Package org.nd4j.linalg.factory.ops

Class NDLoss

  • public class NDLoss
extends Object

    • Constructor Summary

      Constructors 
      Constructor Description
      NDLoss()  

    • Method Summary

      All Methods Instance Methods Concrete Methods 
      Modifier and Type Method Description
      INDArray absoluteDifference​(INDArray label, INDArray predictions, INDArray weights)
      Absolute difference loss: sum_i abs( label[i] - predictions[i] )
      INDArray absoluteDifference​(INDArray label, INDArray predictions, INDArray weights, LossReduce lossReduce)
      Absolute difference loss: sum_i abs( label[i] - predictions[i] )
      INDArray cosineDistance​(INDArray label, INDArray predictions, INDArray weights, int dimension)
      Cosine distance loss: 1 - cosineSimilarity(x,y) or 1 - sum_i label[i] * prediction[i], which is
      equivalent to cosine distance when both the predictions and labels are normalized.
      Note: This loss function assumes that both the predictions and labels are normalized to have unit l2 norm.
      If this is not the case, you should normalize them first by dividing by norm2(String, SDVariable, boolean, int...)
      along the cosine distance dimension (with keepDims=true).
      INDArray cosineDistance​(INDArray label, INDArray predictions, INDArray weights, LossReduce lossReduce, int dimension)
      Cosine distance loss: 1 - cosineSimilarity(x,y) or 1 - sum_i label[i] * prediction[i], which is
      equivalent to cosine distance when both the predictions and labels are normalized.
      Note: This loss function assumes that both the predictions and labels are normalized to have unit l2 norm.
      If this is not the case, you should normalize them first by dividing by norm2(String, SDVariable, boolean, int...)
      along the cosine distance dimension (with keepDims=true).
      INDArray ctcLoss​(INDArray targetLabels, INDArray logitInput, INDArray targetLabelLengths, INDArray logitInputLengths)
      CTC Loss: Connectionist Temporal Classification Loss.
      INDArray hingeLoss​(INDArray label, INDArray predictions, INDArray weights)
      Hinge loss: a loss function used for training classifiers.
      Implements L = max(0, 1 - t * predictions) where t is the label values after internally converting to {-1,1}
      from the user specified {0,1}.
      INDArray hingeLoss​(INDArray label, INDArray predictions, INDArray weights, LossReduce lossReduce)
      Hinge loss: a loss function used for training classifiers.
      Implements L = max(0, 1 - t * predictions) where t is the label values after internally converting to {-1,1}
      from the user specified {0,1}.
      INDArray huberLoss​(INDArray label, INDArray predictions, INDArray weights, double delta)
      Huber loss function, used for robust regression.
      INDArray huberLoss​(INDArray label, INDArray predictions, INDArray weights, LossReduce lossReduce, double delta)
      Huber loss function, used for robust regression.
      INDArray l2Loss​(INDArray var)
      L2 loss: 1/2 * sum(x^2)
      INDArray logLoss​(INDArray label, INDArray predictions)
      Log loss, i.e., binary cross entropy loss, usually used for binary multi-label classification.
      INDArray logLoss​(INDArray label, INDArray predictions, INDArray weights, LossReduce lossReduce, double epsilon)
      Log loss, i.e., binary cross entropy loss, usually used for binary multi-label classification.
      INDArray logPoisson​(INDArray label, INDArray predictions, INDArray weights, boolean full)
      Log poisson loss: a loss function used for training classifiers.
      Implements L = exp(c) - z * c where c is log(predictions) and z is labels.
      INDArray logPoisson​(INDArray label, INDArray predictions, INDArray weights, LossReduce lossReduce, boolean full)
      Log poisson loss: a loss function used for training classifiers.
      Implements L = exp(c) - z * c where c is log(predictions) and z is labels.
      INDArray meanPairwiseSquaredError​(INDArray label, INDArray predictions, INDArray weights)
      Mean pairwise squared error.
      MPWSE loss calculates the difference between pairs of consecutive elements in the predictions and labels arrays.
      For example, if predictions = [p0, p1, p2] and labels are [l0, l1, l2] then MPWSE is:
      [((p0-p1) - (l0-l1))^2 + ((p0-p2) - (l0-l2))^2 + ((p1-p2) - (l1-l2))^2] / 3
      INDArray meanPairwiseSquaredError​(INDArray label, INDArray predictions, INDArray weights, LossReduce lossReduce)
      Mean pairwise squared error.
      MPWSE loss calculates the difference between pairs of consecutive elements in the predictions and labels arrays.
      For example, if predictions = [p0, p1, p2] and labels are [l0, l1, l2] then MPWSE is:
      [((p0-p1) - (l0-l1))^2 + ((p0-p2) - (l0-l2))^2 + ((p1-p2) - (l1-l2))^2] / 3
      INDArray meanSquaredError​(INDArray label, INDArray predictions, INDArray weights)
      Mean squared error loss function.
      INDArray meanSquaredError​(INDArray label, INDArray predictions, INDArray weights, LossReduce lossReduce)
      Mean squared error loss function.
      INDArray sigmoidCrossEntropy​(INDArray label, INDArray predictionLogits, INDArray weights)
      Sigmoid cross entropy: applies the sigmoid activation function on the input logits (input "pre-sigmoid preductions")
      and implements the binary cross entropy loss function.
      INDArray sigmoidCrossEntropy​(INDArray label, INDArray predictionLogits, INDArray weights, LossReduce lossReduce, double labelSmoothing)
      Sigmoid cross entropy: applies the sigmoid activation function on the input logits (input "pre-sigmoid preductions")
      and implements the binary cross entropy loss function.
      INDArray softmaxCrossEntropy​(INDArray oneHotLabels, INDArray logitPredictions, INDArray weights)
      Applies the softmax activation function to the input, then implement multi-class cross entropy:
      -sum_classes label[i] * log(p[c]) where p = softmax(logits)
      If LossReduce#NONE is used, returned shape is [numExamples] out for [numExamples, numClasses] predicitons/labels;
      otherwise, the output is a scalar.
      INDArray softmaxCrossEntropy​(INDArray oneHotLabels, INDArray logitPredictions, INDArray weights, LossReduce lossReduce, double labelSmoothing)
      Applies the softmax activation function to the input, then implement multi-class cross entropy:
      -sum_classes label[i] * log(p[c]) where p = softmax(logits)
      If LossReduce#NONE is used, returned shape is [numExamples] out for [numExamples, numClasses] predicitons/labels;
      otherwise, the output is a scalar.
      INDArray sparseSoftmaxCrossEntropy​(INDArray logits, INDArray labels)
      As per softmaxCrossEntropy(String, SDVariable, SDVariable, LossReduce) but the labels variable
      is represented as an integer array instead of the equivalent one-hot array.
      i.e., if logits are rank N, then labels have rank N-1

