mpsnnpadding-p(3) [mojave man page]
<MPSNNPadding>(3) MetalPerformanceShaders.framework <MPSNNPadding>(3) NAME
<MPSNNPadding> SYNOPSIS
#include <MPSNeuralNetworkTypes.h> Inherited by MPSNNDefaultPadding. Detailed Description A method to describe how MPSCNNKernels should pad images when data outside the image is needed Different (non-Apple) CNN frameworks have different policies for how to size the result of a CNN filter and what padding to add around the edges. Some filters such as pooling and convolution read from neighboring feature channel (pixel) values. Four predefined MPSPaddingMethods are available: MPSNNPaddingMethodValidOnly, MPSNNPaddingMethodFull, MPSNNPaddingMethodSameTL, MPSNNPaddingMethodSameBR. You may also implement your own padding definition with a block that conforms to this prototype. Author Generated automatically by Doxygen for MetalPerformanceShaders.framework from the source code. Version MetalPerformanceShaders-100 Thu Feb 8 2018 <MPSNNPadding>(3)
Check Out this Related Man Page
MPSCNNPoolingGradientNode(3) MetalPerformanceShaders.framework MPSCNNPoolingGradientNode(3) NAME
MPSCNNPoolingGradientNode SYNOPSIS
#import <MPSNNGraphNodes.h> Inherits MPSNNGradientFilterNode. Inherited by MPSCNNDilatedPoolingMaxGradientNode, MPSCNNPoolingAverageGradientNode, MPSCNNPoolingL2NormGradientNode, and MPSCNNPoolingMaxGradientNode. Instance Methods (nonnull instancetype) - initWithSourceGradient:sourceImage:gradientState:kernelWidth:kernelHeight:strideInPixelsX:strideInPixelsY:paddingPolicy: Class Methods (nonnull instancetype) + nodeWithSourceGradient:sourceImage:gradientState:kernelWidth:kernelHeight:strideInPixelsX:strideInPixelsY:paddingPolicy: Properties NSUInteger kernelWidth NSUInteger kernelHeight NSUInteger strideInPixelsX NSUInteger strideInPixelsY Method Documentation - (nonnull instancetype) initWithSourceGradient: (MPSNNImageNode *__nonnull) sourceGradient(MPSNNImageNode *__nonnull) sourceImage(MPSNNGradientStateNode *__nonnull) gradientState(NSUInteger) kernelWidth(NSUInteger) kernelHeight(NSUInteger) strideInPixelsX(NSUInteger) strideInPixelsY(nullable id< MPSNNPadding >) paddingPolicy make a pooling gradient node It would be much easier to use [inferencePoolingNode gradientNodeForSourceGradient:] instead. Parameters: sourceGradient The gradient from the downstream gradient filter. sourceImage The input image to the inference pooling filter gradientState The gradient state produced by the inference poolin filter kernelWidth The kernel width of the inference filter kernelHeight The kernel height of the inference filter strideInPixelsX The X stride from the inference filter strideInPixelsY The Y stride from the inference filter + (nonnull instancetype) nodeWithSourceGradient: (MPSNNImageNode *__nonnull) sourceGradient(MPSNNImageNode *__nonnull) sourceImage(MPSNNGradientStateNode *__nonnull) gradientState(NSUInteger) kernelWidth(NSUInteger) kernelHeight(NSUInteger) strideInPixelsX(NSUInteger) strideInPixelsY(nullable id< MPSNNPadding >) paddingPolicy make a pooling gradient node It would be much easier to use [inferencePoolingNode gradientNodeForSourceGradient:] instead. Parameters: sourceGradient The gradient from the downstream gradient filter. sourceImage The input image to the inference pooling filter gradientState The gradient state produced by the inference poolin filter kernelWidth The kernel width of the inference filter kernelHeight The kernel height of the inference filter strideInPixelsX The X stride from the inference filter strideInPixelsY The Y stride from the inference filter Property Documentation - (NSUInteger) kernelHeight [read], [nonatomic], [assign] - (NSUInteger) kernelWidth [read], [nonatomic], [assign] - (NSUInteger) strideInPixelsX [read], [nonatomic], [assign] - (NSUInteger) strideInPixelsY [read], [nonatomic], [assign] Author Generated automatically by Doxygen for MetalPerformanceShaders.framework from the source code. Version MetalPerformanceShaders-100 Thu Feb 8 2018 MPSCNNPoolingGradientNode(3)