export interface for ILayer |
| Cnvneural::IParameterNode | Represents a serialized parameter block in a model definition |
| Cnvneural::IPlugin | IPlugin is the general factory interface used by NvNeural's plugin system |
| Cnvneural::IPluginLoader | Platform-agnostic plugin loader interface |
| Cnvneural::IPoolingLayer | IPoolingLayer is an optional interface implemented by pooling layers |
| Cnvneural::IPrototypeLayer | IPrototypeLayer is an optional interface that marks a layer as a prototype layer |
| Cnvneural::IPrototypePlugin | IPrototypePlugin is an optional interface implemented by IPlugin objects that describes generic prototype layers implemented inside the plugin |
| Cnvneural::IResourceAggregator | Key-value store for creating IResourceDictionary objects |
| Cnvneural::IResourceDictionary | Key-value store for binary data such as precompiled kernels |
| Cnvneural::IRuntimeOptionsHost | IRuntimeOptionsHost is an interface that provides runtime option communication from the layer to the host |
| Cnvneural::IRuntimeOptionsLayer | IRuntimeOptionsLayer is an optional interface that marks a layer as one that uses runtime options |
| Cnvneural::IShuffleLayer | IShuffleLayer is a common interface implemented by space-to-depth and depth-to-space layers |
| Cnvneural::IStandardInputLayer | Defines a standard input layer |
| Cnvneural::IStatusMessageLayer | IStatusMessageLayer is an optional interface intended for ILayer to provide status messages |
| Cnvneural::IStringList | IStringList represents an immutable collection of strings |
| Cnvneural::IWeightsData | IWeightsData represents a binary buffer provided by IWeightsLoader |
| Cnvneural::IWeightsLoader | IWeightsLoader is an interface that provides weights to layers |
| Cnvneural::LayerDesc | This structure describes an ILayer for tools and network builders |
| Cnvneural::LayerDescHostContainer | "Host-native" container for LayerDesc structures from other modules |
| Cnvneural::LayerInputDesc | Describes a single input terminal for a layer. LayerDesc objects contain arrays of this structure |
| Cnvneural::LayerListIterator | Iterator class to enable range-based for loops and similar constructs across any ILayerList |
| Cnvneural::MemoryTrackingData | Structure describing details of an object's memory allocation behavior |
| Cnvneural::RefPtr< TObject >::OutputWrapper | Details type that allows version-safe use of out-pointer parameters without converting through an intermediate raw pointer variable or mismatching fromPointer/fromPointerNoAddRef |
| Cnvneural::ParamDependencyDesc | The ParamDependencyDesc describe a parameter dependency on parameter named pParamName with value pParamValue |
| Cnvneural::ParamDesc | ParamDesc describes a parameter for the plugin, giving it a name, default value, type, and, if needed, a pointer to greater detail |
| Cnvneural::PrototypeDesc | This structure represent a prototype layer version (backend, tensor format and kernel type), it should be passed to ClassRegistry using registerPrototype |
| Cnvneural::PrototypeDescHostContainer | This class is the host side container for the PrototypeDesc structure (see CoreTypes.h) |
| Cnvneural::refobj::PublicBase< TBaseType > | Helper class for RefObjectBase indicating direct inheritance without providing interfaces |
| Cnvneural::RefPtr< TObject > | Intrusive pointer using IRefObject's reference counting system |
| Cnvneural::RefPtr< const nvneural::IClassRegistry > | |
| Cnvneural::RefPtr< IClassRegistry > | |
| Cnvneural::RefPtr< nvneural::ILayer > | |
| Cnvneural::RefPtr< nvneural::ILogger > | |
| Cnvneural::RefPtr< nvneural::INetworkDebugger > | |
| Cnvneural::RefPtr< nvneural::IPlugin > | |
| Cnvneural::RefPtr< nvneural::IRuntimeOptionsHost > | |
| Cnvneural::ScopedMemoryAllocation | ScopedMemoryAllocation is a helper function for allocating memory blocks from the backend while adding the security and ease of use of the RAII idiom |
| ►Cnvneural::detail::ScriptInterpretInterface< detail::AnyOperand > | |
| Cnvneural::BasePrototypeLayer | Base class for the CUDA prototype layers shipped with NvNeural |
| Cnvneural::StringParamTypeDesc | The StringParamTypeDesc further describes a parameter for the plugin and is pointed to from the higher level parameter descriptor ParamDesc |
| Cnvneural::TensorDimension | TensorDimension describes the dimensions of a four-dimensional image tensor |
| Cnvneural::TensorFormat | TensorFormat describes a specific tensor shape (element type and layout) |
| Cnvneural::XmlNetworkBuilder | XML-based network builder |
1.9.1