    • Constructor Detail

      • NDLoss

        public NDLoss()

    • Method Detail

      • absoluteDifference

        public INDArray absoluteDifference​(INDArray label,
                                   INDArray predictions,
                                   INDArray weights,
                                   LossReduce lossReduce)
        Absolute difference loss: sum_i abs( label[i] - predictions[i] )
        Parameters:
        label - Label array (NUMERIC type)
        predictions - Predictions array (NUMERIC type)
        weights - Weights array. May be null. If null, a weight of 1.0 is used (NUMERIC type)
        lossReduce - Reduction type for the loss. See LossReduce for more details. Default: LossReduce#MEAN_BY_NONZERO_WEIGHT_COUNT
        Returns:
        output loss variable (NUMERIC type)

      • absoluteDifference

        public INDArray absoluteDifference​(INDArray label,
                                   INDArray predictions,
                                   INDArray weights)
        Absolute difference loss: sum_i abs( label[i] - predictions[i] )
        Parameters:
        label - Label array (NUMERIC type)
        predictions - Predictions array (NUMERIC type)
        weights - Weights array. May be null. If null, a weight of 1.0 is used (NUMERIC type)
        Returns:
        output loss variable (NUMERIC type)

      • cosineDistance

        public INDArray cosineDistance​(INDArray label,
                               INDArray predictions,
                               INDArray weights,
                               LossReduce lossReduce,
                               int dimension)
        Cosine distance loss: 1 - cosineSimilarity(x,y) or 1 - sum_i label[i] * prediction[i], which is
        equivalent to cosine distance when both the predictions and labels are normalized.
        Note: This loss function assumes that both the predictions and labels are normalized to have unit l2 norm.
        If this is not the case, you should normalize them first by dividing by norm2(String, SDVariable, boolean, int...)
        along the cosine distance dimension (with keepDims=true).
        Parameters:
        label - Label array (NUMERIC type)
        predictions - Predictions array (NUMERIC type)
        weights - Weights array. May be null. If null, a weight of 1.0 is use (NUMERIC type)
        lossReduce - Reduction type for the loss. See LossReduce for more details. Default: LossReduce#MEAN_BY_NONZERO_WEIGHT_COUNT
        dimension - Dimension to perform the cosine distance over
        Returns:
        output Cosine distance loss (NUMERIC type)

