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

.in +1c
.ti -1c
.RI "(nonnull instancetype) \- \fBinitWithDevice:dataSource:\fP"
.br
.ti -1c
.RI "(nonnull instancetype) \- \fBinitWithDevice:\fP"
.br
.ti -1c
.RI "(nullable instancetype) \- \fBinitWithCoder:device:\fP"
.br
.ti -1c
.RI "(void) \- \fBreloadDataSource:\fP"
.br
.ti -1c
.RI "(void) \- \fBreloadGammaAndBetaFromDataSource\fP"
.br
.ti -1c
.RI "(void) \- \fBreloadGammaAndBetaWithCommandBuffer:gammaAndBetaState:\fP"
.br
.ti -1c
.RI "(\fBMPSCNNInstanceNormalizationGradientState\fP *__nullable) \- \fBresultStateForSourceImage:sourceStates:destinationImage:\fP"
.br
.ti -1c
.RI "(\fBMPSCNNInstanceNormalizationGradientState\fP *__nullable) \- \fBtemporaryResultStateForCommandBuffer:sourceImage:sourceStates:destinationImage:\fP"
.br
.in -1c
.SS "Properties"

.in +1c
.ti -1c
.RI "float \fBepsilon\fP"
.br
.ti -1c
.RI "id< \fBMPSCNNInstanceNormalizationDataSource\fP > \fBdataSource\fP"
.br
.in -1c
.SS "Additional Inherited Members"
.SH "Detailed Description"
.PP 
This depends on Metal\&.framework  This kernel normalizes each image, on a per-channel basis, to have zero mean and unit variance:
.PP
for each image: for each channel: y = (x - mean) * gamma / sqrt(variance + epsilon) + beta; 
.SH "Method Documentation"
.PP 
.SS "\- (nullable instancetype) \fBinitWithCoder:\fP (NSCoder *__nonnull) aDecoder(nonnull id< MTLDevice >) device"
\fBNSSecureCoding\fP compatability  While the standard NSSecureCoding/NSCoding method -initWithCoder: should work, since the file can't know which device your data is allocated on, we have to guess and may guess incorrectly\&. To avoid that problem, use initWithCoder:device instead\&. 
.PP
\fBParameters:\fP
.RS 4
\fIaDecoder\fP The NSCoder subclass with your serialized \fBMPSKernel\fP 
.br
\fIdevice\fP The MTLDevice on which to make the \fBMPSKernel\fP 
.RE
.PP
\fBReturns:\fP
.RS 4
\fBA\fP new \fBMPSCNNInstanceNormalization\fP object, or nil if failure\&. 
.RE
.PP

.PP
Reimplemented from \fBMPSCNNKernel\fP\&.
.SS "\- (nonnull instancetype) initWithDevice: (nonnull id< MTLDevice >) device"
Use initWithDevice:dataSource instead 
.PP
Reimplemented from \fBMPSCNNKernel\fP\&.
.SS "\- (nonnull instancetype) \fBinitWithDevice:\fP (nonnull id< MTLDevice >) device(nonnull id< \fBMPSCNNInstanceNormalizationDataSource\fP >) dataSource"
Initialize a \fBMPSCNNInstanceNormalization\fP kernel on a device\&. 
.PP
\fBParameters:\fP
.RS 4
\fIdataSource\fP An object conforming to the \fBMPSCNNInstanceNormalizationDataSource\fP protocol which 
.RE
.PP

.SS "\- (void) reloadDataSource: (__nonnull id< \fBMPSCNNInstanceNormalizationDataSource\fP >) dataSource"
Reload data using a data source\&.
.PP
\fBParameters:\fP
.RS 4
\fIdataSource\fP The data source which will provide the gamma and beta terms to scale and bias the normalized result respectively\&. 
.RE
.PP

.SS "\- (void) reloadGammaAndBetaFromDataSource "
Reinitialize the filter using the data source provided at kernel initialization\&. 
.SS "\- (void) reloadGammaAndBetaWithCommandBuffer: (__nonnull id< MTLCommandBuffer >) commandBuffer(\fBMPSCNNNormalizationGammaAndBetaState\fP *__nonnull) gammaAndBetaState"
Reload data using new gamma and beta terms contained within an \fBMPSCNNInstanceNormalizationGradientState\fP object\&.
.PP
\fBParameters:\fP
.RS 4
\fIcommandBuffer\fP The command buffer on which to encode the reload\&.
.br
\fIgammaAndBetaState\fP The state containing the updated weights which are to be reloaded\&. 
.RE
.PP

.SS "\- (\fBMPSCNNInstanceNormalizationGradientState\fP * __nullable) resultStateForSourceImage: (\fBMPSImage\fP *__nonnull) sourceImage(NSArray< \fBMPSState\fP * > *__nullable) sourceStates(\fBMPSImage\fP *__nonnull) destinationImage"
Return a \fBMPSCNNInstanceNormalizationGradientState\fP object for the provided source image, source states, and destination image\&. 
.PP
Reimplemented from \fBMPSCNNKernel\fP\&.
.SS "\- (\fBMPSCNNInstanceNormalizationGradientState\fP * __nullable) temporaryResultStateForCommandBuffer: (nonnull id< MTLCommandBuffer >) commandBuffer(\fBMPSImage\fP *__nonnull) sourceImage(NSArray< \fBMPSState\fP * > *__nullable) sourceStates(\fBMPSImage\fP *__nonnull) destinationImage"
Return a temporary \fBMPSCNNInstanceNormalizationGradientState\fP object which may be used with a \fBMPSCNNInstanceNormalization\fP filter\&. 
.PP
Reimplemented from \fBMPSCNNKernel\fP\&.
.SH "Property Documentation"
.PP 
.SS "\- (id<\fBMPSCNNInstanceNormalizationDataSource\fP>) dataSource\fC [read]\fP, \fC [nonatomic]\fP, \fC [retain]\fP"
The data source that the object was initialized with 
.SS "\- epsilon\fC [read]\fP, \fC [write]\fP, \fC [nonatomic]\fP, \fC [assign]\fP"
The epsilon value used to bias the variance when normalizing\&. 

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