nvneural::IPoolingLayer Class Reference

IPoolingLayer is an optional interface implemented by pooling layers. More...

#include <nvneural/layers/IPoolingLayer.h>

Inheritance diagram for nvneural::IPoolingLayer:

Public Member Functions
virtual NeuralResult	getKernelSize (std::size_t *pKernelW, std::size_t *pKernelH) const noexcept=0
	Retrieves the kernel size for the W and H axes. More...
virtual NeuralResult	getPadding (std::size_t *pStartW, std::size_t *pStartH, std::size_t *pEndW, std::size_t *pEndH) const noexcept=0
	Retrieves the start and end padding for the W and H axes. More...
virtual NeuralResult	getStride (std::size_t *pStrideW, std::size_t *pStrideH) const noexcept=0
	Retrieves the operation stride for the W and H axes. More...
virtual PoolType	poolingType () const noexcept=0
	Returns the type of pooling operation performed by this layer.
virtual NeuralResult	setEndPadding (std::size_t endW, std::size_t endH) noexcept=0
	Sets the end padding along the W and H axes. More...
virtual NeuralResult	setKernelSize (std::size_t kernelW, std::size_t kernelH) noexcept=0
	Sets the kernel size for the W and H axes. More...
virtual NeuralResult	setPoolingType (PoolType poolType) noexcept=0
	Sets the type of pooling operation. More...
virtual NeuralResult	setStartPadding (std::size_t startW, std::size_t startH) noexcept=0
	Sets the start padding along the W and H axes. More...
virtual NeuralResult	setStride (std::size_t strideW, std::size_t strideH) noexcept=0
	Sets the operation stride for the W and H axes. 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 = 0x2e8a0e0dbd99fe82ul
	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

IPoolingLayer is an optional interface implemented by pooling layers.

Member Function Documentation

getKernelSize()

virtual NeuralResult nvneural::IPoolingLayer::getKernelSize ( std::size_t *  pKernelW, std::size_t *  pKernelH  ) const

pure virtualnoexcept

Retrieves the kernel size for the W and H axes.

Parameters

pKernelW	Optional pointer to a variable receiving the current kernel size for W
pKernelH	Optional pointer to a variable receiving the current kernel size for H

getPadding()

virtual NeuralResult nvneural::IPoolingLayer::getPadding ( std::size_t *  pStartW, std::size_t *  pStartH, std::size_t *  pEndW, std::size_t *  pEndH  ) const

pure virtualnoexcept

Retrieves the start and end padding for the W and H axes.

Zero values indicate no padding for that component.

Parameters

pStartW	Optional pointer to a variable receiving the current start padding for W
pStartH	Optional pointer to a variable receiving the current start padding for H
pEndW	Optional pointer to a variable receiving the current end padding for W
pEndH	Optional pointer to a variable receiving the current end padding for H

getStride()

virtual NeuralResult nvneural::IPoolingLayer::getStride ( std::size_t *  pStrideW, std::size_t *  pStrideH  ) const

pure virtualnoexcept

Retrieves the operation stride for the W and H axes.

Parameters

pStrideW	Optional pointer to a variable receiving the current stride for W
pStrideH	Optional pointer to a variable receiving the current stride for H

setEndPadding()

virtual NeuralResult nvneural::IPoolingLayer::setEndPadding ( std::size_t  endW, std::size_t  endH  )

pure virtualnoexcept

Sets the end padding along the W and H axes.

Zero values indicate no padding for that component.

Parameters

endW	End padding for the W axis
endH	End padding for the H axis

setKernelSize()

virtual NeuralResult nvneural::IPoolingLayer::setKernelSize ( std::size_t  kernelW, std::size_t  kernelH  )

pure virtualnoexcept

Sets the kernel size for the W and H axes.

Parameters

kernelW	Kernel size for the W axis
kernelH	Kernel size for the H axis

setPoolingType()

virtual NeuralResult nvneural::IPoolingLayer::setPoolingType ( PoolType  poolType )

pure virtualnoexcept

Sets the type of pooling operation.

Parameters

poolType

Pooling operation to perform

setStartPadding()

virtual NeuralResult nvneural::IPoolingLayer::setStartPadding ( std::size_t  startW, std::size_t  startH  )

pure virtualnoexcept

Sets the start padding along the W and H axes.

Zero values indicate no padding for that component.

Parameters

startW	Start padding for the W axis
startH	Start padding for the H axis

setStride()

virtual NeuralResult nvneural::IPoolingLayer::setStride ( std::size_t  strideW, std::size_t  strideH  )

pure virtualnoexcept

Sets the operation stride for the W and H axes.

Parameters

strideW	Stride for the W axis
strideH	Stride for the H axis

---

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

• Core/Inc/nvneural/layers/IPoolingLayer.h