Model (deeplearning4j-nn 0.9.1 API)

All Known Subinterfaces:

Classifier, IOutputLayer, Layer, RecurrentLayer

All Known Implementing Classes:

AbstractLayer, ActivationLayer, AutoEncoder, BaseLayer, BaseOutputLayer, BasePretrainNetwork, BaseRecurrentLayer, BatchNormalization, CenterLossOutputLayer, ComputationGraph, Convolution1DLayer, ConvolutionLayer, DenseLayer, DropoutLayer, EmbeddingLayer, FrozenLayer, GlobalPoolingLayer, GravesBidirectionalLSTM, GravesLSTM, LocalResponseNormalization, LossLayer, LSTM, MultiLayerNetwork, OutputLayer, RBM, RnnOutputLayer, Subsampling1DLayer, SubsamplingLayer, VariationalAutoencoder, ZeroPaddingLayer
```
public interface Model
```
A Model is meant for predicting something from data. Note that this is not like supervised learning where there are labels attached to the examples.

Method Summary

All Methods Instance Methods Abstract Methods Deprecated Methods
Modifier and Type	Method and Description
`void`	`accumulateScore(double accum)` Sets a rolling tally for the score.
`void`	`addListeners(IterationListener... listener)` This method ADDS additional IterationListener to existing listeners
`void`	`applyLearningRateScoreDecay()` Update learningRate using for this model.
`int`	`batchSize()` The current inputs batch size
`void`	`clear()` Clear input
`void`	`computeGradientAndScore()` Update the score
`NeuralNetConfiguration`	`conf()` The configuration for the neural network
`void`	`fit()` All models have a fit method
`void`	`fit(org.nd4j.linalg.api.ndarray.INDArray data)` Fit the model to the given data
`org.nd4j.linalg.api.ndarray.INDArray`	`getGradientsViewArray()`
`ConvexOptimizer`	`getOptimizer()` Returns this models optimizer
`org.nd4j.linalg.api.ndarray.INDArray`	`getParam(String param)` Get the parameter
`Gradient`	`gradient()` Calculate a gradient
`org.nd4j.linalg.primitives.Pair<Gradient,Double>`	`gradientAndScore()` Get the gradient and score
`void`	`init()` Init the model
`void`	`initParams()` Deprecated. As of 0.7.3 - Feb 2017. Not used; neural network params are initialized by the parameter initializaters. Furthermore, most implementations are unsupported or no-op.
`org.nd4j.linalg.api.ndarray.INDArray`	`input()` The input/feature matrix for the model
`void`	`iterate(org.nd4j.linalg.api.ndarray.INDArray input)` Run one iteration
`int`	`numParams()` the number of parameters for the model
`int`	`numParams(boolean backwards)` the number of parameters for the model
`org.nd4j.linalg.api.ndarray.INDArray`	`params()` Parameters of the model (if any)
`Map<String,org.nd4j.linalg.api.ndarray.INDArray>`	`paramTable()` The param table
`Map<String,org.nd4j.linalg.api.ndarray.INDArray>`	`paramTable(boolean backpropParamsOnly)` Table of parameters by key, for backprop For many models (dense layers, etc) - all parameters are backprop parameters
`double`	`score()` The score for the model
`void`	`setBackpropGradientsViewArray(org.nd4j.linalg.api.ndarray.INDArray gradients)` Set the gradients array as a view of the full (backprop) network parameters NOTE: this is intended to be used internally in MultiLayerNetwork and ComputationGraph, not by users.
`void`	`setConf(NeuralNetConfiguration conf)` Setter for the configuration
`void`	`setListeners(Collection<IterationListener> listeners)` Set the IterationListeners for the ComputationGraph (and all layers in the network)
`void`	`setListeners(IterationListener... listeners)` Set the IterationListeners for the ComputationGraph (and all layers in the network)
`void`	`setParam(String key, org.nd4j.linalg.api.ndarray.INDArray val)` Set the parameter with a new ndarray
`void`	`setParams(org.nd4j.linalg.api.ndarray.INDArray params)` Set the parameters for this model.
`void`	`setParamsViewArray(org.nd4j.linalg.api.ndarray.INDArray params)` Set the initial parameters array as a view of the full (backprop) network parameters NOTE: this is intended to be used internally in MultiLayerNetwork and ComputationGraph, not by users.
`void`	`setParamTable(Map<String,org.nd4j.linalg.api.ndarray.INDArray> paramTable)` Setter for the param table
`void`	`update(Gradient gradient)` Update layer weights and biases with gradient change
`void`	`update(org.nd4j.linalg.api.ndarray.INDArray gradient, String paramType)` Perform one update applying the gradient
`void`	`validateInput()` Deprecated. As of 0.7.3 - Feb 2017. No longer used, most implementations are unsupported or no-op.

- Method Detail
  - init
```
void init()
```
    Init the model
  - setListeners
```
void setListeners(Collection<IterationListener> listeners)
```
    Set the IterationListeners for the ComputationGraph (and all layers in the network)
  - setListeners
```
void setListeners(IterationListener... listeners)
```
    Set the IterationListeners for the ComputationGraph (and all layers in the network)
  - addListeners
```
void addListeners(IterationListener... listener)
```
    This method ADDS additional IterationListener to existing listeners
    
    Parameters:
    
    listener -
  - fit
```
void fit()
```
    All models have a fit method
  - update
```
void update(Gradient gradient)
```
    Update layer weights and biases with gradient change
  - update
```
void update(org.nd4j.linalg.api.ndarray.INDArray gradient,
            String paramType)
```
    Perform one update applying the gradient
    
    Parameters:
    
    gradient - the gradient to apply
  - score
```
double score()
```
    The score for the model
    
    Returns:
    
    the score for the model
  - computeGradientAndScore
```
void computeGradientAndScore()
```
    Update the score
  - accumulateScore
```
void accumulateScore(double accum)
```
    Sets a rolling tally for the score. This is useful for mini batch learning when you are accumulating error across a dataset.
    
