NVIDIA NvNeural SDK  2022.2
GPU inference framework for NVIDIA Nsight Deep Learning Designer
nvneural::IConvolutionLayer2 Class Referenceabstract

IConvolutionLayer2 is an optional interface that marks a layer as a convolution layer. More...

#include <nvneural/layers/IConvolutionLayer.h>

Inheritance diagram for nvneural::IConvolutionLayer2:
nvneural::IConvolutionLayer nvneural::IRefObject

Public Member Functions

virtual TensorDimension getPaddingDimension () const noexcept=0
 Returns the currently set padding dimensions of the convolution operation.
 
virtual ConvolutionPaddingMode getPaddingMode () const noexcept=0
 Returns the currently set padding mode of the convolution operation.
 
virtual NeuralResult setPaddingDimension (const TensorDimension &paddingDimension) noexcept=0
 Set the padding dimension for the convolution operation. More...
 
virtual NeuralResult setPaddingMode (ConvolutionPaddingMode mode) noexcept=0
 Set the padding mode of the convolution operation. More...
 
- Public Member Functions inherited from nvneural::IConvolutionLayer
virtual NeuralResult applyBias (bool enableBias) noexcept=0
 Turns bias on or off. More...
 
virtual NeuralResult setFeatureCount (std::size_t numFeatures) noexcept=0
 Sets the feature count of the convolution operation. More...
 
virtual NeuralResult setKernelSize (std::size_t kernelSizeW, std::size_t kernelSizeH) noexcept=0
 Sets the kernel size of the convolution operation. More...
 
virtual NeuralResult setStride (std::size_t strideW, std::size_t strideH) noexcept=0
 Sets the stride of the convolution operation. More...
 
virtual NeuralResult setZeroPadding (bool enablePadding) noexcept=0
 Turns zero padding on or off. More...
 
virtual bool zeroPadding () const noexcept=0
 Returns true if zero padding is enabled.
 
- 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 = 0xe0107167331c03e4ul
 Interface TypeId for InterfaceOf purposes.
 
- Static Public Attributes inherited from nvneural::IConvolutionLayer
static const IRefObject::TypeId typeID = 0x835aee64db0d45baul
 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

IConvolutionLayer2 is an optional interface that marks a layer as a convolution layer.

Networks may fuse convolution layers with batch normalization layers (represented by IBatchNormalizationLayer).

This is a revised version of IConvolutionLayer with additional support for custom symmetric padding values.

Member Function Documentation

◆ setPaddingDimension()

virtual NeuralResult nvneural::IConvolutionLayer2::setPaddingDimension ( const TensorDimension paddingDimension)
pure virtualnoexcept

Set the padding dimension for the convolution operation.

Parameters
paddingDimensionthe padding dimension to set

◆ setPaddingMode()

virtual NeuralResult nvneural::IConvolutionLayer2::setPaddingMode ( ConvolutionPaddingMode  mode)
pure virtualnoexcept

Set the padding mode of the convolution operation.

Parameters
modeone of the padding modes available in enum ConvolutionPaddingMode

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