FineTuneConfiguration (deeplearning4j-nn 0.8.0 API)

java.lang.Object
- org.deeplearning4j.nn.transferlearning.FineTuneConfiguration

public class FineTuneConfiguration
extends Object

Created by Alex on 21/02/2017.

Nested Class Summary

Nested Classes
Modifier and Type Class and Description

static class FineTuneConfiguration.Builder

Nested Classes
Modifier and Type	Class and Description
`static class`	`FineTuneConfiguration.Builder`

Field Summary

Fields
Modifier and Type	Field and Description
`protected org.nd4j.linalg.activations.IActivation`	`activationFn`
`protected Double`	`adamMeanDecay`
`protected Double`	`adamVarDecay`
`protected Boolean`	`backprop`
`protected BackpropType`	`backpropType`
`protected Double`	`biasInit`
`protected Double`	`biasLearningRate`
`protected ConvolutionMode`	`convolutionMode`
`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 Double`	`learningRate`
`protected LearningRatePolicy`	`learningRatePolicy`
`protected Map<Integer,Double>`	`learningRateSchedule`
`protected Double`	`lrPolicyDecayRate`
`protected Double`	`lrPolicyPower`
`protected Double`	`lrPolicySteps`
`protected Double`	`lrScoreBasedDecay`
`protected Integer`	`maxNumLineSearchIterations`
`protected Boolean`	`miniBatch`
`protected Boolean`	`minimize`
`protected Double`	`momentum`
`protected Map<Integer,Double>`	`momentumSchedule`
`protected Integer`	`numIterations`
`protected OptimizationAlgorithm`	`optimizationAlgo`
`protected Boolean`	`pretrain`
`protected Double`	`rho`
`protected Double`	`rmsDecay`
`protected Long`	`seed`
`protected StepFunction`	`stepFunction`
`protected Integer`	`tbpttBackLength`
`protected Integer`	`tbpttFwdLength`
`protected Updater`	`updater`
`protected Boolean`	`useDropConnect`
`protected Boolean`	`useRegularization`
`protected WeightInit`	`weightInit`

Constructor Summary

Constructors
Constructor and Description

FineTuneConfiguration()

Constructors
Constructor and Description
`FineTuneConfiguration()`

Method Summary

All Methods Instance Methods Concrete Methods
Modifier and Type	Method and Description
`NeuralNetConfiguration`	`appliedNeuralNetConfiguration(NeuralNetConfiguration nnc)`
`NeuralNetConfiguration.Builder`	`appliedNeuralNetConfigurationBuilder()`
`void`	`applyToComputationGraphConfiguration(ComputationGraphConfiguration conf)`
`void`	`applyToMultiLayerConfiguration(MultiLayerConfiguration conf)`
`void`	`applyToNeuralNetConfiguration(NeuralNetConfiguration nnc)`

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

lrScoreBasedDecay
```
protected Double lrScoreBasedDecay
```

l1
```
protected Double l1
```

l2
```
protected Double l2
```

l1Bias
```
protected Double l1Bias
```

l2Bias
```
protected Double l2Bias
```

dropOut
```
protected Double dropOut
```

updater
```
protected Updater updater
```

momentum
```
protected Double momentum
```

momentumSchedule

protected Map<Integer,Double> momentumSchedule

epsilon
```
protected Double epsilon
```

rho
```
protected Double rho
```

rmsDecay
```
protected Double rmsDecay
```

adamMeanDecay
```
protected Double adamMeanDecay
```

adamVarDecay
```
protected Double adamVarDecay
```

miniBatch
```
protected Boolean miniBatch
```

numIterations
```
protected Integer numIterations
```

maxNumLineSearchIterations

protected Integer maxNumLineSearchIterations

seed
```
protected Long seed
```

useRegularization
```
protected Boolean useRegularization
```

optimizationAlgo

protected OptimizationAlgorithm optimizationAlgo

stepFunction
```
protected StepFunction stepFunction
```

useDropConnect
```
protected Boolean useDropConnect
```

minimize
```
protected Boolean minimize
```

gradientNormalization

protected GradientNormalization gradientNormalization

gradientNormalizationThreshold

protected Double gradientNormalizationThreshold

learningRatePolicy

protected LearningRatePolicy learningRatePolicy

lrPolicyDecayRate
```
protected Double lrPolicyDecayRate
```

lrPolicySteps
```
protected Double lrPolicySteps
```

lrPolicyPower
```
protected Double lrPolicyPower
```

convolutionMode

protected ConvolutionMode convolutionMode

pretrain
```
protected Boolean pretrain
```

backprop
```
protected Boolean backprop
```

backpropType
```
protected BackpropType backpropType
```

tbpttFwdLength
```
protected Integer tbpttFwdLength
```

tbpttBackLength
```
protected Integer tbpttBackLength
```

Constructor Detail
- FineTuneConfiguration
```
public FineTuneConfiguration()
```

Method Detail

appliedNeuralNetConfiguration

public NeuralNetConfiguration appliedNeuralNetConfiguration(NeuralNetConfiguration nnc)

applyToNeuralNetConfiguration

public void applyToNeuralNetConfiguration(NeuralNetConfiguration nnc)

applyToMultiLayerConfiguration

public void applyToMultiLayerConfiguration(MultiLayerConfiguration conf)

applyToComputationGraphConfiguration

public void applyToComputationGraphConfiguration(ComputationGraphConfiguration conf)

appliedNeuralNetConfigurationBuilder

public NeuralNetConfiguration.Builder appliedNeuralNetConfigurationBuilder()

Class FineTuneConfiguration

Nested Class Summary

Field Summary

Constructor Summary

Method Summary

Methods inherited from class java.lang.Object

Field Detail

activationFn

weightInit

biasInit

dist

learningRate

biasLearningRate

learningRateSchedule

lrScoreBasedDecay

l1

l2

l1Bias

l2Bias

dropOut

updater

momentum

momentumSchedule

epsilon

rho

rmsDecay

adamMeanDecay

adamVarDecay

miniBatch

numIterations

maxNumLineSearchIterations

seed

useRegularization

optimizationAlgo

stepFunction

useDropConnect

minimize

gradientNormalization

gradientNormalizationThreshold

learningRatePolicy

lrPolicyDecayRate

lrPolicySteps

lrPolicyPower

convolutionMode

pretrain

backprop

backpropType

tbpttFwdLength

tbpttBackLength

Constructor Detail

FineTuneConfiguration

Method Detail

appliedNeuralNetConfiguration

applyToNeuralNetConfiguration

applyToMultiLayerConfiguration

applyToComputationGraphConfiguration

appliedNeuralNetConfigurationBuilder