org.deeplearning4j.nn.conf.layers

Class GlobalPoolingLayer

java.lang.Object

org.deeplearning4j.nn.conf.layers.Layer

org.deeplearning4j.nn.conf.layers.GlobalPoolingLayer

All Implemented Interfaces:

java.io.Serializable, java.lang.Cloneable

public class GlobalPoolingLayer
extends Layer

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

Modifier and Type	Class and Description
static class	GlobalPoolingLayer.Builder

Field Summary

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

activationFn, adamMeanDecay, adamVarDecay, biasInit, biasLearningRate, dist, dropOut, epsilon, gradientNormalization, gradientNormalizationThreshold, l1, l1Bias, l2, l2Bias, layerName, learningRate, learningRateSchedule, momentum, momentumSchedule, rho, rmsDecay, updater, weightInit

Method Summary

Modifier and Type	Method and Description
double	getL1ByParam(java.lang.String paramName) Get the L1 coefficient for the given parameter.
double	getL2ByParam(java.lang.String paramName) Get the L2 coefficient for the given parameter.
double	getLearningRateByParam(java.lang.String paramName) Get the (initial) learning rate coefficient for the given parameter.
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
ParamInitializer	initializer()
Layer	instantiate(NeuralNetConfiguration conf, java.util.Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)
void	setNIn(InputType inputType, boolean override) Set the nIn value (number of inputs, or input depth for CNNs) based on the given input type

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

clone, getUpdaterByParam, resetLayerDefaultConfig

Methods inherited from class java.lang.Object

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

Method Detail

instantiate

public Layer instantiate(NeuralNetConfiguration conf,
                         java.util.Collection<IterationListener> iterationListeners,
                         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

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

setNIn

public void setNIn(InputType inputType,
                   boolean override)

Description copied from class: Layer

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

Specified by:

setNIn in class Layer

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.

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

getL1ByParam

public double getL1ByParam(java.lang.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

Specified by:

getL1ByParam in class Layer

Parameters:

paramName - Parameter name

Returns:

L1 value for that parameter

getL2ByParam

public double getL2ByParam(java.lang.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

Specified by:

getL2ByParam in class Layer

Parameters:

paramName - Parameter name

Returns:

L2 value for that parameter

getLearningRateByParam

public double getLearningRateByParam(java.lang.String paramName)

Description copied from class: Layer

Get the (initial) learning rate coefficient for the given parameter. Different parameters may be configured to have different learning rates, though commonly all parameters will have the same learning rate

Specified by:

getLearningRateByParam in class Layer

Parameters:

paramName - Parameter name

Returns:

Initial learning rate value for that parameter