TF 2.0 is out! Get hands-on practice at TF World, Oct 28-31. Use code TF20 for 20% off select passes. Register now


View source on GitHub

Class CategoricalCrossentropy

Computes the crossentropy loss between the labels and predictions.


  • Class tf.compat.v1.keras.losses.CategoricalCrossentropy
  • Class tf.compat.v2.keras.losses.CategoricalCrossentropy
  • Class tf.compat.v2.losses.CategoricalCrossentropy
  • Class tf.losses.CategoricalCrossentropy

Used in the guide:

Used in the tutorials:

Use this crossentropy loss function when there are two or more label classes. We expect labels to be provided in a one_hot representation. If you want to provide labels as integers, please use SparseCategoricalCrossentropy loss. There should be # classes floating point values per feature.

In the snippet below, there is # classes floating pointing values per example. The shape of both y_pred and y_true are [batch_size, num_classes].


cce = tf.keras.losses.CategoricalCrossentropy()
loss = cce(
  [[1., 0., 0.], [0., 1., 0.], [0., 0., 1.]],
  [[.9, .05, .05], [.05, .89, .06], [.05, .01, .94]])
print('Loss: ', loss.numpy())  # Loss: 0.0945

Usage with the compile API:

model = tf.keras.Model(inputs, outputs)
model.compile('sgd', loss=tf.keras.losses.CategoricalCrossentropy())


  • 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.
  • label_smoothing: Float in [0, 1]. When > 0, label values are smoothed, meaning the confidence on label values are relaxed. e.g. label_smoothing=0.2 means that we will use a value of 0.1 for label 0 and 0.9 for label 1"
  • 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 for more details on this.
  • name: Optional name for the op.


View source


Initialize self. See help(type(self)) for accurate signature.



View source


Invokes the Loss instance.


  • 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.)


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.)


  • ValueError: If the shape of sample_weight is invalid.


View source


Instantiates a Loss from its config (output of get_config()).


  • config: Output of get_config().


A Loss instance.


View source