Layer

java.lang.Object
- org.deeplearning4j.nn.conf.layers.Layer

All Implemented Interfaces:

java.io.Serializable, java.lang.Cloneable

Direct Known Subclasses:

FeedForwardLayer, GlobalPoolingLayer, LocalResponseNormalization, SubsamplingLayer, ZeroPaddingLayer
```
public abstract class Layer
extends java.lang.Object
implements java.io.Serializable, java.lang.Cloneable
```
A neural network layer.

See Also:

Serialized Form

Nested Class Summary

Nested Classes
Modifier and Type Class and Description

static class Layer.Builder<T extends Layer.Builder<T>>

Nested Classes
Modifier and Type	Class and Description
`static class`	`Layer.Builder<T extends Layer.Builder<T>>`

Field Summary

Fields
Modifier and Type	Field and Description
`protected org.nd4j.linalg.activations.IActivation`	`activationFn`
`protected double`	`adamMeanDecay`
`protected double`	`adamVarDecay`
`protected double`	`biasInit`
`protected double`	`biasLearningRate`
`protected Distribution`	`dist`
`protected double`	`dropOut`
`protected double`	`epsilon`
`protected GradientNormalization`	`gradientNormalization`
`protected double`	`gradientNormalizationThreshold`
`protected double`	`l1`
`protected double`	`l1Bias`
`protected double`	`l2`
`protected double`	`l2Bias`
`protected java.lang.String`	`layerName`
`protected double`	`learningRate`
`protected java.util.Map<java.lang.Integer,java.lang.Double>`	`learningRateSchedule`
`protected double`	`momentum`
`protected java.util.Map<java.lang.Integer,java.lang.Double>`	`momentumSchedule`
`protected double`	`rho`
`protected double`	`rmsDecay`
`protected Updater`	`updater`
`protected WeightInit`	`weightInit`

Constructor Summary

Constructors
Constructor and Description

Layer(Layer.Builder builder)

Constructors
Constructor and Description
`Layer(Layer.Builder builder)`

Method Summary

All Methods Instance Methods Abstract Methods Concrete Methods
Modifier and Type	Method and Description
`Layer`	`clone()`
`abstract double`	`getL1ByParam(java.lang.String paramName)` Get the L1 coefficient for the given parameter.
`abstract double`	`getL2ByParam(java.lang.String paramName)` Get the L2 coefficient for the given parameter.
`abstract double`	`getLearningRateByParam(java.lang.String paramName)` Get the (initial) learning rate coefficient for the given parameter.
`abstract InputType`	`getOutputType(int layerIndex, InputType inputType)` For a given type of input to this layer, what is the type of the output?
`abstract 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`
`Updater`	`getUpdaterByParam(java.lang.String paramName)` Get the updater for the given parameter.
`abstract ParamInitializer`	`initializer()`
`abstract Layer`	`instantiate(NeuralNetConfiguration conf, java.util.Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)`
`void`	`resetLayerDefaultConfig()` Reset the learning related configs of the layer to default.
`abstract 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 java.lang.Object
equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Field Detail
  - layerName
```
protected java.lang.String layerName
```
  - activationFn
```
protected org.nd4j.linalg.activations.IActivation activationFn
```
  - weightInit
```
protected WeightInit weightInit
```
  - biasInit
```
protected double biasInit
```
  - dist
```
protected Distribution dist
```
  - learningRate
```
protected double learningRate
```
  - biasLearningRate
```
protected double biasLearningRate
```
  - learningRateSchedule
```
protected java.util.Map<java.lang.Integer,java.lang.Double> learningRateSchedule
```
  - momentum
```
protected double momentum
```
  - momentumSchedule
```
protected java.util.Map<java.lang.Integer,java.lang.Double> momentumSchedule
```
  - l1
```
protected double l1
```
  - l2
```
protected double l2
```
  - l1Bias
```
protected double l1Bias
```
  - l2Bias
```
protected double l2Bias
```
  - dropOut
```
protected double dropOut
```
  - updater
```
protected Updater updater
```
  - rho
```
protected double rho
```
  - epsilon
```
protected double epsilon
```
  - rmsDecay
```
protected double rmsDecay
```
  - adamMeanDecay
```
protected double adamMeanDecay
```
  - adamVarDecay
```
protected double adamVarDecay
```
  - gradientNormalization
```
protected GradientNormalization gradientNormalization
```
  - gradientNormalizationThreshold
```
protected double gradientNormalizationThreshold
```
- Constructor Detail
  - Layer
```
public Layer(Layer.Builder builder)
```
- Method Detail
  - resetLayerDefaultConfig
```
public void resetLayerDefaultConfig()
```
    Reset the learning related configs of the layer to default. When instantiated with a global neural network configuration the parameters specified in the neural network configuration will be used. For internal use with the transfer learning API. Users should not have to call this method directly.
  - clone
```
public Layer clone()
```
    Overrides:
    
