Computes the hinge loss between labels and predictions.
loss = maximum(1 - labels * predictions, 0)
.
labels
values are expected to be -1 or 1. If binary (0 or 1) labels are provided,
they will be converted to -1 or 1.
Standalone usage:
Operand<TFloat32> labels = tf.constant(new float[][] { {0.f, 1.f}, {0.f, 0.f} }); Operand<TFloat32> predictions = tf.constant(new float[][] { {0.6f, 0.4f}, {0.4f, 0.6f} }); Hinge hingeLoss = new Hinge(tf); Operand<TFloat32> result = hingeLoss.call(labels, predictions); // produces 1.3f
Calling with sample weight:
Operand<TFloat32> sampleWeight = tf.constant(new float[] {1.f, 0.f}); Operand<TFloat32> result = hingeLoss.call(labels, predictions, sampleWeight); // produces 0.55f
Using SUM
reduction type:
Hinge hingeLoss = new Hinge(tf, Reduction.SUM); Operand<TFloat32> result = hingeLoss.call(labels, predictions); // produces 2.6f
Using NONE
reduction type:
Hinge hingeLoss = new Hinge(tf, Reduction.NONE); Operand<TFloat32> result = hingeLoss.call(labels, predictions); // produces [1.1f, 1.5f]
Inherited Fields
Public Constructors
Hinge(Ops tf)
Creates a Hinge Loss using
getSimpleName() as the loss name and a Loss Reduction
of REDUCTION_DEFAULT |
|
Public Methods
<T extends TNumber> Operand<T> |
Inherited Methods
Public Constructors
public Hinge (Ops tf)
Creates a Hinge Loss using getSimpleName()
as the loss name and a Loss Reduction
of REDUCTION_DEFAULT
Parameters
tf | the TensorFlow Ops |
---|
public Hinge (Ops tf, Reduction reduction)
Creates a Hinge Loss using getSimpleName()
as the loss name
Parameters
tf | the TensorFlow Ops |
---|---|
reduction | Type of Reduction to apply to the loss. |
public Hinge (Ops tf, String name, Reduction reduction)
Creates a Hinge
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.
If run in Graph mode, the computation will throw TFInvalidArgumentException
if the label values are not in the set
[-1., 0., 1.]. In Eager Mode, this call will throw IllegalArgumentException
, if the
label values are not in the set [-1., 0., 1.].
Parameters
labels | the truth values or labels, must be either -1, 0, or 1. Values are expected to be -1 or 1. If binary (0 or 1) labels are provided they will be converted to -1 or 1. |
---|---|
predictions | the predictions, values must be in the range [0. to 1.] inclusive. |
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
Throws
IllegalArgumentException | if the predictions are outside the range [0.-1.]. |
---|