      • cosineDistance

        public INDArray cosineDistance​(INDArray label,
                               INDArray predictions,
                               INDArray weights,
                               int dimension)
        Cosine distance loss: 1 - cosineSimilarity(x,y) or 1 - sum_i label[i] * prediction[i], which is
        equivalent to cosine distance when both the predictions and labels are normalized.
        Note: This loss function assumes that both the predictions and labels are normalized to have unit l2 norm.
        If this is not the case, you should normalize them first by dividing by norm2(String, SDVariable, boolean, int...)
        along the cosine distance dimension (with keepDims=true).
        Parameters:
        label - Label array (NUMERIC type)
        predictions - Predictions array (NUMERIC type)
        weights - Weights array. May be null. If null, a weight of 1.0 is use (NUMERIC type)
        dimension - Dimension to perform the cosine distance over
        Returns:
        output Cosine distance loss (NUMERIC type)

      • ctcLoss

        public INDArray ctcLoss​(INDArray targetLabels,
                        INDArray logitInput,
                        INDArray targetLabelLengths,
                        INDArray logitInputLengths)
        CTC Loss: Connectionist Temporal Classification Loss. See:
        https://dl.acm.org/citation.cfm?id=1143891
        Parameters:
        targetLabels - Label array (NUMERIC type)
        logitInput - Inputs (NUMERIC type)
        targetLabelLengths - Length of the target label (NUMERIC type)
        logitInputLengths - Length of the input (NUMERIC type)
        Returns:
        output Ctc loss (NUMERIC type)

      • hingeLoss

        public INDArray hingeLoss​(INDArray label,
                          INDArray predictions,
                          INDArray weights,
                          LossReduce lossReduce)
        Hinge loss: a loss function used for training classifiers.
        Implements L = max(0, 1 - t * predictions) where t is the label values after internally converting to {-1,1}
        from the user specified {0,1}. Note that Labels should be provided with values {0,1}.
        Parameters:
        label - Label array. Each value should be 0.0 or 1.0 (internally -1 to 1 is used) (NUMERIC type)
        predictions - Predictions array (NUMERIC type)
        weights - Weights array. May be null. If null, a weight of 1.0 is used (NUMERIC type)
        lossReduce - Reduction type for the loss. See LossReduce for more details. Default: LossReduce#MEAN_BY_NONZERO_WEIGHT_COUNT
        Returns:
        output Loss variable (NUMERIC type)

      • hingeLoss

        public INDArray hingeLoss​(INDArray label,
                          INDArray predictions,
                          INDArray weights)
        Hinge loss: a loss function used for training classifiers.
        Implements L = max(0, 1 - t * predictions) where t is the label values after internally converting to {-1,1}
        from the user specified {0,1}. Note that Labels should be provided with values {0,1}.
        Parameters:
        label - Label array. Each value should be 0.0 or 1.0 (internally -1 to 1 is used) (NUMERIC type)
        predictions - Predictions array (NUMERIC type)
        weights - Weights array. May be null. If null, a weight of 1.0 is used (NUMERIC type)
        Returns:
        output Loss variable (NUMERIC type)

      • huberLoss

        public INDArray huberLoss​(INDArray label,
                          INDArray predictions,
                          INDArray weights,
                          LossReduce lossReduce,
                          double delta)
        Huber loss function, used for robust regression. It is similar both squared error loss and absolute difference loss,
        though is less sensitive to outliers than squared error.
        Huber loss implements:

        
 L = 0.5 * (label[i] - predictions[i])^2 if abs(label[i] - predictions[i]) < delta
        
 L = delta * abs(label[i] - predictions[i]) - 0.5 * delta^2 otherwise

        Parameters:
        label - Label array (NUMERIC type)
        predictions - Predictions array (NUMERIC type)
        weights - Weights array. May be null. If null, a weight of 1.0 is used (NUMERIC type)
        lossReduce - Reduction type for the loss. See LossReduce for more details. Default: LossReduce#MEAN_BY_NONZERO_WEIGHT_COUNT
        delta - Loss function delta value
        Returns:
        output Huber loss (NUMERIC type)

