nvneural::IInnerActivationLayer Class Reference

IInnerActivationLayer is an optional interface implemented by layers that fuse pairs of operations. More...

#include <nvneural/LayerTypes.h>

Inheritance diagram for nvneural::IInnerActivationLayer:

Public Member Functions
virtual float	innerActivationCoefficient (std::size_t coefficientIndex) const noexcept=0
	Retrieves the activation coefficient for the specified index. More...
virtual ActivationFunctionId	innerActivationFunction () const noexcept=0
	Retrieves the activation function attached to this layer. More...
virtual NeuralResult	setInnerActivationCoefficient (std::size_t coefficientIndex, float value) noexcept=0
	Sets an inner activation coefficient. More...
virtual NeuralResult	setInnerActivationFunction (ActivationFunctionId activationFunction) noexcept=0
	Sets the inner activation function. 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 = 0xff90b9f223475f88ul
	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

IInnerActivationLayer is an optional interface implemented by layers that fuse pairs of operations.

Model fusing rules can convert layer_A, layer_B pairs to a single layer_AB. All parameters of the source layers, including those related to activation functions, are forwarded to the fused layer; this interface provides access to the inner activation function without requiring arbitrary support for nested activations in the standard layer interfaces.

Nested activation parameters are also passed inside loadFromParameters as the _1_act and _1_act_alpha parameter names. The former is a string that should match an IClassRegistry-accessible ActivationDesc function ID. The latter is a comma-separated list of floating-point values.

Member Function Documentation

innerActivationCoefficient()

virtual float nvneural::IInnerActivationLayer::innerActivationCoefficient ( std::size_t  coefficientIndex ) const

pure virtualnoexcept

Retrieves the activation coefficient for the specified index.

The meaning of this value is activation-specific. If no setActivationCoefficient call was previously issued for this index, the layer should return a default value of zero.

Parameters

coefficientIndex

Coefficient index

innerActivationFunction()

virtual ActivationFunctionId nvneural::IInnerActivationLayer::innerActivationFunction ( ) const

pure virtualnoexcept

Retrieves the activation function attached to this layer.

Should return the most recent value passed to setInnerActivationFunction.

setInnerActivationCoefficient()

virtual NeuralResult nvneural::IInnerActivationLayer::setInnerActivationCoefficient ( std::size_t  coefficientIndex, float  value  )

pure virtualnoexcept

Sets an inner activation coefficient.

The meaning of this value is activation-specific.

Parameters

coefficientIndex	Coefficient index
value	Value to store

setInnerActivationFunction()

virtual NeuralResult nvneural::IInnerActivationLayer::setInnerActivationFunction ( ActivationFunctionId  activationFunction )

pure virtualnoexcept

Sets the inner activation function.

Parameters

activationFunction

Function to assign.

---

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

• Core/Inc/nvneural/LayerTypes.h