    clone in class java.lang.Object
  - instantiate
```
public abstract Layer instantiate(NeuralNetConfiguration conf,
                                  java.util.Collection<IterationListener> iterationListeners,
                                  int layerIndex,
                                  org.nd4j.linalg.api.ndarray.INDArray layerParamsView,
                                  boolean initializeParams)
```
  - initializer
```
public abstract ParamInitializer initializer()
```
  - getOutputType
```
public abstract InputType getOutputType(int layerIndex,
                                        InputType inputType)
```
    For a given type of input to this layer, what is the type of the output?
    
    Parameters:
    
    layerIndex - Index of the layer
    
    inputType - Type of input for the layer
    
    Returns:
    
    Type of output from the layer
    
    Throws:
    
    java.lang.IllegalStateException - if input type is invalid for this layer
  - setNIn
```
public abstract void setNIn(InputType inputType,
                            boolean override)
```
    Set the nIn value (number of inputs, or input depth for CNNs) based on the given input type
    
    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.
    
    Throws:
    
    java.lang.IllegalStateException - if input type is invalid for this layer
  - getPreProcessorForInputType
```
public abstract 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
    
    Parameters:
    
    inputType - InputType to this layer
    
    Returns:
    
    Null if no preprocessor is required, otherwise the type of preprocessor necessary for this layer/input combination
    
    Throws:
    
    java.lang.IllegalStateException - if input type is invalid for this layer
  - getL1ByParam
```
public abstract double getL1ByParam(java.lang.String paramName)
```
    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
    
    Parameters:
    
    paramName - Parameter name
    
    Returns:
    
    L1 value for that parameter
  - getL2ByParam
```
public abstract double getL2ByParam(java.lang.String paramName)
```
    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
    
    Parameters:
    
    paramName - Parameter name
    
    Returns:
    
    L2 value for that parameter
  - getLearningRateByParam
```
public abstract double getLearningRateByParam(java.lang.String paramName)
```
    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
    
    Parameters:
    
    paramName - Parameter name
    
    Returns:
    
    Initial learning rate value for that parameter
  - getUpdaterByParam
```
public Updater getUpdaterByParam(java.lang.String paramName)
```
    Get the updater for the given parameter. Typically the same updater will be used for all updaters, but this is not necessarily the case
    
    Parameters:
    
    paramName - Parameter name
    
    Returns:
    
    Updater for the parameter

Class Layer

Nested Class Summary

Field Summary

Constructor Summary

Method Summary

Methods inherited from class java.lang.Object

Field Detail

layerName

activationFn

weightInit

biasInit

dist

learningRate

biasLearningRate

learningRateSchedule

momentum

momentumSchedule

l1

l2

l1Bias

l2Bias

dropOut

updater

rho

epsilon

rmsDecay

adamMeanDecay

adamVarDecay

gradientNormalization

gradientNormalizationThreshold

Constructor Detail

Layer

Method Detail

resetLayerDefaultConfig

clone

instantiate

initializer

getOutputType

setNIn

getPreProcessorForInputType

getL1ByParam

getL2ByParam

getLearningRateByParam

getUpdaterByParam