    Parameters:
    
    accum - the amount to accum
  - params
```
org.nd4j.linalg.api.ndarray.INDArray params()
```
    Parameters of the model (if any)
    
    Returns:
    
    the parameters of the model
  - numParams
```
int numParams()
```
    the number of parameters for the model
    
    Returns:
    
    the number of parameters for the model
  - numParams
```
int numParams(boolean backwards)
```
    the number of parameters for the model
    
    Returns:
    
    the number of parameters for the model
  - setParams
```
void setParams(org.nd4j.linalg.api.ndarray.INDArray params)
```
    Set the parameters for this model. This expects a linear ndarray which then be unpacked internally relative to the expected ordering of the model
    
    Parameters:
    
    params - the parameters for the model
  - setParamsViewArray
```
void setParamsViewArray(org.nd4j.linalg.api.ndarray.INDArray params)
```
    Set the initial parameters array as a view of the full (backprop) network parameters NOTE: this is intended to be used internally in MultiLayerNetwork and ComputationGraph, not by users.
    
    Parameters:
    
    params - a 1 x nParams row vector that is a view of the larger (MLN/CG) parameters array
  - getGradientsViewArray
```
org.nd4j.linalg.api.ndarray.INDArray getGradientsViewArray()
```
  - setBackpropGradientsViewArray
```
void setBackpropGradientsViewArray(org.nd4j.linalg.api.ndarray.INDArray gradients)
```
    Set the gradients array as a view of the full (backprop) network parameters NOTE: this is intended to be used internally in MultiLayerNetwork and ComputationGraph, not by users.
    
    Parameters:
    
    gradients - a 1 x nParams row vector that is a view of the larger (MLN/CG) gradients array
  - applyLearningRateScoreDecay
```
void applyLearningRateScoreDecay()
```
    Update learningRate using for this model. Use the learningRateScoreBasedDecay to adapt the score if the Eps termination condition is met
  - fit
```
void fit(org.nd4j.linalg.api.ndarray.INDArray data)
```
    Fit the model to the given data
    
    Parameters:
    
    data - the data to fit the model to
  - iterate
```
void iterate(org.nd4j.linalg.api.ndarray.INDArray input)
```
    Run one iteration
    
    Parameters:
    
    input - the input to iterate on
  - gradient
```
Gradient gradient()
```
    Calculate a gradient
    
    Returns:
    
    the gradient for this model
  - gradientAndScore
```
org.nd4j.linalg.primitives.Pair<Gradient,Double> gradientAndScore()
```
    Get the gradient and score
    
    Returns:
    
    the gradient and score
  - batchSize
```
int batchSize()
```
    The current inputs batch size
    
    Returns:
    
    the current inputs batch size
  - conf
```
NeuralNetConfiguration conf()
```
    The configuration for the neural network
    
    Returns:
    
    the configuration for the neural network
  - setConf
```
void setConf(NeuralNetConfiguration conf)
```
    Setter for the configuration
    
    Parameters:
    
    conf -
  - input
```
org.nd4j.linalg.api.ndarray.INDArray input()
```
    The input/feature matrix for the model
    
    Returns:
    
    the input/feature matrix for the model
  - validateInput
```
@Deprecated
void validateInput()
```
    Deprecated. As of 0.7.3 - Feb 2017. No longer used, most implementations are unsupported or no-op.
    
    Validate the input
  - getOptimizer
```
ConvexOptimizer getOptimizer()
```
    Returns this models optimizer
    
    Returns:
    
    this models optimizer
  - getParam
```
org.nd4j.linalg.api.ndarray.INDArray getParam(String param)
```
    Get the parameter
    
    Parameters:
    
    param - the key of the parameter
    
    Returns:
    
    the parameter vector/matrix with that particular key
  - initParams
```
@Deprecated
void initParams()
```
    Deprecated. As of 0.7.3 - Feb 2017. Not used; neural network params are initialized by the parameter initializaters. Furthermore, most implementations are unsupported or no-op.
    
    Initialize the parameters
  - paramTable
```
Map<String,org.nd4j.linalg.api.ndarray.INDArray> paramTable()
```
    The param table
    
    Returns:
  - paramTable
```
Map<String,org.nd4j.linalg.api.ndarray.INDArray> paramTable(boolean backpropParamsOnly)
```
    Table of parameters by key, for backprop For many models (dense layers, etc) - all parameters are backprop parameters
    
    Parameters:
    
    backpropParamsOnly - If true, return backprop params only. If false: return all params (equivalent to paramsTable())
  - setParamTable
```
void setParamTable(Map<String,org.nd4j.linalg.api.ndarray.INDArray> paramTable)
```
    Setter for the param table
    
    Parameters:
    
    paramTable -
  - setParam
```
void setParam(String key,
              org.nd4j.linalg.api.ndarray.INDArray val)
```
    Set the parameter with a new ndarray
    
    Parameters:
    
    key - the key to se t
    
    val - the new ndarray
  - clear
```
void clear()
```
    Clear input

Interface Model

Method Summary

Method Detail

init

setListeners

setListeners

addListeners

fit

update

update

score

computeGradientAndScore

accumulateScore

params

numParams

numParams

setParams

setParamsViewArray

getGradientsViewArray

setBackpropGradientsViewArray

applyLearningRateScoreDecay

fit

iterate

gradient

gradientAndScore

batchSize

conf

setConf

input

validateInput

getOptimizer

getParam

initParams

paramTable

paramTable

setParamTable

setParam

clear