      • huberLoss

        public INDArray huberLoss​(INDArray label,
                          INDArray predictions,
                          INDArray weights,
                          double delta)
        Huber loss function, used for robust regression. It is similar both squared error loss and absolute difference loss,
        though is less sensitive to outliers than squared error.
        Huber loss implements:

        
 L = 0.5 * (label[i] - predictions[i])^2 if abs(label[i] - predictions[i]) < delta
        
 L = delta * abs(label[i] - predictions[i]) - 0.5 * delta^2 otherwise

        Parameters:
        label - Label array (NUMERIC type)
        predictions - Predictions array (NUMERIC type)
        weights - Weights array. May be null. If null, a weight of 1.0 is used (NUMERIC type)
        delta - Loss function delta value
        Returns:
        output Huber loss (NUMERIC type)

      • l2Loss

        public INDArray l2Loss​(INDArray var)
        L2 loss: 1/2 * sum(x^2)
        Parameters:
        var - Variable to calculate L2 loss of (NUMERIC type)
        Returns:
        output L2 loss (NUMERIC type)

      • logLoss

        public INDArray logLoss​(INDArray label,
                        INDArray predictions,
                        INDArray weights,
                        LossReduce lossReduce,
                        double epsilon)
        Log loss, i.e., binary cross entropy loss, usually used for binary multi-label classification. Implements:
        -1/numExamples * sum_i (labels[i] * log(predictions[i] + epsilon) + (1-labels[i]) * log(1-predictions[i] + epsilon))
        Parameters:
        label - Label array (NUMERIC type)
        predictions - Predictions array (NUMERIC type)
        weights - Weights array. May be null. If null, a weight of 1.0 is used (NUMERIC type)
        lossReduce - Reduction type for the loss. See LossReduce for more details. Default: LossReduce#MEAN_BY_NONZERO_WEIGHT_COUNT
        epsilon - epsilon
        Returns:
        output Log loss (NUMERIC type)

      • logLoss

        public INDArray logLoss​(INDArray label,
                        INDArray predictions)
        Log loss, i.e., binary cross entropy loss, usually used for binary multi-label classification. Implements:
        -1/numExamples * sum_i (labels[i] * log(predictions[i] + epsilon) + (1-labels[i]) * log(1-predictions[i] + epsilon))
        Parameters:
        label - Label array (NUMERIC type)
        predictions - Predictions array (NUMERIC type)
        Returns:
        output Log loss (NUMERIC type)

      • logPoisson

        public INDArray logPoisson​(INDArray label,
                           INDArray predictions,
                           INDArray weights,
                           LossReduce lossReduce,
                           boolean full)
        Log poisson loss: a loss function used for training classifiers.
        Implements L = exp(c) - z * c where c is log(predictions) and z is labels.
        Parameters:
        label - Label array. Each value should be 0.0 or 1.0 (NUMERIC type)
        predictions - Predictions array (has to be log(x) of actual predictions) (NUMERIC type)
        weights - Weights array. May be null. If null, a weight of 1.0 is used (NUMERIC type)
        lossReduce - Reduction type for the loss. See LossReduce for more details. Default: LossReduce#MEAN_BY_NONZERO_WEIGHT_COUNT
        full - Boolean flag. true for logPoissonFull, false for logPoisson
        Returns:
        output Loss variable (NUMERIC type)

      • logPoisson

        public INDArray logPoisson​(INDArray label,
                           INDArray predictions,
                           INDArray weights,
                           boolean full)
        Log poisson loss: a loss function used for training classifiers.
        Implements L = exp(c) - z * c where c is log(predictions) and z is labels.
        Parameters:
        label - Label array. Each value should be 0.0 or 1.0 (NUMERIC type)
        predictions - Predictions array (has to be log(x) of actual predictions) (NUMERIC type)
        weights - Weights array. May be null. If null, a weight of 1.0 is used (NUMERIC type)
        full - Boolean flag. true for logPoissonFull, false for logPoisson
        Returns:
        output Loss variable (NUMERIC type)

