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

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

.in +1c
.ti -1c
.RI "(nonnull \fBMPSCNNLossDescriptor\fP *) + \fBcnnLossDescriptorWithType:reductionType:\fP"
.br
.in -1c
.SS "Properties"

.in +1c
.ti -1c
.RI "\fBMPSCNNLossType\fP \fBlossType\fP"
.br
.ti -1c
.RI "\fBMPSCNNReductionType\fP \fBreductionType\fP"
.br
.ti -1c
.RI "float \fBweight\fP"
.br
.ti -1c
.RI "float \fBlabelSmoothing\fP"
.br
.ti -1c
.RI "NSUInteger \fBnumberOfClasses\fP"
.br
.ti -1c
.RI "float \fBepsilon\fP"
.br
.ti -1c
.RI "float \fBdelta\fP"
.br
.in -1c
.SH "Detailed Description"
.PP 
This depends on Metal\&.framework\&.  The \fBMPSCNNLossDescriptor\fP specifies a loss filter descriptor\&. The same descriptor can be used to initialize both the \fBMPSCNNLoss\fP and the MPSCNNLossGradient filters\&. 
.SH "Method Documentation"
.PP 
.SS "+ (nonnull \fBMPSCNNLossDescriptor\fP*) cnnLossDescriptorWithType: (\fBMPSCNNLossType\fP) lossType(\fBMPSCNNReductionType\fP) reductionType"
Make a descriptor for a \fBMPSCNNLoss\fP or MPSCNNLossGradient object\&. 
.PP
\fBParameters:\fP
.RS 4
\fIlossType\fP The type of a loss filter\&. 
.br
\fIreductionType\fP The type of a reduction operation to apply\&. This argument is ignored in the MPSCNNLossGradient filter\&. 
.RE
.PP
\fBReturns:\fP
.RS 4
\fBA\fP valid \fBMPSCNNLossDescriptor\fP object or nil, if failure\&. 
.RE
.PP

.SS "\- (nonnull instancetype) init "

.SH "Property Documentation"
.PP 
.SS "\- delta\fC [read]\fP, \fC [write]\fP, \fC [nonatomic]\fP, \fC [assign]\fP"
The delta parameter\&. The default value is 1\&.0f\&.  This parameter is valid only for the loss functions of the following type(s): MPSCNNLossTypeHuber\&.
.PP
Given predictions and labels (ground truth), it is applied in the following way: if (|predictions - labels| <= delta, loss = 0\&.5f * predictions^2 if (|predictions - labels| > delta, loss = 0\&.5 * delta^2 + delta * (|predictions - labels| - delta) 
.SS "\- epsilon\fC [read]\fP, \fC [write]\fP, \fC [nonatomic]\fP, \fC [assign]\fP"
The epsilon parameter\&. The default value is 1e-7\&.  This parameter is valid only for the loss functions of the following type(s): MPSCNNLossTypeLog\&.
.PP
Given predictions and labels (ground truth), it is applied in the following way: -(labels * log(predictions + epsilon)) - ((1 - labels) * log(1 - predictions + epsilon)) 
.SS "\- labelSmoothing\fC [read]\fP, \fC [write]\fP, \fC [nonatomic]\fP, \fC [assign]\fP"
The label smoothing parameter\&. The default value is 0\&.0f\&.  This parameter is valid only for the loss functions of the following type(s): MPSCNNLossFunctionTypeSoftmaxCrossEntropy, MPSCNNLossFunctionTypeSigmoidCrossEntropy\&.
.PP
MPSCNNLossFunctionTypeSoftmaxCrossEntropy: given labels (ground truth), it is applied in the following way: labels = labelSmoothing > 0 ? labels * (1 - labelSmoothing) + labelSmoothing / numberOfClasses : labels
.PP
MPSCNNLossFunctionTypeSigmoidCrossEntropy: given labels (ground truth), it is applied in the following way: labels = labelSmoothing > 0 ? labels * (1 - labelSmoothing) + 0\&.5 * labelSmoothing : labels 
.SS "\- lossType\fC [read]\fP, \fC [write]\fP, \fC [nonatomic]\fP, \fC [assign]\fP"
The type of a loss filter\&.  This parameter specifies the type of a loss filter\&. 
.SS "\- numberOfClasses\fC [read]\fP, \fC [write]\fP, \fC [nonatomic]\fP, \fC [assign]\fP"
The number of classes parameter\&. The default value is 1\&.  This parameter is valid only for the loss functions of the following type(s): MPSCNNLossFunctionTypeSoftmaxCrossEntropy\&.
.PP
Given labels (ground truth), it is applied in the following way: labels = labelSmoothing > 0 ? labels * (1 - labelSmoothing) + labelSmoothing / numberOfClasses : labels 
.SS "\- reductionType\fC [read]\fP, \fC [write]\fP, \fC [nonatomic]\fP, \fC [assign]\fP"
The type of a reduction operation performed in the loss filter\&.  This parameter specifies the type of a reduction operation performed in the loss filter\&. 
.SS "\- weight\fC [read]\fP, \fC [write]\fP, \fC [nonatomic]\fP, \fC [assign]\fP"
The scale factor to apply to each element of a result\&.  Each element of a result is multiplied by the weight value\&. The default value is 1\&.0f\&. 

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