BaseLayer.Builder (deeplearning4j-nn 0.9.0 API)

java.lang.Object
- org.deeplearning4j.nn.conf.layers.Layer.Builder<T>
- - org.deeplearning4j.nn.conf.layers.BaseLayer.Builder<T>

Direct Known Subclasses:: FeedForwardLayer.Builder

Enclosing class:: BaseLayer

public abstract static class BaseLayer.Builder<T extends BaseLayer.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` Deprecated.
`protected double`	`adamVarDecay` Deprecated.
`protected double`	`biasInit`
`protected double`	`biasLearningRate`
`protected Distribution`	`dist`
`protected double`	`epsilon` Deprecated.
`protected GradientNormalization`	`gradientNormalization`
`protected double`	`gradientNormalizationThreshold`
`protected org.nd4j.linalg.learning.config.IUpdater`	`iupdater`
`protected double`	`l1`
`protected double`	`l1Bias`
`protected double`	`l2`
`protected double`	`l2Bias`
`protected double`	`learningRate`
`protected LearningRatePolicy`	`learningRatePolicy`
`protected Map<Integer,Double>`	`learningRateSchedule`
`protected double`	`momentum` Deprecated.
`protected Map<Integer,Double>`	`momentumAfter` Deprecated.
`protected double`	`rho` Deprecated.
`protected double`	`rmsDecay` Deprecated.
`protected Updater`	`updater` Deprecated.
`protected WeightInit`	`weightInit`

Fields inherited from class org.deeplearning4j.nn.conf.layers.Layer.Builder
dropOut, layerName

Constructor Summary

Constructors
Constructor and Description

Builder()

Constructors
Constructor and Description
`Builder()`

Method Summary

All Methods Instance Methods Concrete Methods Deprecated Methods
Modifier and Type	Method and Description
`T`	`activation(org.nd4j.linalg.activations.Activation activation)`
`T`	`activation(org.nd4j.linalg.activations.IActivation activationFunction)`
`T`	`activation(String activationFunction)` Deprecated. Use `activation(Activation)` or `@activation(IActivation)`
`T`	`adamMeanDecay(double adamMeanDecay)` Deprecated. use `.updater(Adam.builder().beta1(adamMeanDecay).build())` intead
`T`	`adamVarDecay(double adamVarDecay)` Deprecated. use `.updater(Adam.builder().beta2(adamVarDecay).build())` intead
`T`	`biasInit(double biasInit)`
`T`	`biasLearningRate(double biasLearningRate)` Bias learning rate.
`T`	`dist(Distribution dist)` Distribution to sample initial weights from.
`T`	`epsilon(double epsilon)` Deprecated. Use use `.updater(Adam.builder().epsilon(epsilon).build())` or similar instead
`T`	`gradientNormalization(GradientNormalization gradientNormalization)` Gradient normalization strategy.
`T`	`gradientNormalizationThreshold(double threshold)` Threshold for gradient normalization, only used for GradientNormalization.ClipL2PerLayer, GradientNormalization.ClipL2PerParamType, and GradientNormalization.ClipElementWiseAbsoluteValue Not used otherwise. L2 threshold for first two types of clipping, or absolute value threshold for last type of clipping.
`T`	`l1(double l1)` L1 regularization coefficient (weights only).
`T`	`l1Bias(double l1Bias)` L1 regularization coefficient for the bias.
`T`	`l2(double l2)` L2 regularization coefficient (weights only).
`T`	`l2Bias(double l2Bias)` L2 regularization coefficient for the bias.
`T`	`learningRate(double learningRate)` Learning rate.
`T`	`learningRateDecayPolicy(LearningRatePolicy policy)` Learning rate decay policy.
`T`	`learningRateSchedule(Map<Integer,Double> learningRateSchedule)` Learning rate schedule.
`T`	`momentum(double momentum)` Deprecated. Use `.updater(new Nesterov(momentum))` instead
`T`	`momentumAfter(Map<Integer,Double> momentumAfter)` Deprecated. Use `.updater(Nesterov.builder().momentumSchedule(schedule).build())` instead
`T`	`rho(double rho)` Deprecated. use `.updater(new AdaDelta(rho,epsilon))` intead
`T`	`rmsDecay(double rmsDecay)` Deprecated. use `.updater(new RmsProp(rmsDecay))` instead
`T`	`updater(org.nd4j.linalg.learning.config.IUpdater updater)` Gradient updater.
`T`	`updater(Updater updater)` Gradient updater.
`T`	`weightInit(WeightInit weightInit)` Weight initialization scheme.

