# tf.keras.losses.Huber

<br />

|---|---|
| [![](https://www.tensorflow.org/images/tf_logo_32px.png) TensorFlow 2 version](https://www.tensorflow.org/api_docs/python/tf/keras/losses/Huber) | [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/losses.py#L708-L754) |

Computes the Huber loss between `y_true` and `y_pred`.

#### View aliases


**Compat aliases for migration**

See
[Migration guide](https://www.tensorflow.org/guide/migrate) for
more details.

[`tf.compat.v1.keras.losses.Huber`](https://www.tensorflow.org/api_docs/python/tf/keras/losses/Huber), \`tf.compat.v2.keras.losses.Huber\`, \`tf.compat.v2.losses.Huber\`

<br />

    tf.keras.losses.Huber(
        delta=1.0, reduction=losses_utils.ReductionV2.AUTO, name='huber_loss'
    )

For each value x in `error = y_true - y_pred`:

    loss = 0.5 * x^2                  if |x| <= d
    loss = 0.5 * d^2 + d * (|x| - d)  if |x| > d

where d is `delta`. See: <https://en.wikipedia.org/wiki/Huber_loss>

#### Usage:

    l = tf.keras.losses.Huber()
    loss = l([0., 1., 1.], [1., 0., 1.])
    print('Loss: ', loss.numpy())  # Loss: 0.333

Usage with the `compile` API:

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

<br />

<br />

<br />

| ## Args ||
|---|---|
| `delta` | A float, the point where the Huber loss function changes from a quadratic to linear. |
| `reduction` | (Optional) Type of [`tf.keras.losses.Reduction`](https://www.tensorflow.org/api_docs/python/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`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/distribute/Strategy), outside of built-in training loops such as [`tf.keras`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/keras) `compile` and `fit`, using `AUTO` or `SUM_OVER_BATCH_SIZE` will raise an error. Please see https://www.tensorflow.org/alpha/tutorials/distribute/training_loops for more details on this. |
| `name` | Optional name for the op. |

<br />

## Methods

### `from_config`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/losses.py#L128-L138)

    @classmethod
    from_config(
        config
    )

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

<br />

<br />

<br />

| Args ||
|---|---|
| `config` | Output of `get_config()`. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A `Loss` instance. ||

<br />

### `get_config`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/losses.py#L218-L223)

    get_config()

### `__call__`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/losses.py#L94-L126)

    __call__(
        y_true, y_pred, sample_weight=None
    )

Invokes the `Loss` instance.

<br />

<br />

<br />

| 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 on`dN-1`: all loss functions reduce by 1 dimension, usually axis=-1.) |

<br />

<br />

<br />

<br />

| 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.) ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `ValueError` | If the shape of `sample_weight` is invalid. |

<br />