.TH "MPSCNNPoolingL2NormGradient" 3 "Mon Jul 9 2018" "Version MetalPerformanceShaders-119.3" "MetalPerformanceShaders.framework" \" -*- nroff -*-
.ad l
.nh
.SH NAME
MPSCNNPoolingL2NormGradient
.SH SYNOPSIS
.br
.PP
.PP
\fC#import <MPSCNNPooling\&.h>\fP
.PP
Inherits \fBMPSCNNPoolingGradient\fP\&.
.SS "Instance Methods"

.in +1c
.ti -1c
.RI "(nonnull instancetype) \- \fBinitWithDevice:kernelWidth:kernelHeight:strideInPixelsX:strideInPixelsY:\fP"
.br
.ti -1c
.RI "(nullable instancetype) \- \fBinitWithCoder:device:\fP"
.br
.in -1c
.SS "Additional Inherited Members"
.SH "Detailed Description"
.PP 
This depends on Metal\&.framework  Specifies the filter for computing the gradient of the L2-Norm pooling filter\&. The operation backpropagates a gradient vector using chain rule\&.
.PP
L2-Norm pooling forward pass is defined as: 
.PP
.nf
out(x) = sqrt( sum_{dx \in Window(x)} in(s*x+dx) * in(s*x+dx) ), where

.fi
.PP
.PP
the pooling window definition 'Window(x)' follows \fBMPSCNNPooling\fP specification and 's' is the pixel stride and in() is the source input image\&.
.PP
Hence the partial derivative of the output value wrt\&. to the input value needed in the gradient backpropagation in \fBMPSCNNPoolingGradient\fP is: 
.PP
.nf
d out(x)/d in(y) = sum_{dx \in Window(x)} delta_{s*x+dx, y} in(s*x+dx) / out(x), where

.fi
.PP
.PP
delta_{x,y} is the Kronecker delta symbol for which 
.PP
.nf
delta_{x,y} =  {  1, when x == y
               {  0, otherwise,

.fi
.PP
 and out(x) is the L2-norm pooling value at point 'x' defined above\&. 
.SH "Method Documentation"
.PP 
.SS "\- (nullable instancetype) \fBinitWithCoder:\fP (NSCoder *__nonnull) aDecoder(nonnull id< MTLDevice >) device"
\fBNSSecureCoding\fP compatability  See \fBMPSKernel::initWithCoder\fP\&. 
.PP
\fBParameters:\fP
.RS 4
\fIaDecoder\fP The NSCoder subclass with your serialized \fBMPSCNNPoolingL2NormGradient\fP 
.br
\fIdevice\fP The MTLDevice on which to make the \fBMPSCNNPoolingL2NormGradient\fP 
.RE
.PP
\fBReturns:\fP
.RS 4
\fBA\fP new \fBMPSCNNPoolingL2NormGradient\fP object, or nil if failure\&. 
.RE
.PP

.PP
Reimplemented from \fBMPSCNNPoolingGradient\fP\&.
.SS "\- (nonnull instancetype) \fBinitWithDevice:\fP (nonnull id< MTLDevice >) device(NSUInteger) kernelWidth(NSUInteger) kernelHeight(NSUInteger) strideInPixelsX(NSUInteger) strideInPixelsY"
Initialize a gradient L2-norm pooling filter 
.PP
\fBParameters:\fP
.RS 4
\fIdevice\fP The device the filter will run on 
.br
\fIkernelWidth\fP The width of the kernel\&. Can be an odd or even value\&. 
.br
\fIkernelHeight\fP The height of the kernel\&. Can be an odd or even value\&. 
.br
\fIstrideInPixelsX\fP The input stride (upsampling factor) in the x dimension\&. 
.br
\fIstrideInPixelsY\fP The input stride (upsampling factor) in the y dimension\&. 
.RE
.PP
\fBReturns:\fP
.RS 4
\fBA\fP valid \fBMPSCNNPoolingL2NormGradient\fP object or nil, if failure\&. 
.RE
.PP

.PP
Reimplemented from \fBMPSCNNPoolingGradient\fP\&.

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