mpsnnconcatenationgradientnode(3) [mojave man page]
MPSNNConcatenationGradientNode(3) MetalPerformanceShaders.framework MPSNNConcatenationGradientNode(3) NAME
MPSNNConcatenationGradientNode SYNOPSIS
#import <MPSNNGraphNodes.h> Inherits MPSNNGradientFilterNode. Instance Methods (nonnull instancetype) - initWithSourceGradient:sourceImage:gradientState: Class Methods (nonnull instancetype) + nodeWithSourceGradient:sourceImage:gradientState: Additional Inherited Members Detailed Description A MPSNNSlice filter that operates as the conjugate computation for concatentation operators during training As concatenation is formally just a copy and not a computation, there isn't a lot of arithmetic for the slice operator to do, but we still need to extract out the relevant portion of the gradient of the input signal that went into the corresponding concatenation destination image. Method Documentation - (nonnull instancetype) initWithSourceGradient: (MPSNNImageNode *__nonnull) gradientSourceNode(MPSNNImageNode *__nonnull) sourceImage(MPSNNGradientStateNode *__nonnull) gradientState Init a MPSNNConcatenationGradientNode Generally you should use [MPSNNConcatenationNode gradientFiltersWithSources:] instead. Parameters: gradientSourceNode The gradient image functioning as input for the operator sourceImage The particular input image to the concatentation, if any, that the slice corresponds with gradientState The gradient state produced by the concatenation filter, consumed by this filter + (nonnull instancetype) nodeWithSourceGradient: (MPSNNImageNode *__nonnull) gradientSourceNode(MPSNNImageNode *__nonnull) sourceImage(MPSNNGradientStateNode *__nonnull) gradientState create a MPSNNConcatenationGradientNode Generally you should use [MPSNNConcatenationNode gradientFiltersWithSources:] instead. Parameters: gradientSourceNode The gradient image functioning as input for the operator sourceImage The particular input image to the concatentation, if any, that the slice corresponds with gradientState The gradient state produced by the concatenation filter, consumed by this filter Author Generated automatically by Doxygen for MetalPerformanceShaders.framework from the source code. Version MetalPerformanceShaders-100 Thu Feb 8 2018 MPSNNConcatenationGradientNode(3)
Check Out this Related Man Page
MPSCNNDilatedPoolingMaxGradientNode(3) MetalPerformanceShaders.framework MPSCNNDilatedPoolingMaxGradientNode(3) NAME
MPSCNNDilatedPoolingMaxGradientNode SYNOPSIS
#import <MPSNNGraphNodes.h> Inherits MPSCNNPoolingGradientNode. Instance Methods (nonnull instancetype) - initWithSourceGradient:sourceImage:gradientState:kernelWidth:kernelHeight:strideInPixelsX:strideInPixelsY:dilationRateX:dilationRateY: Class Methods (nonnull instancetype) + nodeWithSourceGradient:sourceImage:gradientState:kernelWidth:kernelHeight:strideInPixelsX:strideInPixelsY:dilationRateX:dilationRateY: Properties NSUInteger dilationRateX NSUInteger dilationRateY Method Documentation - (nonnull instancetype) initWithSourceGradient: (MPSNNImageNode *__nonnull) sourceGradient(MPSNNImageNode *__nonnull) sourceImage(MPSNNGradientStateNode *__nonnull) gradientState(NSUInteger) kernelWidth(NSUInteger) kernelHeight(NSUInteger) strideInPixelsX(NSUInteger) strideInPixelsY(NSUInteger) dilationRateX(NSUInteger) dilationRateY 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(NSUInteger) dilationRateX(NSUInteger) dilationRateY 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) dilationRateX [read], [nonatomic], [assign] - (NSUInteger) dilationRateY [read], [nonatomic], [assign] Author Generated automatically by Doxygen for MetalPerformanceShaders.framework from the source code. Version MetalPerformanceShaders-100 Thu Feb 8 2018 MPSCNNDilatedPoolingMaxGradientNode(3)