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

.in +1c
.ti -1c
.RI "(nonnull instancetype) \- \fBinitWithSource:convolutionGradientState:weights:\fP"
.br
.in -1c
.SS "Class Methods"

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

.in +1c
.ti -1c
.RI "\fBMPSCNNConvolutionGradientStateNode\fP * \fBconvolutionGradientState\fP"
.br
.in -1c
.SH "Detailed Description"
.PP 
\fBA\fP \fBMPSNNFilterNode\fP representing a \fBMPSCNNConvolutionTranspose\fP kernel 
.SH "Method Documentation"
.PP 
.SS "\- (nonnull instancetype) initWithSource: (\fBMPSNNImageNode\fP *__nonnull) sourceNode(\fBMPSCNNConvolutionGradientStateNode\fP *__nullable) convolutionGradientState(nonnull id< \fBMPSCNNConvolutionDataSource\fP >) weights"
Init a node representing a \fBMPSCNNConvolutionTransposeNode\fP kernel 
.PP
\fBParameters:\fP
.RS 4
\fIsourceNode\fP The \fBMPSNNImageNode\fP representing the source \fBMPSImage\fP for the filter 
.br
\fIconvolutionGradientState\fP 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 \fBMPSCNNConvolutionGradientState\fP node here\&. 
.br
\fIweights\fP \fBA\fP pointer to a valid object conforming to the \fBMPSCNNConvolutionDataSource\fP protocol\&. This object is provided by you to encapsulate storage for convolution weights and biases\&. 
.RE
.PP
\fBReturns:\fP
.RS 4
\fBA\fP new MPSNNFilter node for a \fBMPSCNNConvolutionTransposeNode\fP kernel\&. 
.RE
.PP

.SS "+ (nonnull instancetype) nodeWithSource: (\fBMPSNNImageNode\fP *__nonnull) sourceNode(\fBMPSCNNConvolutionGradientStateNode\fP *__nullable) convolutionGradientState(nonnull id< \fBMPSCNNConvolutionDataSource\fP >) weights"
Init an autoreleased not representing a \fBMPSCNNConvolutionTransposeNode\fP kernel 
.PP
\fBParameters:\fP
.RS 4
\fIsourceNode\fP The \fBMPSNNImageNode\fP representing the source \fBMPSImage\fP for the filter 
.br
\fIconvolutionGradientState\fP 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\&. 
.br
\fIweights\fP \fBA\fP pointer to a valid object conforming to the \fBMPSCNNConvolutionDataSource\fP protocol\&. This object is provided by you to encapsulate storage for convolution weights and biases\&. 
.RE
.PP
\fBReturns:\fP
.RS 4
\fBA\fP new MPSNNFilter node for a \fBMPSCNNConvolutionTransposeNode\fP kernel\&. 
.RE
.PP

.SH "Property Documentation"
.PP 
.SS "\- (\fBMPSCNNConvolutionGradientStateNode\fP*) convolutionGradientState\fC [read]\fP, \fC [nonatomic]\fP, \fC [assign]\fP"
unavailable 

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