org.deeplearning4j.nn.layers.pooling

Class GlobalPoolingLayer

java.lang.Object

org.deeplearning4j.nn.layers.BaseLayer<GlobalPoolingLayer>

org.deeplearning4j.nn.layers.pooling.GlobalPoolingLayer

All Implemented Interfaces:

java.io.Serializable, java.lang.Cloneable, Layer, Model

public class GlobalPoolingLayer
extends BaseLayer<GlobalPoolingLayer>

Global pooling layer - used to do pooling over time for RNNs, and 2d pooling for CNNs.
Supports the following PoolingTypes: SUM, AVG, MAX, PNORM
Global pooling layer can also handle mask arrays when dealing with variable length inputs. Mask arrays are assumed to be 2d, and are fed forward through the network during training or post-training forward pass:
- Time series: mask arrays are shape [minibatchSize, maxTimeSeriesLength] and contain values 0 or 1 only
- CNNs: mask have shape [minibatchSize, height] or [minibatchSize, width]. Important: the current implementation assumes that for CNNs + variable length (masking), the input shape is [minibatchSize, depth, height, 1] or [minibatchSize, depth, 1, width] respectively. This is the case with global pooling in architectures like CNN for sentence classification.

Behaviour with default settings:
- 3d (time series) input with shape [minibatchSize, vectorSize, timeSeriesLength] -> 2d output [minibatchSize, vectorSize]
- 4d (CNN) input with shape [minibatchSize, depth, height, width] -> 2d output [minibatchSize, depth]

Alternatively, by setting collapseDimensions = false in the configuration, it is possible to retain the reduced dimensions as 1s: this gives [minibatchSize, vectorSize, 1] for RNN output, and [minibatchSize, depth, 1, 1] for CNN output.

See Also:

Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from interface org.deeplearning4j.nn.api.Layer

Layer.TrainingMode, Layer.Type

Field Summary

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

conf, dropoutApplied, dropoutMask, gradient, gradientsFlattened, gradientViews, index, input, iterationListeners, maskArray, maskState, optimizer, params, paramsFlattened, score, solver

Constructor Summary

Constructors

Constructor and Description
GlobalPoolingLayer(NeuralNetConfiguration conf)

Method Summary

Modifier and Type	Method and Description
org.nd4j.linalg.api.ndarray.INDArray	activate(boolean training) Trigger an activation with the last specified input
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon) Calculate the gradient relative to the error in the next layer
double	calcL1(boolean backpropParamsOnly) Calculate the l1 regularization term 0.0 if regularization is not used.
double	calcL2(boolean backpropParamsOnly) Calculate the l2 regularization term 0.0 if regularization is not used.
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray, MaskState currentMaskState, int minibatchSize) Feed forward the input mask array, setting in in the layer as appropriate.
boolean	isPretrainLayer() Returns true if the layer can be trained in an unsupervised/pretrain manner (VAE, RBMs etc)
Layer.Type	type() Returns the layer type

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

accumulateScore, activate, activate, activate, activate, activate, activationMean, applyDropOutIfNecessary, applyLearningRateScoreDecay, applyMask, batchSize, calcGradient, clear, clone, computeGradientAndScore, conf, createGradient, derivativeActivation, error, fit, fit, getIndex, getInput, getInputMiniBatchSize, getListeners, getMaskArray, getOptimizer, getParam, gradient, gradientAndScore, init, initParams, input, iterate, layerConf, layerNameAndIndex, merge, numParams, numParams, params, paramTable, paramTable, preOutput, preOutput, preOutput, preOutput, score, setBackpropGradientsViewArray, setConf, setIndex, setInput, setInputMiniBatchSize, setListeners, setListeners, setMaskArray, setParam, setParams, setParams, setParamsViewArray, setParamTable, setScoreWithZ, toString, transpose, update, update, validateInput

