NVIDIA NvNeural SDK  2022.2
GPU inference framework for NVIDIA Nsight Deep Learning Designer
nvneural::IWeightsLoader Class Referenceabstract

IWeightsLoader is an interface that provides weights to layers. More...

#include <nvneural/CoreTypes.h>

Inheritance diagram for nvneural::IWeightsLoader:
nvneural::IRefObject

Public Member Functions

virtual NeuralResult getWeightsForLayer (IWeightsData **ppWeightsDataOut, const INetworkRuntime *pNetwork, const ILayer *pLayer, const char *pName) const noexcept=0
 Retrieves a weights data buffer in a canonical format. More...
 
- Public Member Functions inherited from nvneural::IRefObject
virtual RefCount addRef () const noexcept=0
 Increments the object's reference count. More...
 
virtual const void * queryInterface (TypeId interface) const noexcept=0
 This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.
 
virtual void * queryInterface (TypeId interface) noexcept=0
 Retrieves a new object interface pointer. More...
 
virtual RefCount release () const noexcept=0
 Decrements the object's reference count and destroy the object if the reference count reaches zero. More...
 

Static Public Attributes

static const IRefObject::TypeId typeID = 0x5bac8f6ca68c52b6ul
 Interface TypeId for InterfaceOf purposes.
 
- Static Public Attributes inherited from nvneural::IRefObject
static const TypeId typeID = 0x14ecc3f9de638e1dul
 Interface TypeId for InterfaceOf purposes.
 

Additional Inherited Members

- Public Types inherited from nvneural::IRefObject
using RefCount = std::uint32_t
 Typedef used to track the number of active references to an object.
 
using TypeId = std::uint64_t
 Every interface must define a unique TypeId. This should be randomized.
 
- Protected Member Functions inherited from nvneural::IRefObject
virtual ~IRefObject ()=default
 A protected destructor prevents accidental stack-allocation of IRefObjects or use with other smart pointer classes like std::unique_ptr.
 

Detailed Description

IWeightsLoader is an interface that provides weights to layers.

The implementation is completely application-defined and may involve embedded resources instead of direct filesystem access.

Member Function Documentation

◆ getWeightsForLayer()

virtual NeuralResult nvneural::IWeightsLoader::getWeightsForLayer ( IWeightsData **  ppWeightsDataOut,
const INetworkRuntime pNetwork,
const ILayer pLayer,
const char *  pName 
) const
pure virtualnoexcept

Retrieves a weights data buffer in a canonical format.

Parameters
ppWeightsDataOutPointer to a variable receiving the created IWeightsData object
pNetworkNetworkRuntime containing the layer
pLayerLayer to retrieve data for
pNameBuffer to retrieve

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