      • meanPairwiseSquaredError

        public INDArray meanPairwiseSquaredError​(INDArray label,
                                         INDArray predictions,
                                         INDArray weights,
                                         LossReduce lossReduce)
        Mean pairwise squared error.
        MPWSE loss calculates the difference between pairs of consecutive elements in the predictions and labels arrays.
        For example, if predictions = [p0, p1, p2] and labels are [l0, l1, l2] then MPWSE is:
        [((p0-p1) - (l0-l1))^2 + ((p0-p2) - (l0-l2))^2 + ((p1-p2) - (l1-l2))^2] / 3
        Parameters:
        label - Label array (NUMERIC type)
        predictions - Predictions array (NUMERIC type)
        weights - Weights array. May be null. If null, a weight of 1.0 is used. Must be either null, scalar, or have shape [batchSize] (NUMERIC type)
        lossReduce - Reduction type for the loss. See LossReduce for more details. Default: LossReduce#MEAN_BY_NONZERO_WEIGHT_COUNT
        Returns:
        output Loss variable, scalar output (NUMERIC type)

      • meanPairwiseSquaredError

        public INDArray meanPairwiseSquaredError​(INDArray label,
                                         INDArray predictions,
                                         INDArray weights)
        Mean pairwise squared error.
        MPWSE loss calculates the difference between pairs of consecutive elements in the predictions and labels arrays.
        For example, if predictions = [p0, p1, p2] and labels are [l0, l1, l2] then MPWSE is:
        [((p0-p1) - (l0-l1))^2 + ((p0-p2) - (l0-l2))^2 + ((p1-p2) - (l1-l2))^2] / 3
        Parameters:
        label - Label array (NUMERIC type)
        predictions - Predictions array (NUMERIC type)
        weights - Weights array. May be null. If null, a weight of 1.0 is used. Must be either null, scalar, or have shape [batchSize] (NUMERIC type)
        Returns:
        output Loss variable, scalar output (NUMERIC type)

      • meanSquaredError

        public INDArray meanSquaredError​(INDArray label,
                                 INDArray predictions,
                                 INDArray weights,
                                 LossReduce lossReduce)
        Mean squared error loss function. Implements (label[i] - prediction[i])^2 - i.e., squared error on a per-element basis.
        When averaged (using LossReduce#MEAN_BY_WEIGHT or LossReduce#MEAN_BY_NONZERO_WEIGHT_COUNT (the default))
        this is the mean squared error loss function.
        Parameters:
        label - Label array (NUMERIC type)
        predictions - Predictions array (NUMERIC type)
        weights - Weights array. May be null. If null, a weight of 1.0 is used (NUMERIC type)
        lossReduce - Reduction type for the loss. See LossReduce for more details. Default: LossReduce#MEAN_BY_NONZERO_WEIGHT_COUNT
        Returns:
        output Loss variable (NUMERIC type)

      • meanSquaredError

        public INDArray meanSquaredError​(INDArray label,
                                 INDArray predictions,
                                 INDArray weights)
        Mean squared error loss function. Implements (label[i] - prediction[i])^2 - i.e., squared error on a per-element basis.
        When averaged (using LossReduce#MEAN_BY_WEIGHT or LossReduce#MEAN_BY_NONZERO_WEIGHT_COUNT (the default))
        this is the mean squared error loss function.
        Parameters:
        label - Label array (NUMERIC type)
        predictions - Predictions array (NUMERIC type)
        weights - Weights array. May be null. If null, a weight of 1.0 is used (NUMERIC type)
        Returns:
        output Loss variable (NUMERIC type)

      • sigmoidCrossEntropy

        public INDArray sigmoidCrossEntropy​(INDArray label,
                                    INDArray predictionLogits,
                                    INDArray weights,
                                    LossReduce lossReduce,
                                    double labelSmoothing)
        Sigmoid cross entropy: applies the sigmoid activation function on the input logits (input "pre-sigmoid preductions")
        and implements the binary cross entropy loss function. This implementation is numerically more stable than using
        standard (but separate) sigmoid activation function and log loss (binary cross entropy) loss function.
        Implements:
        -1/numExamples * sum_i (labels[i] * log(sigmoid(logits[i])) + (1-labels[i]) * log(1-sigmoid(logits[i])))
        though this is done in a mathematically equivalent but more numerical stable form.

