org.deeplearning4j.nn.modelimport.keras.layers

Class KerasLoss

java.lang.Object

org.deeplearning4j.nn.modelimport.keras.KerasLayer

org.deeplearning4j.nn.modelimport.keras.layers.KerasLoss

public class KerasLoss
extends KerasLayer

Builds a DL4J LossLayer from a Keras training loss function.

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
static java.lang.String	KERAS_CLASS_NAME_LOSS

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

className, DIM_ORDERING_TENSORFLOW, DIM_ORDERING_THEANO, dimOrder, dropout, inboundLayerNames, INIT_GLOROT_NORMAL, INIT_GLOROT_UNIFORM, INIT_HE_NORMAL, INIT_HE_UNIFORM, INIT_IDENTITY, INIT_LECUN_UNIFORM, INIT_NORMAL, INIT_ORTHOGONAL, INIT_UNIFORM, INIT_ZERO, inputShape, KERAS_ACTIVATION_HARD_SIGMOID, KERAS_ACTIVATION_LINEAR, KERAS_ACTIVATION_RELU, KERAS_ACTIVATION_SIGMOID, KERAS_ACTIVATION_SOFTMAX, KERAS_ACTIVATION_SOFTPLUS, KERAS_ACTIVATION_SOFTSIGN, KERAS_ACTIVATION_TANH, KERAS_LOSS_BINARY_CROSSENTROPY, KERAS_LOSS_CATEGORICAL_CROSSENTROPY, KERAS_LOSS_COSINE_PROXIMITY, KERAS_LOSS_HINGE, KERAS_LOSS_KLD, KERAS_LOSS_KULLBACK_LEIBLER_DIVERGENCE, KERAS_LOSS_MAE, KERAS_LOSS_MAPE, KERAS_LOSS_MEAN_ABSOLUTE_ERROR, KERAS_LOSS_MEAN_ABSOLUTE_PERCENTAGE_ERROR, KERAS_LOSS_MEAN_SQUARED_ERROR, KERAS_LOSS_MEAN_SQUARED_LOGARITHMIC_ERROR, KERAS_LOSS_MSE, KERAS_LOSS_MSLE, KERAS_LOSS_POISSON, KERAS_LOSS_SPARSE_CATEGORICAL_CROSSENTROPY, KERAS_LOSS_SQUARED_HINGE, layer, LAYER_BORDER_MODE_FULL, LAYER_BORDER_MODE_SAME, LAYER_BORDER_MODE_VALID, LAYER_CLASS_NAME_ACTIVATION, LAYER_CLASS_NAME_AVERAGE_POOLING_1D, LAYER_CLASS_NAME_AVERAGE_POOLING_2D, LAYER_CLASS_NAME_BATCHNORMALIZATION, LAYER_CLASS_NAME_CONVOLUTION_1D, LAYER_CLASS_NAME_CONVOLUTION_2D, LAYER_CLASS_NAME_DENSE, LAYER_CLASS_NAME_DROPOUT, LAYER_CLASS_NAME_EMBEDDING, LAYER_CLASS_NAME_FLATTEN, LAYER_CLASS_NAME_GLOBAL_AVERAGE_POOLING_1D, LAYER_CLASS_NAME_GLOBAL_AVERAGE_POOLING_2D, LAYER_CLASS_NAME_GLOBAL_MAX_POOLING_1D, LAYER_CLASS_NAME_GLOBAL_MAX_POOLING_2D, LAYER_CLASS_NAME_INPUT, LAYER_CLASS_NAME_LSTM, LAYER_CLASS_NAME_MAX_POOLING_1D, LAYER_CLASS_NAME_MAX_POOLING_2D, LAYER_CLASS_NAME_MERGE, LAYER_CLASS_NAME_TIME_DISTRIBUTED, LAYER_CLASS_NAME_TIME_DISTRIBUTED_DENSE, LAYER_CLASS_NAME_ZERO_PADDING_1D, LAYER_CLASS_NAME_ZERO_PADDING_2D, LAYER_FIELD_ACTIVATION, LAYER_FIELD_B_REGULARIZER, LAYER_FIELD_BATCH_INPUT_SHAPE, LAYER_FIELD_BORDER_MODE, LAYER_FIELD_CLASS_NAME, LAYER_FIELD_CONFIG, LAYER_FIELD_DIM_ORDERING, LAYER_FIELD_DROPOUT, LAYER_FIELD_DROPOUT_W, LAYER_FIELD_INBOUND_NODES, LAYER_FIELD_INIT, LAYER_FIELD_LAYER, LAYER_FIELD_NAME, LAYER_FIELD_NB_COL, LAYER_FIELD_NB_FILTER, LAYER_FIELD_NB_ROW, LAYER_FIELD_OUTPUT_DIM, LAYER_FIELD_POOL_SIZE, LAYER_FIELD_STRIDES, LAYER_FIELD_SUBSAMPLE, LAYER_FIELD_W_REGULARIZER, layerName, REGULARIZATION_TYPE_L1, REGULARIZATION_TYPE_L2, vertex, weightL1Regularization, weightL2Regularization, weights

