<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#L1019-L1170) |

Computes the alpha balanced focal crossentropy loss.

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

    tf.keras.losses.CategoricalFocalCrossentropy(
        alpha=0.25,
        gamma=2.0,
        from_logits=False,
        label_smoothing=0.0,
        axis=-1,
        reduction='sum_over_batch_size',
        name='categorical_focal_crossentropy',
        dtype=None
    )

Use this crossentropy loss function when there are two or more label
classes and if you want to handle class imbalance without using
`class_weights`. We expect labels to be provided in a `one_hot`
representation.

According to [Lin et al., 2018](https://arxiv.org/pdf/1708.02002.pdf), it
helps to apply a focal factor to down-weight easy examples and focus more on
hard examples. The general formula for the focal loss (FL)
is as follows:

`FL(p_t) = (1 - p_t) ** gamma * log(p_t)`

where `p_t` is defined as follows:
`p_t = output if y_true == 1, else 1 - output`

`(1 - p_t) ** gamma` is the `modulating_factor`, where `gamma` is a focusing
parameter. When `gamma` = 0, there is no focal effect on the cross entropy.
`gamma` reduces the importance given to simple examples in a smooth manner.

The authors use alpha-balanced variant of focal loss (FL) in the paper:
`FL(p_t) = -alpha * (1 - p_t) ** gamma * log(p_t)`

where `alpha` is the weight factor for the classes. If `alpha` = 1, the
loss won't be able to handle class imbalance properly as all
classes will have the same weight. This can be a constant or a list of
constants. If alpha is a list, it must have the same length as the number
of classes.

The formula above can be generalized to:
`FL(p_t) = alpha * (1 - p_t) ** gamma * CrossEntropy(y_true, y_pred)`

where minus comes from `CrossEntropy(y_true, y_pred)` (CE).

Extending this to multi-class case is straightforward:
`FL(p_t) = alpha * (1 - p_t) ** gamma * CategoricalCE(y_true, y_pred)`

In the snippet below, there is `num_classes` floating pointing values per
example. The shape of both `y_pred` and `y_true` are
`(batch_size, num_classes)`.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `alpha` | A weight balancing factor for all classes, default is `0.25` as mentioned in the reference. It can be a list of floats or a scalar. In the multi-class case, alpha may be set by inverse class frequency by using `compute_class_weight` from `sklearn.utils`. |
| `gamma` | A focusing parameter, default is `2.0` as mentioned in the reference. It helps to gradually reduce the importance given to simple (easy) examples in a smooth manner. |
| `from_logits` | Whether `output` is expected to be a logits tensor. By default, we consider that `output` 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 = [[0., 1., 0.], [0., 0., 1.]]
    y_pred = [[0.05, 0.95, 0], [0.1, 0.8, 0.1]]
    # Using 'auto'/'sum_over_batch_size' reduction type.
    cce = keras.losses.CategoricalFocalCrossentropy()
    cce(y_true, y_pred)
    0.23315276

    # Calling with 'sample_weight'.
    cce(y_true, y_pred, sample_weight=np.array([0.3, 0.7]))
    0.1632

    # Using 'sum' reduction type.
    cce = keras.losses.CategoricalFocalCrossentropy(
        reduction="sum")
    cce(y_true, y_pred)
    0.46631

    # Using 'none' reduction type.
    cce = keras.losses.CategoricalFocalCrossentropy(
        reduction=None)
    cce(y_true, y_pred)
    array([3.2058331e-05, 4.6627346e-01], dtype=float32)

Usage with the `compile()` API:

    model.compile(optimizer='adam',
                  loss=keras.losses.CategoricalFocalCrossentropy())

<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#L1159-L1170)

    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.