Package org.deeplearning4j.nn.conf.layers.convolutional

Class Cropping2D

java.lang.Object

org.deeplearning4j.nn.conf.layers.Layer

org.deeplearning4j.nn.conf.layers.NoParamLayer

org.deeplearning4j.nn.conf.layers.convolutional.Cropping2D

All Implemented Interfaces:

Serializable, Cloneable, TrainingConfig

public class Cropping2D
extends NoParamLayer

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	Cropping2D.Builder

Field Summary

Fields inherited from class org.deeplearning4j.nn.conf.layers.Layer

constraints, iDropout, layerName

Constructor Summary

Constructors

Modifier	Constructor	Description
	Cropping2D(int[] cropping)
	Cropping2D(int cropTopBottom, int cropLeftRight)
	Cropping2D(int cropTop, int cropBottom, int cropLeft, int cropRight)
	Cropping2D(CNN2DFormat dataFormat, int cropTopBottom, int cropLeftRight)
	Cropping2D(CNN2DFormat format, int cropTop, int cropBottom, int cropLeft, int cropRight)
protected	Cropping2D(Cropping2D.Builder builder)

Method Summary

Modifier and Type	Method	Description
LayerMemoryReport	getMemoryReport(InputType inputType)	This is a report of the estimated memory consumption for the given layer
InputType	getOutputType(int layerIndex, InputType inputType)	For a given type of input to this layer, what is the type of the output?
InputPreProcessor	getPreProcessorForInputType(InputType inputType)	For the given type of input to this layer, what preprocessor (if any) is required? Returns null if no preprocessor is required, otherwise returns an appropriate InputPreProcessor for this layer, such as a CnnToFeedForwardPreProcessor
Layer	instantiate(NeuralNetConfiguration conf, Collection<TrainingListener> trainingListeners, int layerIndex, INDArray layerParamsView, boolean initializeParams, DataType networkDataType)
void	setNIn(InputType inputType, boolean override)	Set the nIn value (number of inputs, or input channels for CNNs) based on the given input type

Methods inherited from class org.deeplearning4j.nn.conf.layers.NoParamLayer

getGradientNormalization, getGradientNormalizationThreshold, getRegularizationByParam, initializer, isPretrainParam

Methods inherited from class org.deeplearning4j.nn.conf.layers.Layer

clone, getUpdaterByParam, initializeConstraints, resetLayerDefaultConfig, setDataType

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.deeplearning4j.nn.api.TrainingConfig

getLayerName

Constructor Detail

Cropping2D

public Cropping2D(int cropTopBottom,
                  int cropLeftRight)

Parameters:

cropTopBottom - Amount of cropping to apply to both the top and the bottom of the input activations

cropLeftRight - Amount of cropping to apply to both the left and the right of the input activations

Cropping2D

public Cropping2D(CNN2DFormat dataFormat,
                  int cropTopBottom,
                  int cropLeftRight)

Cropping2D

public Cropping2D(int cropTop,
                  int cropBottom,
                  int cropLeft,
                  int cropRight)

Parameters:

cropTop - Amount of cropping to apply to the top of the input activations

cropBottom - Amount of cropping to apply to the bottom of the input activations

cropLeft - Amount of cropping to apply to the left of the input activations

cropRight - Amount of cropping to apply to the right of the input activations

Cropping2D

public Cropping2D(CNN2DFormat format,
                  int cropTop,
                  int cropBottom,
                  int cropLeft,
                  int cropRight)

Cropping2D

public Cropping2D(int[] cropping)

Parameters:

cropping - Cropping as either a length 2 array, with values [cropTopBottom, cropLeftRight], or as a length 4 array, with values [cropTop, cropBottom, cropLeft, cropRight]

Cropping2D

protected Cropping2D(Cropping2D.Builder builder)

Method Detail

instantiate

public Layer instantiate(NeuralNetConfiguration conf,
                         Collection<TrainingListener> trainingListeners,
                         int layerIndex,
                         INDArray layerParamsView,
                         boolean initializeParams,
                         DataType networkDataType)

Specified by:

instantiate in class Layer

getOutputType

public InputType getOutputType(int layerIndex,
                               InputType inputType)

Description copied from class: Layer

For a given type of input to this layer, what is the type of the output?

Specified by:

getOutputType in class Layer

Parameters:

layerIndex - Index of the layer

inputType - Type of input for the layer

Returns:

Type of output from the layer

getPreProcessorForInputType

public InputPreProcessor getPreProcessorForInputType(InputType inputType)

Description copied from class: Layer

For the given type of input to this layer, what preprocessor (if any) is required?
Returns null if no preprocessor is required, otherwise returns an appropriate InputPreProcessor for this layer, such as a CnnToFeedForwardPreProcessor

Specified by:

getPreProcessorForInputType in class Layer

Parameters:

inputType - InputType to this layer

Returns:

Null if no preprocessor is required, otherwise the type of preprocessor necessary for this layer/input combination

getMemoryReport

public LayerMemoryReport getMemoryReport(InputType inputType)

Description copied from class: Layer

This is a report of the estimated memory consumption for the given layer

Specified by:

getMemoryReport in class Layer

Parameters:

inputType - Input type to the layer. Memory consumption is often a function of the input type

Returns:

Memory report for the layer

setNIn

public void setNIn(InputType inputType,
                   boolean override)

Description copied from class: Layer

Set the nIn value (number of inputs, or input channels for CNNs) based on the given input type

Overrides:

setNIn in class NoParamLayer

Parameters:

inputType - Input type for this layer

override - If false: only set the nIn value if it's not already set. If true: set it regardless of whether it's already set or not.