|
NVIDIA NvNeural SDK
2022.2
GPU inference framework for NVIDIA Nsight Deep Learning Designer
|
IConvolutionLayer2 is an optional interface that marks a layer as a convolution layer. More...
#include <nvneural/layers/IConvolutionLayer.h>
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. | |
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.
|
pure virtualnoexcept |
Set the padding dimension for the convolution operation.
| paddingDimension | the padding dimension to set |
|
pure virtualnoexcept |
Set the padding mode of the convolution operation.
| mode | one of the padding modes available in enum ConvolutionPaddingMode |