org.deeplearning4j.nn.conf.layers

Class CenterLossOutputLayer

java.lang.Object

org.deeplearning4j.nn.conf.layers.Layer

org.deeplearning4j.nn.conf.layers.BaseLayer

org.deeplearning4j.nn.conf.layers.FeedForwardLayer

org.deeplearning4j.nn.conf.layers.BaseOutputLayer

org.deeplearning4j.nn.conf.layers.CenterLossOutputLayer

All Implemented Interfaces:

Serializable, Cloneable

public class CenterLossOutputLayer
extends BaseOutputLayer

Center loss is similar to triplet loss except that it enforces intraclass consistency and doesn't require feed forward of multiple examples. Center loss typically converges faster for training ImageNet-based convolutional networks. "If example x is in class Y, ensure that embedding(x) is close to average(embedding(y)) for all examples y in Y"

Author:

Justin Long (@crockpotveggies), Alex Black (@AlexDBlack)

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	CenterLossOutputLayer.Builder

Field Summary

Fields

Modifier and Type	Field and Description
protected double	alpha
protected boolean	gradientCheck
protected double	lambda

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

hasBias, lossFn

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

nIn, nOut

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

activationFn, biasInit, biasUpdater, dist, gradientNormalization, gradientNormalizationThreshold, iUpdater, l1, l1Bias, l2, l2Bias, weightInit, weightNoise

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

constraints, iDropout, layerName

Constructor Summary

Constructors

Modifier	Constructor and Description
protected	CenterLossOutputLayer(CenterLossOutputLayer.Builder builder)

Method Summary

Modifier and Type	Method and Description
double	getAlpha()
boolean	getGradientCheck()
double	getL1ByParam(String paramName) Get the L1 coefficient for the given parameter.
double	getL2ByParam(String paramName) Get the L2 coefficient for the given parameter.
double	getLambda()
LayerMemoryReport	getMemoryReport(InputType inputType) This is a report of the estimated memory consumption for the given layer
org.nd4j.linalg.learning.config.IUpdater	getUpdaterByParam(String paramName) Get the updater for the given parameter.
ParamInitializer	initializer()
Layer	instantiate(NeuralNetConfiguration conf, Collection<TrainingListener> trainingListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)

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

hasBias

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

getOutputType, getPreProcessorForInputType, isPretrainParam, setNIn

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

clone, resetLayerDefaultConfig

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

initializeConstraints

Methods inherited from class java.lang.Object

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

Field Detail

alpha

protected double alpha

lambda

protected double lambda

gradientCheck

protected boolean gradientCheck

Constructor Detail

CenterLossOutputLayer

protected CenterLossOutputLayer(CenterLossOutputLayer.Builder builder)

Method Detail

instantiate

public Layer instantiate(NeuralNetConfiguration conf,
                         Collection<TrainingListener> trainingListeners,
                         int layerIndex,
                         org.nd4j.linalg.api.ndarray.INDArray layerParamsView,
                         boolean initializeParams)

Specified by:

instantiate in class Layer

initializer

public ParamInitializer initializer()

Specified by:

initializer in class Layer

Returns:

The parameter initializer for this model

getUpdaterByParam

public org.nd4j.linalg.learning.config.IUpdater getUpdaterByParam(String paramName)

Description copied from class: BaseLayer

Get the updater for the given parameter. Typically the same updater will be used for all updaters, but this is not necessarily the case

Overrides:

getUpdaterByParam in class BaseLayer

Parameters:

paramName - Parameter name

Returns:

IUpdater for the parameter

getL1ByParam

public double getL1ByParam(String paramName)

Description copied from class: Layer

Get the L1 coefficient for the given parameter. Different parameters may have different L1 values, even for a single .l1(x) configuration. For example, biases generally aren't L1 regularized, even if weights are

Overrides:

getL1ByParam in class FeedForwardLayer

Parameters:

paramName - Parameter name

Returns:

L1 value for that parameter

getL2ByParam

public double getL2ByParam(String paramName)

Description copied from class: Layer

Get the L2 coefficient for the given parameter. Different parameters may have different L2 values, even for a single .l2(x) configuration. For example, biases generally aren't L1 regularized, even if weights are

Overrides:

getL2ByParam in class FeedForwardLayer

Parameters:

paramName - Parameter name

Returns:

L2 value for that parameter

getAlpha

public double getAlpha()

getLambda

public double getLambda()

getGradientCheck

public boolean getGradientCheck()

getMemoryReport

public LayerMemoryReport getMemoryReport(InputType inputType)

Description copied from class: Layer

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

Overrides:

getMemoryReport in class BaseOutputLayer

Parameters:

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

Returns:

Memory report for the layer