MPSNNConcatenationNode(3)

NAME

       MPSNNConcatenationNode

SYNOPSIS

       #import <MPSNNGraphNodes.h>

       Inherits MPSNNFilterNode.

   Instance Methods
       (nonnull instancetype) - initWithSources:

   Class Methods
       (nonnull instancetype) + nodeWithSources:

   Additional Inherited Members

Detailed Description

       Node representing a the concatenation (in the feature channel
       dimension) of the results from one or more kernels

Method Documentation

   - (nonnull instancetype) initWithSources: (NSArray< MPSNNImageNode * >
       *__nonnull) sourceNodes
       Init a node that concatenates feature channels from multiple images  In
       some neural network designs, it is necessary to append feature channels
       from one neural network filter to the results of another. If we have
       three image nodes with M, N and O feature channels in them, passed to
       -initWithSources: as @[imageM, imageN, imageO], then feature channels
       [0,M-1] will be drawn from image M, feature channels [M, M+N-1] will be
       drawn from image N and feature channels [M+N, M+N+O-1] will be drawn
       from image O.

       As all images are padded out to a multiple of four feature channels, M,
       N and O here are also multiples of four, even when the MPSImages are
       not. That is, if the image is 23 feature channels and one channel of
       padding, it takes up 24 feature channels worth of space in the
       concatenated result.

       Performance Note: Generally, concatenation is free as long as all of
       the sourceNodes are produced by filters in the same MPSNNGraph. Most
       MPSCNNKernels have the ability to write their results at a feature
       channel offset within a target MPSImage. However, if the MPSNNImageNode
       source nodes come from images external to the MPSNNGraph, then we have
       to do a copy operation to assemble the concatenated node. As a result,
       when deciding where to break a large logical graph into multiple
       smaller MPSNNGraphs, it is better for concatenations to appear at the
       ends of subgraphs when possible rather than at the start, to the extent
       that all the images used in the concatenation are produced by that
       subgraph.

       Parameters:
           sourceNodes The MPSNNImageNode representing the source MPSImages
           for the filter

       Returns:
           A new MPSNNFilter node that concatenates its inputs.



   + (nonnull instancetype) nodeWithSources: (NSArray< MPSNNImageNode * >
       *__nonnull) sourceNodes
       Init a autoreleased node that concatenates feature channels from
       multiple images  In some neural network designs, it is necessary to
       append feature channels from one neural network filter to the results
       of another. If we have three image nodes with M, N and O feature
       channels in them, passed to -initWithSources: as @[imageM, imageN,
       imageO], then feature channels [0,M-1] will be drawn from image M,
       feature channels [M, M+N-1] will be drawn from image N and feature
       channels [M+N, M+N+O-1] will be drawn from image O.

       As all images are padded out to a multiple of four feature channels, M,
       N and O here are also multiples of four, even when the MPSImages are
       not. That is, if the image is 23 feature channels and one channel of
       padding, it takes up 24 feature channels worth of space in the
       concatenated result.

       Performance Note: Generally, concatenation is free as long as all of
       the sourceNodes are produced by filters in the same MPSNNGraph. Most
       MPSCNNKernels have the ability to write their results at a feature
       channel offset within a target MPSImage. However, if the MPSNNImageNode
       source nodes come from images external to the MPSNNGraph, then we have
       to do a copy operation to assemble the concatenated node. As a result,
       when deciding where to break a large logical graph into multiple
       smaller MPSNNGraphs, it is better for concatenations to appear at the
       ends of subgraphs when possible rather than at the start, to the extent
       that all the images used in the concatenation are produced by that
       subgraph.

       Parameters:
           sourceNodes The MPSNNImageNode representing the source MPSImages
           for the filter

       Returns:
           A new MPSNNFilter node that concatenates its inputs.

Author

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





Version MetalPerformanceShaders-Thu2Jul 13 2017      MPSNNConcatenationNode(3)


Mac OS X 10.12.6 - Generated Tue Oct 31 15:33:05 CDT 2017