mpscnnupsamplingnearestgradientnode(3) [mojave man page]
MPSCNNUpsamplingNearestGradientNode(3) MetalPerformanceShaders.framework MPSCNNUpsamplingNearestGradientNode(3) NAME
MPSCNNUpsamplingNearestGradientNode SYNOPSIS
#import <MPSNNGraphNodes.h> Inherits MPSNNGradientFilterNode. Instance Methods (nonnull instancetype) - initWithSourceGradient:sourceImage:gradientState:scaleFactorX:scaleFactorY: Class Methods (nonnull instancetype) + nodeWithSourceGradient:sourceImage:gradientState:scaleFactorX:scaleFactorY: Properties double scaleFactorX double scaleFactorY Detailed Description Node representing a MPSCNNUpsamplingNearest kernel Method Documentation - (nonnull instancetype) initWithSourceGradient: (MPSNNImageNode *__nonnull) sourceGradient(MPSNNImageNode *__nonnull) sourceImage(MPSNNGradientStateNode *__nonnull) gradientState(double) scaleFactorX(double) scaleFactorY A node to represent the gradient calculation for nearest upsampling training. [forwardFilter gradientFilterWithSources:] is a more convient way to do this. Parameters: sourceGradient The input gradient from the 'downstream' gradient filter. sourceImage The input image from the forward filter node gradientState The gradient state from the forward filter scaleFactorX The X scale factor from the forward pass scaleFactorY The Y scale factor from the forward pass Returns: A MPSCNNUpsamplingNearestGradientNode + (nonnull instancetype) nodeWithSourceGradient: (MPSNNImageNode *__nonnull) sourceGradient(MPSNNImageNode *__nonnull) sourceImage(MPSNNGradientStateNode *__nonnull) gradientState(double) scaleFactorX(double) scaleFactorY A node to represent the gradient calculation for nearest upsampling training. [forwardFilter gradientFilterWithSources:] is a more convient way to do this. Parameters: sourceGradient The input gradient from the 'downstream' gradient filter. sourceImage The input image from the forward filter node gradientState The gradient state from the forward filter scaleFactorX The X scale factor from the forward pass scaleFactorY The Y scale factor from the forward pass Returns: A MPSCNNUpsamplingNearestGradientNode Property Documentation - (double) scaleFactorX [read], [nonatomic], [assign] - (double) scaleFactorY [read], [nonatomic], [assign] Author Generated automatically by Doxygen for MetalPerformanceShaders.framework from the source code. Version MetalPerformanceShaders-100 Thu Feb 8 2018 MPSCNNUpsamplingNearestGradientNode(3)
Check Out this Related Man Page
MPSCNNConvolutionGradientNode(3) MetalPerformanceShaders.framework MPSCNNConvolutionGradientNode(3) NAME
MPSCNNConvolutionGradientNode SYNOPSIS
#import <MPSNNGraphNodes.h> Inherits MPSNNGradientFilterNode, and <MPSNNTrainableNode>. Instance Methods (nonnull instancetype) - initWithSourceGradient:sourceImage:convolutionGradientState:weights: Class Methods (nonnull instancetype) + nodeWithSourceGradient:sourceImage:convolutionGradientState:weights: Additional Inherited Members Method Documentation - (nonnull instancetype) initWithSourceGradient: (MPSNNImageNode *__nonnull) sourceGradient(MPSNNImageNode *__nonnull) sourceImage(MPSCNNConvolutionGradientStateNode *__nonnull) gradientState(nullable id< MPSCNNConvolutionDataSource >) weights A node to represent the gradient calculation for convolution training. Parameters: sourceGradient The input gradient from the 'downstream' gradient filter. Often that is a neuron gradient filter node. sourceImage The input image from the forward convolution node gradientState The gradient state from the forward convolution weights The data source from the forward convolution. It may not contain an integrated neuron. Similary, any normalization should be broken out into a separate node. Pass nil to use the weights from the forward convolution pass. Returns: A MPSCNNConvolutionGradientNode + (nonnull instancetype) nodeWithSourceGradient: (MPSNNImageNode *__nonnull) sourceGradient(MPSNNImageNode *__nonnull) sourceImage(MPSCNNConvolutionGradientStateNode *__nonnull) gradientState(nullable id< MPSCNNConvolutionDataSource >) weights A node to represent the gradient calculation for convolution training. Parameters: sourceGradient The input gradient from the 'downstream' gradient filter. Often that is a neuron gradient filter node. sourceImage The input image from the forward convolution node gradientState The gradient state from the forward convolution weights The data source from the forward convolution. It may not contain an integrated neuron. Similary, any normalization should be broken out into a separate node. Pass nil to use the weights from the forward convolution pass. Returns: A MPSCNNConvolutionGradientNode Author Generated automatically by Doxygen for MetalPerformanceShaders.framework from the source code. Version MetalPerformanceShaders-100 Thu Feb 8 2018 MPSCNNConvolutionGradientNode(3)