.TH "MPSCNNDilatedPoolingMaxNode" 3 "Mon Jul 9 2018" "Version MetalPerformanceShaders-119.3" "MetalPerformanceShaders.framework" \" -*- nroff -*-
.ad l
.nh
.SH NAME
MPSCNNDilatedPoolingMaxNode
.SH SYNOPSIS
.br
.PP
.PP
\fC#import <MPSNNGraphNodes\&.h>\fP
.PP
Inherits \fBMPSNNFilterNode\fP\&.
.SS "Instance Methods"

.in +1c
.ti -1c
.RI "(nonnull instancetype) \- \fBinitWithSource:kernelWidth:kernelHeight:strideInPixelsX:strideInPixelsY:dilationRateX:dilationRateY:\fP"
.br
.ti -1c
.RI "(nonnull instancetype) \- \fBinitWithSource:filterSize:stride:dilationRate:\fP"
.br
.ti -1c
.RI "(nonnull instancetype) \- \fBinitWithSource:filterSize:\fP"
.br
.in -1c
.SS "Class Methods"

.in +1c
.ti -1c
.RI "(nonnull instancetype) + \fBnodeWithSource:filterSize:\fP"
.br
.ti -1c
.RI "(nonnull instancetype) + \fBnodeWithSource:filterSize:stride:dilationRate:\fP"
.br
.in -1c
.SS "Properties"

.in +1c
.ti -1c
.RI "NSUInteger \fBdilationRateX\fP"
.br
.ti -1c
.RI "NSUInteger \fBdilationRateY\fP"
.br
.in -1c
.SH "Detailed Description"
.PP 
\fBA\fP node for a MPSCNNDilatedPooling kernel  This class corresponds to the MPSCNNDilatedPooling class\&. 
.SH "Method Documentation"
.PP 
.SS "\- (nonnull instancetype) initWithSource: (\fBMPSNNImageNode\fP *__nonnull) sourceNode(NSUInteger) size"
Convenience initializer for MPSCNNDilatedPooling nodes with square non-overlapping kernels 
.PP
\fBParameters:\fP
.RS 4
\fIsourceNode\fP The \fBMPSNNImageNode\fP representing the source \fBMPSImage\fP for the filter 
.br
\fIsize\fP kernelWidth = kernelHeight = strideInPixelsX = strideInPixelsY = dilationRateX = dilationRateY = size 
.RE
.PP
\fBReturns:\fP
.RS 4
\fBA\fP new MPSNNFilter node for a MPSCNNDilatedPooling kernel\&. 
.RE
.PP

.SS "\- (nonnull instancetype) initWithSource: (\fBMPSNNImageNode\fP *__nonnull) sourceNode(NSUInteger) size(NSUInteger) stride(NSUInteger) dilationRate"
Convenience initializer for MPSCNNDilatedPooling nodes with square kernels and equal dilation factors 
.PP
\fBParameters:\fP
.RS 4
\fIsourceNode\fP The \fBMPSNNImageNode\fP representing the source \fBMPSImage\fP for the filter 
.br
\fIsize\fP kernelWidth = kernelHeight = size 
.br
\fIstride\fP strideInPixelsX = strideInPixelsY = stride 
.br
\fIdilationRate\fP dilationRateX = dilationRateY = stride 
.RE
.PP
\fBReturns:\fP
.RS 4
\fBA\fP new MPSNNFilter node for a MPSCNNDilatedPooling kernel\&. 
.RE
.PP

.SS "\- (nonnull instancetype) initWithSource: (\fBMPSNNImageNode\fP *__nonnull) sourceNode(NSUInteger) kernelWidth(NSUInteger) kernelHeight(NSUInteger) strideInPixelsX(NSUInteger) strideInPixelsY(NSUInteger) dilationRateX(NSUInteger) dilationRateY"
Init a node representing a \fBMPSCNNPooling\fP kernel 
.PP
\fBParameters:\fP
.RS 4
\fIsourceNode\fP The \fBMPSNNImageNode\fP representing the source \fBMPSImage\fP for the filter 
.br
\fIkernelWidth\fP The width of the max filter window 
.br
\fIkernelHeight\fP The height of the max filter window 
.br
\fIstrideInPixelsX\fP The output stride (downsampling factor) in the x dimension\&. 
.br
\fIstrideInPixelsY\fP The output stride (downsampling factor) in the y dimension\&. 
.br
\fIdilationRateX\fP The dilation factor in the x dimension\&. 
.br
\fIdilationRateY\fP The dilation factor in the y dimension\&. 
.RE
.PP
\fBReturns:\fP
.RS 4
\fBA\fP new MPSNNFilter node for a \fBMPSCNNPooling\fP kernel\&. 
.RE
.PP

.SS "+ (nonnull instancetype) nodeWithSource: (\fBMPSNNImageNode\fP *__nonnull) sourceNode(NSUInteger) size"
Convenience initializer for MPSCNNDilatedPooling nodes with square non-overlapping kernels 
.PP
\fBParameters:\fP
.RS 4
\fIsourceNode\fP The \fBMPSNNImageNode\fP representing the source \fBMPSImage\fP for the filter 
.br
\fIsize\fP kernelWidth = kernelHeight = strideInPixelsX = strideInPixelsY = dilationRateX = dilationRateY = size 
.RE
.PP
\fBReturns:\fP
.RS 4
\fBA\fP new MPSNNFilter node for a MPSCNNDilatedPooling kernel\&. 
.RE
.PP

.SS "+ (nonnull instancetype) nodeWithSource: (\fBMPSNNImageNode\fP *__nonnull) sourceNode(NSUInteger) size(NSUInteger) stride(NSUInteger) dilationRate"
Convenience initializer for MPSCNNDilatedPooling nodes with square kernels and equal dilation factors 
.PP
\fBParameters:\fP
.RS 4
\fIsourceNode\fP The \fBMPSNNImageNode\fP representing the source \fBMPSImage\fP for the filter 
.br
\fIsize\fP kernelWidth = kernelHeight = size 
.br
\fIstride\fP strideInPixelsX = strideInPixelsY = stride 
.br
\fIdilationRate\fP dilationRateX = dilationRateY = stride 
.RE
.PP
\fBReturns:\fP
.RS 4
\fBA\fP new MPSNNFilter node for a MPSCNNDilatedPooling kernel\&. 
.RE
.PP

.SH "Property Documentation"
.PP 
.SS "\- (NSUInteger) dilationRateX\fC [read]\fP, \fC [nonatomic]\fP, \fC [assign]\fP"

.SS "\- (NSUInteger) dilationRateY\fC [read]\fP, \fC [nonatomic]\fP, \fC [assign]\fP"


.SH "Author"
.PP 
Generated automatically by Doxygen for MetalPerformanceShaders\&.framework from the source code\&.