Constructor Summary

Constructors

Constructor and Description
KerasLoss(java.lang.String layerName, java.lang.String inboundLayerName, java.lang.String kerasLoss) Constructor from layer name and input shape.
KerasLoss(java.lang.String layerName, java.lang.String inboundLayerName, java.lang.String kerasLoss, boolean enforceTrainingConfig) Constructor from layer name and input shape.

Method Summary

Modifier and Type	Method and Description
LossLayer	getLossLayer() Get DL4J LossLayer.
InputType	getOutputType(InputType... inputType) Get layer output type.

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

checkForUnsupportedConfigurations, copyWeightsToLayer, getActivationFromConfig, getBiasL1RegularizationFromConfig, getClassName, getClassNameFromConfig, getConvolutionModeFromConfig, getDimOrder, getDropoutFromConfig, getInboundLayerNames, getInboundLayerNamesFromConfig, getInnerLayerConfigFromConfig, getInputPreprocessor, getInputShape, getKerasLayerFromConfig, getKerasLayerFromConfig, getKernelSizeFromConfig, getLayer, getLayerName, getLayerNameFromConfig, getNOutFromConfig, getNumParams, getPaddingFromBorderModeConfig, getStrideFromConfig, getTimeDistributedLayerConfig, getVertex, getWeightInitFromConfig, getWeightL1RegularizationFromConfig, getWeightL2RegularizationFromConfig, isInputPreProcessor, isLayer, isValidInboundLayer, isVertex, mapActivation, mapLossFunction, mapPoolingDimensions, mapPoolingType, mapWeightInitialization, setDimOrder, setInboundLayerNames, setWeights, usesRegularization

Methods inherited from class java.lang.Object

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

Field Detail

KERAS_CLASS_NAME_LOSS

public static final java.lang.String KERAS_CLASS_NAME_LOSS

See Also:

Constant Field Values

Constructor Detail

KerasLoss

public KerasLoss(java.lang.String layerName,
                 java.lang.String inboundLayerName,
                 java.lang.String kerasLoss)
          throws UnsupportedKerasConfigurationException

Constructor from layer name and input shape.

Parameters:

layerName - layer name

inboundLayerName - name of inbound layer

kerasLoss - name of Keras loss function

Throws:

InvalidKerasConfigurationException

UnsupportedKerasConfigurationException

KerasLoss

public KerasLoss(java.lang.String layerName,
                 java.lang.String inboundLayerName,
                 java.lang.String kerasLoss,
                 boolean enforceTrainingConfig)
          throws UnsupportedKerasConfigurationException

Constructor from layer name and input shape.

Parameters:

layerName - layer name

inboundLayerName - name of inbound layer

kerasLoss - name of Keras loss function

enforceTrainingConfig - whether to enforce training-related configuration options

Throws:

InvalidKerasConfigurationException

UnsupportedKerasConfigurationException

Method Detail

getLossLayer

public LossLayer getLossLayer()

Get DL4J LossLayer.

Returns:

LossLayer

getOutputType

public InputType getOutputType(InputType... inputType)
                        throws InvalidKerasConfigurationException

Get layer output type.

Overrides:

getOutputType in class KerasLayer

Parameters:

inputType - Array of InputTypes

Returns:

output type as InputType

Throws:

InvalidKerasConfigurationException