Methods inherited from class java.lang.Object

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

Constructor Detail

GlobalPoolingLayer

public GlobalPoolingLayer(NeuralNetConfiguration conf)

Method Detail

isPretrainLayer

public boolean isPretrainLayer()

Description copied from interface: Layer

Returns true if the layer can be trained in an unsupervised/pretrain manner (VAE, RBMs etc)

Returns:

true if the layer can be pretrained (using fit(INDArray), false otherwise

calcL2

public double calcL2(boolean backpropParamsOnly)

Description copied from interface: Layer

Calculate the l2 regularization term
0.0 if regularization is not used. Or 0.5 * l2Coeff * l2Magnitude otherwise.
Note that this does not divide by mini-batch size

Specified by:

calcL2 in interface Layer

Overrides:

calcL2 in class BaseLayer<GlobalPoolingLayer>

Parameters:

backpropParamsOnly - If true: calculate L2 based on backprop params only. If false: calculate based on all params (including pretrain params, if any)

Returns:

the l2 regularization term for this layer.

calcL1

public double calcL1(boolean backpropParamsOnly)

Description copied from interface: Layer

Calculate the l1 regularization term
0.0 if regularization is not used. Or l1Coeff * l1Magnitude otherwise.
Note that this does not divide by mini-batch size

Specified by:

calcL1 in interface Layer

Overrides:

calcL1 in class BaseLayer<GlobalPoolingLayer>

Parameters:

backpropParamsOnly - If true: calculate L1 based on backprop params only. If false: calculate based on all params (including pretrain params, if any)

Returns:

the l1 regularization term for this layer.

type

public Layer.Type type()

Description copied from interface: Layer

Returns the layer type

Specified by:

type in interface Layer

Overrides:

type in class BaseLayer<GlobalPoolingLayer>

Returns:

activate

public org.nd4j.linalg.api.ndarray.INDArray activate(boolean training)

Description copied from interface: Layer

Trigger an activation with the last specified input

Specified by:

activate in interface Layer

Overrides:

activate in class BaseLayer<GlobalPoolingLayer>

Parameters:

training - training or test mode

Returns:

the activation of the last specified input

backpropGradient

public Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray> backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)

Description copied from interface: Layer

Calculate the gradient relative to the error in the next layer

Specified by:

backpropGradient in interface Layer

Overrides:

backpropGradient in class BaseLayer<GlobalPoolingLayer>

Parameters:

epsilon - w^(L+1)*delta^(L+1). Or, equiv: dC/da, i.e., (dC/dz)*(dz/da) = dC/da, where C is cost function a=sigma(z) is activation.

Returns:

Pair where Gradient is gradient for this layer, INDArray is epsilon needed by next layer, but before element-wise multiply by sigmaPrime(z). So for standard feed-forward layer, if this layer is L, then return.getSecond() == (w^(L)*(delta^(L))^T)^T

feedForwardMaskArray

public Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState> feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray,
                                                                                 MaskState currentMaskState,
                                                                                 int minibatchSize)

Description copied from interface: Layer

Feed forward the input mask array, setting in in the layer as appropriate. This allows different layers to handle masks differently - for example, bidirectional RNNs and normal RNNs operate differently with masks (the former sets activations to 0 outside of the data present region (and keeps the mask active for future layers like dense layers), whereas normal RNNs don't zero out the activations/errors )instead relying on backpropagated error arrays to handle the variable length case.
This is also used for example for networks that contain global pooling layers, arbitrary preprocessors, etc.

Specified by:

feedForwardMaskArray in interface Layer

Overrides:

feedForwardMaskArray in class BaseLayer<GlobalPoolingLayer>

Parameters:

maskArray - Mask array to set

currentMaskState - Current state of the mask - see MaskState

minibatchSize - Current minibatch size. Needs to be known as it cannot always be inferred from the activations array due to reshaping (such as a DenseLayer within a recurrent neural network)

Returns:

New mask array after this layer, along with the new mask state.