nvneural::INetworkLayer Class Reference

INetworkLayer objects are ILayers that encapsulate an externally defined network graph. More...

#include <NetworkLayer.h>

Inheritance diagram for nvneural::INetworkLayer:

Public Member Functions
virtual NeuralResult	addFusingRuleToSubNetwork (const char *pFusingRule) noexcept=0
	Adds a v2 fusing rule to the subgraph's network builder object. More...
virtual NeuralResult	getFlattenSubNetworkLayerList (ILayerList **ppLayerList, size_t *pDepth) const noexcept=0
	Returns a recursively flattened list of layers contained in the subgraph. More...
virtual NeuralResult	getOutputs (ILayerList **ppLayerList) const noexcept=0
	Returns a list of output layers defined in the subgraph. 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 = 0x90a0da9f3d52f363ul
	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

INetworkLayer objects are ILayers that encapsulate an externally defined network graph.

They do not actually contain an INetworkRuntime, but instead proxy their reshape/evaluate/etc. operations into an internally tracked list of ILayer objects.

Member Function Documentation

addFusingRuleToSubNetwork()

virtual NeuralResult nvneural::INetworkLayer::addFusingRuleToSubNetwork ( const char *  pFusingRule )

pure virtualnoexcept

Adds a v2 fusing rule to the subgraph's network builder object.

Must be called before calling ILayer::loadFromParameters.

Parameters

pFusingRule

Fusing rule definition using v2 syntax

See also

nvneural::FusingRule

getFlattenSubNetworkLayerList()

virtual NeuralResult nvneural::INetworkLayer::getFlattenSubNetworkLayerList ( ILayerList **  ppLayerList, size_t *  pDepth  ) const

pure virtualnoexcept

Returns a recursively flattened list of layers contained in the subgraph.

Input connection layers are internally aliases to external layers and as such are not represented in the returned list. Any network layers that are part of the subgraph are themselves flattened and included in the list.

Parameters

ppLayerList	Pointer to a variable receiving a list of contained layers
pDepth	Pointer to a variable receiving the maximum subgraph depth

getOutputs()

virtual NeuralResult nvneural::INetworkLayer::getOutputs ( ILayerList **  ppLayerList ) const

pure virtualnoexcept

Returns a list of output layers defined in the subgraph.

Parameters

ppLayerList

Pointer to a variable receiving a list of subgraph output layers

See also

INetworkRuntime::getOutputLayers

---

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

• Host/Inc/NetworkLayer.h