MPSNNFilterNode(3) MetalPerformanceShaders.framework MPSNNFilterNode(3)
NAME
MPSNNFilterNode
SYNOPSIS
#import <MPSNNGraphNodes.h>
Inherits NSObject.
Inherited by MPSCNNConvolutionNode, MPSCNNDilatedPoolingMaxNode,
MPSCNNLogSoftMaxNode, MPSCNNNeuronNode, MPSCNNNormalizationNode,
MPSCNNPoolingNode, MPSCNNSoftMaxNode, MPSCNNUpsamplingBilinearNode,
MPSCNNUpsamplingNearestNode, MPSNNBinaryArithmeticNode,
MPSNNConcatenationNode, and MPSNNScaleNode.
Instance Methods
(nonnull instancetype) - init
Properties
MPSNNImageNode * resultImage
MPSNNStateNode * resultState
NSArray< MPSNNStateNode * > * resultStates
id< MPSNNPadding > paddingPolicy
NSString * label
Detailed Description
A placeholder node denoting a neural network filter stage There are as
many MPSNNFilterNode subclasses as there are MPS neural network filter
objects. Make one of those. This class defines an polymorphic interface
for them.
Method Documentation
- (nonnull instancetype) init
Reimplemented in MPSCNNNeuronNode.
Property Documentation
- label [read], [write], [atomic], [copy]
A string to help identify this object.
- (id<MPSNNPadding>) paddingPolicy [read], [write], [nonatomic],
[retain]
The padding method used for the filter node The default value varies
per filter.
- (MPSNNImageNode*) resultImage [read], [nonatomic], [assign]
Get the node representing the image result of the filter Except where
otherwise noted, the precision used for the result image (see format
property) is copied from the precision from the first input image node.
- (MPSNNStateNode*) resultState [read], [nonatomic], [assign]
convenience method for resultStates[0] If resultStates is nil, returns
nil
- (NSArray<MPSNNStateNode*>*) resultStates [read], [nonatomic], [assign]
Get the node representing the state result of the filter If more than
one, see description of subclass for ordering.
Author
Generated automatically by Doxygen for
MetalPerformanceShaders.framework from the source code.
Version MetalPerformanceShaders-Thu2Jul 13 2017 MPSNNFilterNode(3)
Mac OS X 10.12.6 - Generated Tue Oct 31 16:17:16 CDT 2017