MeanAbsolutePercentageError

public class MeanAbsolutePercentageError

Computes the mean absolute percentage error between labels and predictions.

loss = 100 * abs(labels - predictions) / labels

Standalone usage: 

    Operand<TFloat32> labels =
        tf.constant(new float[][] { {2.f, 1.f}, {2.f, 3.f} });
    Operand<TFloat32> predictions =
        tf.constant(new float[][] { {1.f, 1.f}, {1.f, 0.f} });
    MeanAbsolutePercentageError mape = new MeanAbsolutePercentageError(tf);
    Operand<TFloat32> result = mape.call(labels, predictions);
    // produces 50f

Calling with sample weight: 

    Operand<TFloat32> sampleWeight = tf.constant(new float[] {0.7f, 0.3f});
    Operand<TFloat32> result = mape.call(labels, predictions, sampleWeight);
    // produces 20f

Using SUM reduction type: 

    MeanAbsolutePercentageError mape = new MeanAbsolutePercentageError(tf, Reduction.SUM);
    Operand<TFloat32> result = mape.call(labels, predictions);
    // produces 100.0f

Using NONE reduction type: 

    MeanAbsolutePercentageError mape = new MeanAbsolutePercentageError(tf, Reduction.NONE);
    Operand<TFloat32> result = mape.call(labels, predictions);
    // produces [25f, 75f]

Inherited Fields

org.tensorflow.framework.losses.Loss
public static final Reduction REDUCTION_DEFAULT

Public Constructors

MeanAbsolutePercentageError(Ops tf)
Creates a MeanAbsolutePercentageError Loss using getSimpleName() as the loss name and a Loss Reduction of REDUCTION_DEFAULT
MeanAbsolutePercentageError(Ops tf, Reduction reduction)
Creates a MeanAbsolutePercentageError Loss using getSimpleName() as the loss name
MeanAbsolutePercentageError(Ops tf, String name, Reduction reduction)
Creates a MeanAbsolutePercentageError

Public Methods

<T extends TNumber> Operand<T>
call(Operand<? extends TNumber> labels, Operand<T> predictions, Operand<T> sampleWeights)
Generates an Operand that calculates the loss.

Inherited Methods

org.tensorflow.framework.losses.Loss
abstract <T extends TNumber> Operand<T>
call(Operand<? extends TNumber> labels, Operand<T> predictions, Operand<T> sampleWeights)
Generates an Operand that calculates the loss.
<T extends TNumber> Operand<T>
call(Operand<? extends TNumber> labels, Operand<T> predictions)
Calculates the loss
Reduction
getReduction()
Gets the loss reduction
Ops
getTF()
Gets the TensorFlow Ops
boolean
equals(Object arg0)
final Class<?>
getClass()
int
hashCode()
final void
notify()
final void
notifyAll()
String
toString()
final void
wait(long arg0, int arg1)
final void
wait(long arg0)
final void
wait()

Public Constructors

public MeanAbsolutePercentageError (Ops tf)

Creates a MeanAbsolutePercentageError Loss using getSimpleName() as the loss name and a Loss Reduction of REDUCTION_DEFAULT

Parameters
tf the TensorFlow Ops

public MeanAbsolutePercentageError (Ops tf, Reduction reduction)

Creates a MeanAbsolutePercentageError Loss using getSimpleName() as the loss name

Parameters
tf the TensorFlow Ops
reduction Type of Reduction to apply to the loss.

public MeanAbsolutePercentageError (Ops tf, String name, Reduction reduction)

Creates a MeanAbsolutePercentageError

Parameters
tf the TensorFlow Ops
name the name of the loss
reduction Type of Reduction to apply to the loss.

Public Methods

public Operand<T> call (Operand<? extends TNumber> labels, Operand<T> predictions, Operand<T> sampleWeights)

Generates an Operand that calculates the loss.

Parameters
labels the truth values or labels
predictions the predictions
sampleWeights Optional sampleWeights acts as a coefficient for the loss. If a scalar is provided, then the loss is simply scaled by the given value. If SampleWeights is a tensor of size [batch_size], then the total loss for each sample of the batch is rescaled by the corresponding element in the SampleWeights vector. If the shape of SampleWeights is [batch_size, d0, .. dN-1] (or can be broadcast to this shape), then each loss element of predictions is scaled by the corresponding value of SampleWeights. (Note on dN-1: all loss functions reduce by 1 dimension, usually axis=-1.)
Returns
  • the loss