<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/losses/losses.py#L915-L1016) |

Computes the crossentropy loss between the labels and predictions.

Inherits From: [`Loss`](https://www.tensorflow.org/api_docs/python/tf/keras/Loss)

    tf.keras.losses.CategoricalCrossentropy(
        from_logits=False,
        label_smoothing=0.0,
        axis=-1,
        reduction='sum_over_batch_size',
        name='categorical_crossentropy',
        dtype=None
    )

### Used in the notebooks

| Used in the guide | Used in the tutorials |
|---|---|
| - [Effective Tensorflow 2](https://www.tensorflow.org/guide/effective_tf2) - [Debug a TensorFlow 2 migrated training pipeline](https://www.tensorflow.org/guide/migrate/migration_debugging) | - [Adversarial example using FGSM](https://www.tensorflow.org/tutorials/generative/adversarial_fgsm) - [Retraining an Image Classifier](https://www.tensorflow.org/hub/tutorials/tf2_image_retraining) - [Implement Differential Privacy with TensorFlow Privacy](https://www.tensorflow.org/responsible_ai/privacy/tutorials/classification_privacy) - [Assess privacy risks with the TensorFlow Privacy Report](https://www.tensorflow.org/responsible_ai/privacy/tutorials/privacy_report) - [On-Device Training with TensorFlow Lite](https://www.tensorflow.org/lite/examples/on_device_training/overview) |

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 `num_classes` floating
point values per feature, i.e., the shape of both `y_pred` and `y_true` are
`[batch_size, num_classes]`.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `from_logits` | Whether `y_pred` is expected to be a logits tensor. By default, we assume that `y_pred` encodes a probability distribution. |
| `label_smoothing` | Float in \[0, 1\]. When \> 0, label values are smoothed, meaning the confidence on label values are relaxed. For example, if `0.1`, use `0.1 / num_classes` for non-target labels and `0.9 + 0.1 / num_classes` for target labels. |
| `axis` | The axis along which to compute crossentropy (the features axis). Defaults to `-1`. |
| `reduction` | Type of reduction to apply to the loss. In almost all cases this should be `"sum_over_batch_size"`. Supported options are `"sum"`, `"sum_over_batch_size"`, `"mean"`, `"mean_with_sample_weight"` or `None`. `"sum"` sums the loss, `"sum_over_batch_size"` and `"mean"` sum the loss and divide by the sample size, and `"mean_with_sample_weight"` sums the loss and divides by the sum of the sample weights. `"none"` and `None` perform no aggregation. Defaults to `"sum_over_batch_size"`. |
| `name` | Optional name for the loss instance. |
| `dtype` | The dtype of the loss's computations. Defaults to `None`, which means using [`keras.backend.floatx()`](https://www.tensorflow.org/api_docs/python/tf/keras/backend/floatx). [`keras.backend.floatx()`](https://www.tensorflow.org/api_docs/python/tf/keras/backend/floatx) is a `"float32"` unless set to different value (via [`keras.backend.set_floatx()`](https://www.tensorflow.org/api_docs/python/tf/keras/backend/set_floatx)). If a [`keras.DTypePolicy`](https://www.tensorflow.org/api_docs/python/tf/keras/DTypePolicy) is provided, then the `compute_dtype` will be utilized. |

<br />

#### Examples:

#### Standalone usage:

    y_true = np.array([[0, 1, 0], [0, 0, 1]])
    y_pred = np.array([[0.05, 0.95, 0], [0.1, 0.8, 0.1]])
    # Using 'auto'/'sum_over_batch_size' reduction type.
    cce = keras.losses.CategoricalCrossentropy()
    cce(y_true, y_pred)
    1.177

    # Calling with 'sample_weight'.
    cce(y_true, y_pred, sample_weight=np.array([0.3, 0.7]))
    0.814

    # Using 'sum' reduction type.
    cce = keras.losses.CategoricalCrossentropy(
        reduction="sum")
    cce(y_true, y_pred)
    2.354

    # Using 'none' reduction type.
    cce = keras.losses.CategoricalCrossentropy(
        reduction=None)
    cce(y_true, y_pred)
    array([0.0513, 2.303], dtype=float32)

Usage with the `compile()` API:

    model.compile(optimizer='sgd',
                  loss=keras.losses.CategoricalCrossentropy())

<br />

<br />

<br />

| ## Attributes ||
|---|---|
| `dtype` | <br /> <br /> |

<br />

## Methods

### `call`

[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/losses/losses.py#L28-L34)

    call(
        y_true, y_pred
    )

### `from_config`

[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/losses/losses.py#L42-L46)

    @classmethod
    from_config(
        config
    )

### `get_config`

[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/losses/losses.py#L1007-L1016)

    get_config()

### `__call__`

[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/losses/loss.py#L56-L85)

    __call__(
        y_true, y_pred, sample_weight=None
    )

Call self as a function.