Computes the crossentropy loss between the labels and predictions.
tf.keras.losses.SparseCategoricalCrossentropy(
from_logits=False, reduction=losses_utils.ReductionV2.AUTO,
name='sparse_categorical_crossentropy'
)
Use this crossentropy loss function when there are two or more label classes.
We expect labels 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 y_pred
and a single floating point value per feature for y_true
.
In the snippet below, there is a single floating point value per example for
y_true
and # classes
floating pointing values per example for y_pred
.
The shape of y_true
is [batch_size]
and the shape of y_pred
is
[batch_size, num_classes]
.
Usage:
cce = tf.keras.losses.SparseCategoricalCrossentropy()
loss = cce(
tf.convert_to_tensor([0, 1, 2]),
tf.convert_to_tensor([[.9, .05, .05], [.5, .89, .6], [.05, .01, .94]]))
print('Loss: ', loss.numpy()) # Loss: 0.3239
Usage with the compile
API:
model = tf.keras.Model(inputs, outputs)
model.compile('sgd', loss=tf.keras.losses.SparseCategoricalCrossentropy())
Args |
from_logits
|
Whether y_pred is expected to be a logits tensor. By default,
we assume that y_pred encodes a probability distribution.
Note: Using from_logits=True may be more numerically stable.
|
reduction
|
(Optional) Type of tf.keras.losses.Reduction to apply to loss.
Default value is AUTO . AUTO indicates that the reduction option will
be determined by the usage context. For almost all cases this defaults to
SUM_OVER_BATCH_SIZE .
When used with tf.distribute.Strategy , outside of built-in training
loops such as tf.keras compile and fit , using AUTO or
SUM_OVER_BATCH_SIZE will raise an error. Please see
https://www.tensorflow.org/tutorials/distribute/custom_training
for more details on this.
|
name
|
Optional name for the op.
|
Methods
from_config
View source
@classmethod
from_config(
config
)
Instantiates a Loss
from its config (output of get_config()
).
Args |
config
|
Output of get_config() .
|
get_config
View source
get_config()
__call__
View source
__call__(
y_true, y_pred, sample_weight=None
)
Invokes the Loss
instance.
Args |
y_true
|
Ground truth values. shape = [batch_size, d0, .. dN]
|
y_pred
|
The predicted values. shape = [batch_size, d0, .. dN]
|
sample_weight
|
Optional sample_weight acts as a
coefficient for the loss. If a scalar is provided, then the loss is
simply scaled by the given value. If sample_weight 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 sample_weight vector. If
the shape of sample_weight is [batch_size, d0, .. dN-1] (or can be
broadcasted to this shape), then each loss element of y_pred is scaled
by the corresponding value of sample_weight . (Note ondN-1 : all loss
functions reduce by 1 dimension, usually axis=-1.)
|
Returns |
Weighted loss float Tensor . If reduction is NONE , this has
shape [batch_size, d0, .. dN-1] ; otherwise, it is scalar. (Note dN-1
because all loss functions reduce by 1 dimension, usually axis=-1.)
|
Raises |
ValueError
|
If the shape of sample_weight is invalid.
|