Methods inherited from class org.deeplearning4j.nn.conf.layers.Layer.Builder
build, dropOut, name

Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Field Detail
  - 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 Map<Integer,Double> learningRateSchedule
```
  - momentum
```
@Deprecated
protected double momentum
```
    Deprecated.
  - momentumAfter
```
@Deprecated
protected Map<Integer,Double> momentumAfter
```
    Deprecated.
  - l1
```
protected double l1
```
  - l2
```
protected double l2
```
  - l1Bias
```
protected double l1Bias
```
  - l2Bias
```
protected double l2Bias
```
  - updater
```
@Deprecated
protected Updater updater
```
    Deprecated.
  - iupdater
```
protected org.nd4j.linalg.learning.config.IUpdater iupdater
```
  - rho
```
@Deprecated
protected double rho
```
    Deprecated.
  - epsilon
```
@Deprecated
protected double epsilon
```
    Deprecated.
  - rmsDecay
```
@Deprecated
protected double rmsDecay
```
    Deprecated.
  - adamMeanDecay
```
@Deprecated
protected double adamMeanDecay
```
    Deprecated.
  - adamVarDecay
```
@Deprecated
protected double adamVarDecay
```
    Deprecated.
  - gradientNormalization
```
protected GradientNormalization gradientNormalization
```
  - gradientNormalizationThreshold
```
protected double gradientNormalizationThreshold
```
  - learningRatePolicy
```
protected LearningRatePolicy learningRatePolicy
```
- Constructor Detail
  - Builder
```
public Builder()
```
- Method Detail
  - activation
```
@Deprecated
public T activation(String activationFunction)
```
    Deprecated. Use activation(Activation) or @activation(IActivation)
    
    Layer activation function. Typical values include:
    "relu" (rectified linear), "tanh", "sigmoid", "softmax", "hardtanh", "leakyrelu", "maxout", "softsign", "softplus"
  - activation
```
public T activation(org.nd4j.linalg.activations.IActivation activationFunction)
```
  - activation
```
public T activation(org.nd4j.linalg.activations.Activation activation)
```
  - weightInit
```
public T weightInit(WeightInit weightInit)
```
    Weight initialization scheme.
    
    See Also:
    
    WeightInit
  - biasInit
```
public T biasInit(double biasInit)
```
  - dist
```
public T dist(Distribution dist)
```
    Distribution to sample initial weights from. Used in conjunction with .weightInit(WeightInit.DISTRIBUTION).
  - learningRate
```
public T learningRate(double learningRate)
```
    Learning rate. Defaults to 1e-1
  - biasLearningRate
```
public T biasLearningRate(double biasLearningRate)
```
    Bias learning rate. Set this to apply a different learning rate to the bias
  - learningRateSchedule
```
public T learningRateSchedule(Map<Integer,Double> learningRateSchedule)
```
    Learning rate schedule. Map of the iteration to the learning rate to apply at that iteration.
  - l1
```
public T l1(double l1)
```
    L1 regularization coefficient (weights only). Use l1Bias(double) to configure the l1 regularization coefficient for the bias.
  - l2
```
public T l2(double l2)
```
    L2 regularization coefficient (weights only). Use l2Bias(double) to configure the l2 regularization coefficient for the bias.
  - l1Bias
```
public T l1Bias(double l1Bias)
```
    L1 regularization coefficient for the bias. Default: 0. See also l1(double)
  - l2Bias
```
public T l2Bias(double l2Bias)
```
    L2 regularization coefficient for the bias. Default: 0. See also l2(double)
  - momentum
```
@Deprecated
public T momentum(double momentum)
```
    Deprecated. Use .updater(new Nesterov(momentum)) instead
    
    Momentum rate.
  - momentumAfter
```
@Deprecated
public T momentumAfter(Map<Integer,Double> momentumAfter)
```
    Deprecated. Use .updater(Nesterov.builder().momentumSchedule(schedule).build()) instead
    
