mpscnndropoutgradient(3) [mojave man page]

MPSCNNDropoutGradient(3)				 MetalPerformanceShaders.framework				  MPSCNNDropoutGradient(3)

NAME

       MPSCNNDropoutGradient

SYNOPSIS

       #import <MPSCNNDropout.h>

       Inherits MPSCNNGradientKernel.

   Instance Methods
       (nonnull instancetype) - initWithDevice:
       (nullable instancetype) - initWithCoder:device:
       (nonnull instancetype) - initWithDevice:keepProbability:seed:maskStrideInPixels:

   Properties
       float keepProbability
       NSUInteger seed
       MTLSize maskStrideInPixels

   Additional Inherited Members
Detailed Description
       This depends on Metal.framework	This filter is the backward filter for the MPSCNNDropout forward filter. It requires the mask data, along
       with all the associated parameters used to generate the mask, from the forward pass. The mask is associated with a
       MPSCNNDropoutGradientState object.

       In this kernel, use the secondaryOffset to apply an offset to the mask data.

Method Documentation
   - (nullable instancetype) initWithCoder: (NSCoder *__nonnull) aDecoder(nonnull id< MTLDevice >) device
       <NSSecureCoding> support

       Reimplemented from MPSCNNGradientKernel.

   - (nonnull instancetype) initWithDevice: (nonnull id< MTLDevice >) device
       Standard init with default properties per filter type

       Parameters:
	   device The device that the filter will be used on. May not be NULL.

       Returns:
	   A pointer to the newly initialized object. This will fail, returning nil if the device is not supported. Devices must be
	   MTLFeatureSet_iOS_GPUFamily2_v1 or later.

       Reimplemented from MPSCNNGradientKernel.

   - (nonnull instancetype) initWithDevice: (nonnull id< MTLDevice >) device(float) keepProbability(NSUInteger) seed(MTLSize) maskStrideInPixels
       Standard init with default properties per filter type.

       Parameters:
	   device The device that the filter will be used on.
	   keepProbability The probability that each element in the input is kept. The valid range is (0.0f, 1.0f).
	   seed The seed used to generate random numbers.
	   maskStrideInPixels The mask stride in the x, y, and z dimensions, which allows for the broadcasting of mask data. The only valid values
	   are 0 and 1 for each dimension. For no broadcasting, set the values for each dimension to 1. For broadcasting, set desired values to 0.

       Returns:
	   A valid MPSCNNDropoutGradient object or nil, if failure.

Property Documentation
   - keepProbability [read],  [nonatomic],  [assign]
       The probability that each element in the input is kept. The valid range is (0.0f, 1.0f).

   - maskStrideInPixels [read],  [nonatomic],  [assign]
       The mask stride in the x, y, and x dimensions, which allows for the broadcasting the mask data.	The only valid values are 0 and 1 for each
       dimension. For no broadcasting, set the values for each dimension to 1. For broadcasting, set desired values to 0.

   - seed [read],  [nonatomic],  [assign]
       The seed used to generate random numbers.

Author
       Generated automatically by Doxygen for MetalPerformanceShaders.framework from the source code.

Version MetalPerformanceShaders-100				  Thu Feb 8 2018					  MPSCNNDropoutGradient(3)

Check Out this Related Man Page

MPSCNNPoolingL2Norm(3)					 MetalPerformanceShaders.framework				    MPSCNNPoolingL2Norm(3)

NAME

       MPSCNNPoolingL2Norm

SYNOPSIS

       #import <MPSCNNPooling.h>

       Inherits MPSCNNPooling.

   Instance Methods
       (nonnull instancetype) - initWithDevice:kernelWidth:kernelHeight:strideInPixelsX:strideInPixelsY:
       (nullable instancetype) - initWithCoder:device:

   Additional Inherited Members
Detailed Description
       This depends on Metal.framework	Specifies the L2-norm pooling filter. For each pixel, returns L2-Norm of pixels in the kernelWidth x
       kernelHeight filter region. out[c,x,y] = sqrt ( sum_{dx,dy} in[c,x+dx,y+dy] * in[c,x+dx,y+dy] ).

Method Documentation
   - (nullable instancetype) initWithCoder: (NSCoder *__nonnull) aDecoder(nonnull id< MTLDevice >) device
       NSSecureCoding compatability  See MPSKernel::initWithCoder.

       Parameters:
	   aDecoder The NSCoder subclass with your serialized MPSCNNPooling
	   device The MTLDevice on which to make the MPSCNNPooling

       Returns:
	   A new MPSCNNPooling object, or nil if failure.

       Reimplemented from MPSCNNPooling.

   - (nonnull instancetype) initWithDevice: (nonnull id< MTLDevice >) device(NSUInteger) kernelWidth(NSUInteger) kernelHeight(NSUInteger)
       strideInPixelsX(NSUInteger) strideInPixelsY
       Initialize a MPSCNNPoolingL2Norm pooling filter

       Parameters:
	   device The device the filter will run on
	   kernelWidth The width of the kernel. Can be an odd or even value.
	   kernelHeight The height of the kernel. Can be an odd or even value.
	   strideInPixelsX The output stride (downsampling factor) in the x dimension.
	   strideInPixelsY The output stride (downsampling factor) in the y dimension.

       Returns:
	   A valid MPSCNNPooling object or nil, if failure.

       Reimplemented from MPSCNNPooling.

Author
       Generated automatically by Doxygen for MetalPerformanceShaders.framework from the source code.

Version MetalPerformanceShaders-100				  Thu Feb 8 2018					    MPSCNNPoolingL2Norm(3)

Linux and UNIX Man Pages

mpscnndropoutgradient(3) [mojave man page]

Check Out this Related Man Page