boone.structure

Class ConvolutionMap

java.lang.Object

boone.structure.Layer

boone.structure.Map

boone.structure.FilterMap

boone.structure.ConvolutionMap

All Implemented Interfaces:

Storable, java.lang.Cloneable

public class ConvolutionMap
extends FilterMap

A convolution map. $Id$

Since:

February, 2022

Author:

Helmut A. Mayer

Field Summary

Fields inherited from class boone.structure.FilterMap

connectedFilters, filterHeight, filters, filterWidth, padHeight, padWidth, strideHeight, strideWidth

Fields inherited from class boone.structure.Map

height, link, neuron, neurons, width

Constructor Summary

Constructors

Constructor and Description
ConvolutionMap(int filterWidth, int filterHeight, int padWidth, int padHeight, int strideWidth, int strideHeight, Neuron neuron, Link link) Constructs a general convolution layer.
ConvolutionMap(Map map) Constructs a map copy.

Method Summary

Modifier and Type	Method and Description
ConvolutionMap	clone() Returns a semi-deep clone of this map.
java.lang.String	toString() Returns the type(width x height) of this map.

Methods inherited from class boone.structure.FilterMap

attachFilter, connect, createFilter, getFilterHeight, getFilterLink, getFilters, getFilterWidth, getPadHeight, getPadWidth, getStrideHeight, getStrideWidth

Methods inherited from class boone.structure.Map

connect, disconnect, getDepth, getHeight, getLinkCount, getNeuron, getNeuron, getNeurons, getSize, getWidth, reset, setIOType, toXML

Methods inherited from class boone.structure.Layer

addMap, addMap, fromXML, getLevel, getMapCount, getMaps, getNeuron, removeMap, setLevel

Methods inherited from class java.lang.Object

equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Constructor Detail

ConvolutionMap

public ConvolutionMap(int filterWidth,
                      int filterHeight,
                      int padWidth,
                      int padHeight,
                      int strideWidth,
                      int strideHeight,
                      Neuron neuron,
                      Link link)

Constructs a general convolution layer. Note that after construction the layer contains no neurons, as they are determined when connecting the layer.

Parameters:

filterWidth - the width of the filter

filterHeight - the height of the filter

padWidth - the width of the pad

padHeight - the height of the pad

strideWidth - the width of the stride

strideHeight - the height of the stride

neuron - the neuron type (if null, default neuron)

link - the link type (if null, default link)

ConvolutionMap

public ConvolutionMap(Map map)

Constructs a map copy. The neurons in the map and all the links are cloned. The links are set up according to the original map. However, sink or source of the links are only set, if the original neuron was also sink or source. If the link was connected to a non-map neuron, it is not connected in the cloned map.

Parameters:

map - the map to be copied

Method Detail

clone

public ConvolutionMap clone()

Returns a semi-deep clone of this map.

Overrides:

clone in class Map

Returns:

the clone

toString

public java.lang.String toString()

Returns the type(width x height) of this map.

Overrides:

toString in class Map

Returns:

the string expression