    Momentum schedule. Map of the iteration to the momentum rate to apply at that iteration.
  - updater
```
public T updater(Updater updater)
```
    Gradient updater. For example, SGD for standard stochastic gradient descent, NESTEROV for Nesterov momentum, RSMPROP for RMSProp, etc.
    
    See Also:
    
    Updater
  - updater
```
public T updater(org.nd4j.linalg.learning.config.IUpdater updater)
```
    Gradient updater. For example, Adam or Nesterovs
    
    Parameters:
    
    updater - Updater to use
  - rho
```
@Deprecated
public T rho(double rho)
```
    Deprecated. use .updater(new AdaDelta(rho,epsilon)) intead
    
    Ada delta coefficient, rho. Only applies if using .updater(Updater.ADADELTA)
    
    Parameters:
    
    rho -
  - rmsDecay
```
@Deprecated
public T rmsDecay(double rmsDecay)
```
    Deprecated. use .updater(new RmsProp(rmsDecay)) instead
    
    Decay rate for RMSProp. Only applies if using .updater(Updater.RMSPROP)
  - epsilon
```
@Deprecated
public T epsilon(double epsilon)
```
    Deprecated. Use use .updater(Adam.builder().epsilon(epsilon).build()) or similar instead
    
    Epsilon value for updaters: Adam, RMSProp, Adagrad, Adadelta
    
    Parameters:
    
    epsilon - Epsilon value to use
  - adamMeanDecay
```
@Deprecated
public T adamMeanDecay(double adamMeanDecay)
```
    Deprecated. use .updater(Adam.builder().beta1(adamMeanDecay).build()) intead
    
    Mean decay rate for Adam updater. Only applies if using .updater(Updater.ADAM)
  - adamVarDecay
```
@Deprecated
public T adamVarDecay(double adamVarDecay)
```
    Deprecated. use .updater(Adam.builder().beta2(adamVarDecay).build()) intead
    
    Variance decay rate for Adam updater. Only applies if using .updater(Updater.ADAM)
  - gradientNormalization
```
public T gradientNormalization(GradientNormalization gradientNormalization)
```
    Gradient normalization strategy. Used to specify gradient renormalization, gradient clipping etc.
    
    Parameters:
    
    gradientNormalization - Type of normalization to use. Defaults to None.
    
    See Also:
    
    GradientNormalization
  - gradientNormalizationThreshold
```
public T gradientNormalizationThreshold(double threshold)
```
    Threshold for gradient normalization, only used for GradientNormalization.ClipL2PerLayer, GradientNormalization.ClipL2PerParamType, and GradientNormalization.ClipElementWiseAbsoluteValue
    Not used otherwise.
    L2 threshold for first two types of clipping, or absolute value threshold for last type of clipping.
  - learningRateDecayPolicy
```
public T learningRateDecayPolicy(LearningRatePolicy policy)
```
    Learning rate decay policy. Used to adapt learning rate based on policy.
    
    Parameters:
    
    policy - Type of policy to use. Defaults to None.
    
    See Also:
    
    GradientNormalization

Class BaseLayer.Builder<T extends BaseLayer.Builder<T>>

Field Summary

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

Constructor Summary

Method Summary

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

Methods inherited from class java.lang.Object

Field Detail

activationFn

weightInit

biasInit

dist

learningRate

biasLearningRate

learningRateSchedule

momentum

momentumAfter

l1

l2

l1Bias

l2Bias

updater

iupdater

rho

epsilon

rmsDecay

adamMeanDecay

adamVarDecay

gradientNormalization

gradientNormalizationThreshold

learningRatePolicy

Constructor Detail

Builder

Method Detail

activation

activation

activation

weightInit

biasInit

dist

learningRate

biasLearningRate

learningRateSchedule

l1

l2

l1Bias

l2Bias

momentum

momentumAfter

updater

updater

rho

rmsDecay

epsilon

adamMeanDecay

adamVarDecay

gradientNormalization

gradientNormalizationThreshold

learningRateDecayPolicy