Linux and UNIX Man Pages

Linux & Unix Commands - Search Man Pages

mpscnnconvolutiontransposenode(3) [mojave man page]

MPSCNNConvolutionTransposeNode(3)			 MetalPerformanceShaders.framework			 MPSCNNConvolutionTransposeNode(3)

NAME
MPSCNNConvolutionTransposeNode SYNOPSIS
#import <MPSNNGraphNodes.h> Inherits MPSCNNConvolutionNode. Instance Methods (nonnull instancetype) - initWithSource:convolutionGradientState:weights: Class Methods (nonnull instancetype) + nodeWithSource:convolutionGradientState:weights: Properties MPSCNNConvolutionGradientStateNode * convolutionGradientState Detailed Description A MPSNNFilterNode representing a MPSCNNConvolutionTranspose kernel Method Documentation - (nonnull instancetype) initWithSource: (MPSNNImageNode *__nonnull) sourceNode(MPSCNNConvolutionGradientStateNode *__nullable) convolutionGradientState(nonnull id< MPSCNNConvolutionDataSource >) weights Init a node representing a MPSCNNConvolutionTransposeNode kernel Parameters: sourceNode The MPSNNImageNode representing the source MPSImage for the filter convolutionGradientState When the convolution transpose is used to 'undo' an earlier convolution in the graph, it is generally desired that the output image be the same size as the input image to the earlier convolution. You may optionally specify this size identity by passing in the MPSCNNConvolutionGradientState node here. weights A pointer to a valid object conforming to the MPSCNNConvolutionDataSource protocol. This object is provided by you to encapsulate storage for convolution weights and biases. Returns: A new MPSNNFilter node for a MPSCNNConvolutionTransposeNode kernel. + (nonnull instancetype) nodeWithSource: (MPSNNImageNode *__nonnull) sourceNode(MPSCNNConvolutionGradientStateNode *__nullable) convolutionGradientState(nonnull id< MPSCNNConvolutionDataSource >) weights Init an autoreleased not representing a MPSCNNConvolutionTransposeNode kernel Parameters: sourceNode The MPSNNImageNode representing the source MPSImage for the filter convolutionGradientState When the convolution transpose is used to 'undo' an earlier convolution in the graph, it is generally desired that the output image be the same size as the input image to the earlier convolution. You may optionally specify this size identity by passing in the MPSNNConvolutionGradientStateNode created by the convolution node here. weights A pointer to a valid object conforming to the MPSCNNConvolutionDataSource protocol. This object is provided by you to encapsulate storage for convolution weights and biases. Returns: A new MPSNNFilter node for a MPSCNNConvolutionTransposeNode kernel. Property Documentation - (MPSCNNConvolutionGradientStateNode*) convolutionGradientState [read], [nonatomic], [assign] unavailable Author Generated automatically by Doxygen for MetalPerformanceShaders.framework from the source code. Version MetalPerformanceShaders-100 Thu Feb 8 2018 MPSCNNConvolutionTransposeNode(3)

Check Out this Related Man Page

MPSCNNPoolingNode(3)					 MetalPerformanceShaders.framework				      MPSCNNPoolingNode(3)

NAME
MPSCNNPoolingNode SYNOPSIS
#import <MPSNNGraphNodes.h> Inherits MPSNNFilterNode. Inherited by MPSCNNPoolingAverageNode, MPSCNNPoolingL2NormNode, and MPSCNNPoolingMaxNode. Instance Methods (nonnull instancetype) - initWithSource:kernelWidth:kernelHeight:strideInPixelsX:strideInPixelsY: (nonnull instancetype) - initWithSource:filterSize:stride: (nonnull instancetype) - initWithSource:filterSize: Class Methods (nonnull instancetype) + nodeWithSource:filterSize: (nonnull instancetype) + nodeWithSource:filterSize:stride: Additional Inherited Members Detailed Description A node for a MPSCNNPooling kernel This is an abstract base class that does not correspond with any particular MPSCNNKernel. Please make one of the MPSCNNPooling subclasses instead. Method Documentation - (nonnull instancetype) initWithSource: (MPSNNImageNode *__nonnull) sourceNode(NSUInteger) size Convenience initializer for MPSCNNPooling nodes with square non-overlapping kernels Parameters: sourceNode The MPSNNImageNode representing the source MPSImage for the filter size kernelWidth = kernelHeight = strideInPixelsX = strideInPixelsY = size Returns: A new MPSNNFilter node for a MPSCNNPooling kernel. - (nonnull instancetype) initWithSource: (MPSNNImageNode *__nonnull) sourceNode(NSUInteger) size(NSUInteger) stride Convenience initializer for MPSCNNPooling nodes with square kernels Parameters: sourceNode The MPSNNImageNode representing the source MPSImage for the filter size kernelWidth = kernelHeight = size stride strideInPixelsX = strideInPixelsY = stride Returns: A new MPSNNFilter node for a MPSCNNPooling kernel. - (nonnull instancetype) initWithSource: (MPSNNImageNode *__nonnull) sourceNode(NSUInteger) kernelWidth(NSUInteger) kernelHeight(NSUInteger) strideInPixelsX(NSUInteger) strideInPixelsY Init a node representing a MPSCNNPooling kernel Parameters: sourceNode The MPSNNImageNode representing the source MPSImage for the filter kernelWidth The width of the max filter window kernelHeight The height of the max filter window strideInPixelsX The output stride (downsampling factor) in the x dimension. strideInPixelsY The output stride (downsampling factor) in the y dimension. Returns: A new MPSNNFilter node for a MPSCNNPooling kernel. + (nonnull instancetype) nodeWithSource: (MPSNNImageNode *__nonnull) sourceNode(NSUInteger) size Convenience initializer for MPSCNNPooling nodes with square non-overlapping kernels Parameters: sourceNode The MPSNNImageNode representing the source MPSImage for the filter size kernelWidth = kernelHeight = strideInPixelsX = strideInPixelsY = size Returns: A new MPSNNFilter node for a MPSCNNPooling kernel. + (nonnull instancetype) nodeWithSource: (MPSNNImageNode *__nonnull) sourceNode(NSUInteger) size(NSUInteger) stride Convenience initializer for MPSCNNPooling nodes with square non-overlapping kernels and a different stride Parameters: sourceNode The MPSNNImageNode representing the source MPSImage for the filter size kernelWidth = kernelHeight = size stride strideInPixelsX = strideInPixelsY = stride Returns: A new MPSNNFilter node for a MPSCNNPooling kernel. Author Generated automatically by Doxygen for MetalPerformanceShaders.framework from the source code. Version MetalPerformanceShaders-100 Thu Feb 8 2018 MPSCNNPoolingNode(3)
Man Page