        When label smoothing is > 0, the following label smoothing is used:

        
 numClasses = labels.size(1);<br>
 label = (1.0 - labelSmoothing) * label + 0.5 * labelSmoothing

        Parameters:
        label - Label array (NUMERIC type)
        predictionLogits - Predictions array (NUMERIC type)
        weights - Weights array. May be null. If null, a weight of 1.0 is used (NUMERIC type)
        lossReduce - Reduction type for the loss. See LossReduce for more details. Default: LossReduce#MEAN_BY_NONZERO_WEIGHT_COUNT
        labelSmoothing - Label smoothing value. Default value: 0
        Returns:
        output Loss variable (NUMERIC type)

      • sigmoidCrossEntropy

        public INDArray sigmoidCrossEntropy​(INDArray label,
                                    INDArray predictionLogits,
                                    INDArray weights)
        Sigmoid cross entropy: applies the sigmoid activation function on the input logits (input "pre-sigmoid preductions")
        and implements the binary cross entropy loss function. This implementation is numerically more stable than using
        standard (but separate) sigmoid activation function and log loss (binary cross entropy) loss function.
        Implements:
        -1/numExamples * sum_i (labels[i] * log(sigmoid(logits[i])) + (1-labels[i]) * log(1-sigmoid(logits[i])))
        though this is done in a mathematically equivalent but more numerical stable form.

        When label smoothing is > 0, the following label smoothing is used:

        
 numClasses = labels.size(1);<br>
 label = (1.0 - labelSmoothing) * label + 0.5 * labelSmoothing

        Parameters:
        label - Label array (NUMERIC type)
        predictionLogits - Predictions array (NUMERIC type)
        weights - Weights array. May be null. If null, a weight of 1.0 is used (NUMERIC type)
        Returns:
        output Loss variable (NUMERIC type)

      • softmaxCrossEntropy

        public INDArray softmaxCrossEntropy​(INDArray oneHotLabels,
                                    INDArray logitPredictions,
                                    INDArray weights,
                                    LossReduce lossReduce,
                                    double labelSmoothing)
        Applies the softmax activation function to the input, then implement multi-class cross entropy:
        -sum_classes label[i] * log(p[c]) where p = softmax(logits)
        If LossReduce#NONE is used, returned shape is [numExamples] out for [numExamples, numClasses] predicitons/labels;
        otherwise, the output is a scalar.


        When label smoothing is > 0, the following label smoothing is used:


        
 numClasses = labels.size(1);<br>
 oneHotLabel = (1.0 - labelSmoothing) * oneHotLabels + labelSmoothing/numClasses

        Parameters:
        oneHotLabels - Label array. Should be one-hot per example and same shape as predictions (for example, [mb, nOut]) (NUMERIC type)
        logitPredictions - Predictions array (pre-softmax) (NUMERIC type)
        weights - Weights array. May be null. If null, a weight of 1.0 is used (NUMERIC type)
        lossReduce - Reduction type for the loss. See LossReduce for more details. Default: LossReduce#MEAN_BY_NONZERO_WEIGHT_COUNT
        labelSmoothing - Label smoothing value. Default value: 0
        Returns:
        output Loss variable (NUMERIC type)

      • softmaxCrossEntropy

        public INDArray softmaxCrossEntropy​(INDArray oneHotLabels,
                                    INDArray logitPredictions,
                                    INDArray weights)
        Applies the softmax activation function to the input, then implement multi-class cross entropy:
        -sum_classes label[i] * log(p[c]) where p = softmax(logits)
        If LossReduce#NONE is used, returned shape is [numExamples] out for [numExamples, numClasses] predicitons/labels;
        otherwise, the output is a scalar.


        When label smoothing is > 0, the following label smoothing is used:


        
 numClasses = labels.size(1);<br>
 oneHotLabel = (1.0 - labelSmoothing) * oneHotLabels + labelSmoothing/numClasses

        Parameters:
        oneHotLabels - Label array. Should be one-hot per example and same shape as predictions (for example, [mb, nOut]) (NUMERIC type)
        logitPredictions - Predictions array (pre-softmax) (NUMERIC type)
        weights - Weights array. May be null. If null, a weight of 1.0 is used (NUMERIC type)
        Returns:
        output Loss variable (NUMERIC type)

      • sparseSoftmaxCrossEntropy

        public INDArray sparseSoftmaxCrossEntropy​(INDArray logits,
                                          INDArray labels)
        As per softmaxCrossEntropy(String, SDVariable, SDVariable, LossReduce) but the labels variable
        is represented as an integer array instead of the equivalent one-hot array.
        i.e., if logits are rank N, then labels have rank N-1
        Parameters:
        logits - Logits array ("pre-softmax activations") (NUMERIC type)
        labels - Labels array. Must be an integer type. (INT type)
        Returns:
        output Softmax cross entropy (NUMERIC type)