org.deeplearning4j.nn.modelimport.keras.layers.convolutional

Class KerasConvolution

java.lang.Object

org.deeplearning4j.nn.modelimport.keras.KerasLayer

org.deeplearning4j.nn.modelimport.keras.layers.convolutional.KerasConvolution

Direct Known Subclasses:

KerasAtrousConvolution1D, KerasAtrousConvolution2D, KerasConvolution1D, KerasConvolution2D, KerasConvolution3D, KerasDeconvolution2D, KerasDepthwiseConvolution2D, KerasLocallyConnected1D, KerasLocallyConnected2D, KerasSeparableConvolution2D

public abstract class KerasConvolution
extends KerasLayer

Nested Class Summary

Nested classes/interfaces inherited from class org.deeplearning4j.nn.modelimport.keras.KerasLayer

KerasLayer.DimOrder

Field Summary

Fields

Modifier and Type	Field and Description
protected boolean	hasBias
protected int	numTrainableParams

Fields inherited from class org.deeplearning4j.nn.modelimport.keras.KerasLayer

className, conf, dimOrder, dropout, inboundLayerNames, inputShape, kerasMajorVersion, layer, layerName, originalLayerConfig, outboundLayerNames, vertex, weightL1Regularization, weightL2Regularization, weights

Constructor Summary

Constructors

Constructor and Description
KerasConvolution()
KerasConvolution(Integer kerasVersion) Pass-through constructor from KerasLayer
KerasConvolution(Map<String,Object> layerConfig) Constructor from parsed Keras layer configuration dictionary.
KerasConvolution(Map<String,Object> layerConfig, boolean enforceTrainingConfig) Constructor from parsed Keras layer configuration dictionary.

Method Summary

Modifier and Type	Method and Description
INDArray	getConvParameterValues(INDArray kerasParamValue) Return processed parameter values obtained from Keras convolutional layers.
int	getNumParams() Returns number of trainable parameters in layer.
void	setWeights(Map<String,INDArray> weights) Set weights for layer.

Methods inherited from class org.deeplearning4j.nn.modelimport.keras.KerasLayer

clearCustomLayers, clearLambdaLayers, copyWeightsToLayer, getClassName, getDimOrder, getInboundLayerNames, getInputPreprocessor, getInputShape, getKerasMajorVersion, getLayer, getLayerName, getNInFromConfig, getOutputType, getVertex, getWeights, isInputPreProcessor, isLayer, isValidInboundLayer, isVertex, registerCustomLayer, registerLambdaLayer, setInboundLayerNames, setLayer, usesRegularization

Methods inherited from class java.lang.Object

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

Field Detail

numTrainableParams

protected int numTrainableParams

hasBias

protected boolean hasBias

Constructor Detail

KerasConvolution

public KerasConvolution()
                 throws UnsupportedKerasConfigurationException

Throws:

UnsupportedKerasConfigurationException

KerasConvolution

public KerasConvolution(Integer kerasVersion)
                 throws UnsupportedKerasConfigurationException

Pass-through constructor from KerasLayer

Parameters:

kerasVersion - major keras version

Throws:

UnsupportedKerasConfigurationException - Unsupported Keras config

KerasConvolution

public KerasConvolution(Map<String,Object> layerConfig)
                 throws InvalidKerasConfigurationException,
                        UnsupportedKerasConfigurationException

Constructor from parsed Keras layer configuration dictionary.

Parameters:

layerConfig - dictionary containing Keras layer configuration

Throws:

InvalidKerasConfigurationException - Invalid Keras config

UnsupportedKerasConfigurationException - Unsupported Keras config

KerasConvolution

public KerasConvolution(Map<String,Object> layerConfig,
                        boolean enforceTrainingConfig)
                 throws InvalidKerasConfigurationException,
                        UnsupportedKerasConfigurationException

Constructor from parsed Keras layer configuration dictionary.

Parameters:

layerConfig - dictionary containing Keras layer configuration

enforceTrainingConfig - whether to enforce training-related configuration options

Throws:

InvalidKerasConfigurationException - Invalid Keras config

UnsupportedKerasConfigurationException - Unsupported Keras config

Method Detail

getNumParams

public int getNumParams()

Returns number of trainable parameters in layer.

Overrides:

getNumParams in class KerasLayer

Returns:

number of trainable parameters (2)

setWeights

public void setWeights(Map<String,INDArray> weights)
                throws InvalidKerasConfigurationException

Set weights for layer.

Overrides:

setWeights in class KerasLayer

Parameters:

weights - Map from parameter name to INDArray.

Throws:

InvalidKerasConfigurationException

getConvParameterValues

public INDArray getConvParameterValues(INDArray kerasParamValue)
                                throws InvalidKerasConfigurationException

Return processed parameter values obtained from Keras convolutional layers.

Parameters:

kerasParamValue - INDArray containing raw Keras weights to be processed

Returns:

Processed weights, according to which backend was used.

Throws:

InvalidKerasConfigurationException - Invalid Keras configuration exception.