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

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

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

.in +1c
.ti -1c
.RI "\fBMPSNNConvolutionAccumulatorPrecisionOption\fP \fBaccumulatorPrecision\fP"
.br
.ti -1c
.RI "\fBMPSCNNConvolutionGradientStateNode\fP * \fBconvolutionGradientState\fP"
.br
.in -1c
.SH "Method Documentation"
.PP 
.SS "\- (nonnull instancetype) initWithSource: (\fBMPSNNImageNode\fP *__nonnull) sourceNode(nonnull id< \fBMPSCNNConvolutionDataSource\fP >) weights"
Init a node representing a \fBMPSCNNConvolution\fP kernel 
.PP
\fBParameters:\fP
.RS 4
\fIsourceNode\fP The \fBMPSNNImageNode\fP representing the source \fBMPSImage\fP for the filter 
.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\&. If it is used for training, it may not have a neuron embedded in the convolution descriptor\&. 
.RE
.PP
\fBReturns:\fP
.RS 4
\fBA\fP new MPSNNFilter node for a \fBMPSCNNConvolution\fP kernel\&. 
.RE
.PP

.PP
Implemented in \fBMPSCNNFullyConnectedNode\fP\&.
.SS "+ (nonnull instancetype) nodeWithSource: (\fBMPSNNImageNode\fP *__nonnull) sourceNode(nonnull id< \fBMPSCNNConvolutionDataSource\fP >) weights"
Init an autoreleased not representing a \fBMPSCNNConvolution\fP kernel 
.PP
\fBParameters:\fP
.RS 4
\fIsourceNode\fP The \fBMPSNNImageNode\fP representing the source \fBMPSImage\fP for the filter 
.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\&. If it is used for training, it may not have a neuron embedded in the convolution descriptor\&. 
.RE
.PP
\fBReturns:\fP
.RS 4
\fBA\fP new MPSNNFilter node for a \fBMPSCNNConvolution\fP kernel\&. 
.RE
.PP

.PP
Implemented in \fBMPSCNNFullyConnectedNode\fP\&.
.SH "Property Documentation"
.PP 
.SS "\- (\fBMPSNNConvolutionAccumulatorPrecisionOption\fP) accumulatorPrecision\fC [read]\fP, \fC [write]\fP, \fC [nonatomic]\fP, \fC [assign]\fP"
Set the floating-point precision used by the convolution accumulator  Default: MPSNNConvolutionAccumulatorPrecisionOptionFloat 
.SS "\- (\fBMPSCNNConvolutionGradientStateNode\fP*) convolutionGradientState\fC [read]\fP, \fC [nonatomic]\fP, \fC [assign]\fP"
\fBA\fP node to represent a \fBMPSCNNConvolutionGradientState\fP object  Use this if the convolution is mirrored by a convolution transpose node later on in the graph to make sure that the size of the image returned from the convolution transpose matches the size of the image passed in to this node\&. 

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