Computes the crossentropy loss between labels and predictions.
Use this crossentropy loss function when there are two or more label classes. The labels are
expected to be provided as integers. If you want to provide labels using one-hot
representation, please use CategoricalCrossentropy
loss. There should be # classes
floating point values per feature for predictions
and a single floating
point value per feature for label
.
In the snippet below, there is a single floating point value per example for labels
and # classes
floating pointing values per example for predictions
. The shape of labels
is [batch_size]
and the shape of
predictions
is [batch_size, num_classes]
.
Standalone usage:
Operand<TFloat32> labels = tf.constant(new float[] {1, 2}); Operand<TFloat32> predictions = tf.constant(new float[][] { {0.05f, 0.95f, 0f}, {0.1f, 0.8f, 0.1f} }); SparseCategoricalCrossentropy sparseCCE = new SparseCategoricalCrossentropy(tf); Operand<TFloat32> result = sparseCCE.call(labels, predictions); // produces 1.177f
Calling with sample weight:
Operand<TFloat32> sampleWeight = tf.constant(new float[] {0.3f, 0.7f}); Operand<TFloat32> result = sparseCCE.call(labels, predictions, sampleWeight); // produces 0.814f
Using SUM
reduction type:
SparseCategoricalCrossentropy sparseCCE = new SparseCategoricalCrossentropy(tf, Reduction.SUM); Operand<TFloat32> result = sparseCCE.call(labels, predictions); // produces 2.354f
Using NONE
reduction type:
SparseCategoricalCrossentropy sparseCCE = new SparseCategoricalCrossentropy(tf, Reduction.NONE); Operand<TFloat32> result = sparseCCE.call(labels, predictions); // produces [0.0513f, 2.303f]
Constants
int | AXIS_DEFAULT | |
boolean | FROM_LOGITS_DEFAULT |
Inherited Fields
Public Constructors
SparseCategoricalCrossentropy(Ops tf)
Creates a SparseCategoricalCrossentropy loss using
getSimpleName() as the loss
name, a Loss Reduction of REDUCTION_DEFAULT , and fromLogits=FROM_LOGITS_DEFAULT . |
|
SparseCategoricalCrossentropy(Ops tf, String name)
Creates a SparseCategoricalCrossentropy loss using a Loss Reduction of
REDUCTION_DEFAULT , and fromLogits=FROM_LOGITS_DEFAULT . |
|
SparseCategoricalCrossentropy(Ops tf, Reduction reduction)
Creates a SparseCategoricalCrossentropy loss using
getSimpleName() as the loss
name, with Reduction.AUTO and fromLogits=FROM_LOGITS_DEFAULT . |
|
SparseCategoricalCrossentropy(Ops tf, String name, Reduction reduction)
Creates a SparseCategoricalCrossentropy loss with Reduction.AUTO and fromLogits=
FROM_LOGITS_DEFAULT . |
|
SparseCategoricalCrossentropy(Ops tf, String name, boolean fromLogits)
Creates a SparseCategoricalCrossentropy using a Loss Reduction of
REDUCTION_DEFAULT , and fromLogits=FROM_LOGITS_DEFAULT . |
|
SparseCategoricalCrossentropy(Ops tf, boolean fromLogits)
Creates a SparseCategoricalCrossentropy loss using
getSimpleName() as the loss
name, a Loss Reduction of REDUCTION_DEFAULT and fromLogits=FROM_LOGITS_DEFAULT . |
|
SparseCategoricalCrossentropy(Ops tf, boolean fromLogits, Reduction reduction)
Creates a SparseCategoricalCrossentropy loss using
getSimpleName() as the loss
name, |
|
SparseCategoricalCrossentropy(Ops tf, String name, boolean fromLogits, Reduction reduction, int axis)
Creates a SparseCategoricalCrossentropy
|
Public Methods
<T extends TNumber> Operand<T> |
Inherited Methods
Constants
public static final int AXIS_DEFAULT
public static final boolean FROM_LOGITS_DEFAULT
Public Constructors
public SparseCategoricalCrossentropy (Ops tf)
Creates a SparseCategoricalCrossentropy loss using getSimpleName()
as the loss
name, a Loss Reduction of REDUCTION_DEFAULT
, and fromLogits=FROM_LOGITS_DEFAULT
.
Parameters
tf | the TensorFlow Ops |
---|
public SparseCategoricalCrossentropy (Ops tf, String name)
Creates a SparseCategoricalCrossentropy loss using a Loss Reduction of REDUCTION_DEFAULT
, and fromLogits=FROM_LOGITS_DEFAULT
.
Parameters
tf | the TensorFlow Ops |
---|---|
name | the name of this loss function |
public SparseCategoricalCrossentropy (Ops tf, Reduction reduction)
Creates a SparseCategoricalCrossentropy loss using getSimpleName()
as the loss
name, with Reduction.AUTO and fromLogits=FROM_LOGITS_DEFAULT
.
Parameters
tf | the TensorFlow Ops |
---|---|
reduction | Type of Reduction to apply to loss. |
public SparseCategoricalCrossentropy (Ops tf, String name, Reduction reduction)
Creates a SparseCategoricalCrossentropy loss with Reduction.AUTO and fromLogits=FROM_LOGITS_DEFAULT
.
Parameters
tf | the TensorFlow Ops |
---|---|
name | the name of this loss function |
reduction | Type of Reduction to apply to loss. |
public SparseCategoricalCrossentropy (Ops tf, String name, boolean fromLogits)
Creates a SparseCategoricalCrossentropy using a Loss Reduction of REDUCTION_DEFAULT
, and fromLogits=FROM_LOGITS_DEFAULT
.
Parameters
tf | the TensorFlow Ops |
---|---|
name | the name of this loss function |
fromLogits | Whether to interpret predictions as a tensor of logit values |
public SparseCategoricalCrossentropy (Ops tf, boolean fromLogits)
Creates a SparseCategoricalCrossentropy loss using getSimpleName()
as the loss
name, a Loss Reduction of REDUCTION_DEFAULT
and fromLogits=FROM_LOGITS_DEFAULT
.
Parameters
tf | the TensorFlow Ops |
---|---|
fromLogits | Whether to interpret predictions as a tensor of logit values |
public SparseCategoricalCrossentropy (Ops tf, boolean fromLogits, Reduction reduction)
Creates a SparseCategoricalCrossentropy loss using getSimpleName()
as the loss
name,
Parameters
tf | the TensorFlow Ops |
---|---|
fromLogits | Whether to interpret predictions as a tensor of logit values |
reduction | Type of Reduction to apply to loss. |
public SparseCategoricalCrossentropy (Ops tf, String name, boolean fromLogits, Reduction reduction, int axis)
Creates a SparseCategoricalCrossentropy
Parameters
tf | the TensorFlow Ops |
---|---|
name | the name of this loss function |
fromLogits | Whether to interpret predictions as a tensor of logit values |
reduction | Type of Reduction to apply to loss. |
axis | The channels axis. axis=-1 corresponds to data format `Channels Last'
and axis=1 corresponds to data format 'Channels First'.
|
Public Methods
public Operand<T> call (Operand<? extends TNumber> labels, Operand<T> predictions, Operand<T> sampleWeights)
Generates an Operand the calculates the loss.
If run in Graph mode, the computation will throw TFInvalidArgumentException
if the predictions values are outside the
range o [0. to 1.]. In Eager Mode, this call will throw IllegalArgumentException
, if
the predictions values are outside the range o [0. to 1.]
Parameters
labels | the truth values or labels |
---|---|
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.]. |
---|