# tf.keras.metrics.squared_hinge

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/keras-team/keras/tree/v2.13.1/keras/losses.py#L1875-L1906) |

Computes the squared hinge loss between `y_true` \& `y_pred`.

#### View aliases


**Main aliases**

[`tf.keras.losses.squared_hinge`](https://www.tensorflow.org/api_docs/python/tf/keras/metrics/squared_hinge), [`tf.losses.squared_hinge`](https://www.tensorflow.org/api_docs/python/tf/keras/metrics/squared_hinge), [`tf.metrics.squared_hinge`](https://www.tensorflow.org/api_docs/python/tf/keras/metrics/squared_hinge)
**Compat aliases for migration**

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

\`tf.compat.v1.keras.losses.squared_hinge\`, \`tf.compat.v1.keras.metrics.squared_hinge\`

<br />

    tf.keras.metrics.squared_hinge(
        y_true, y_pred
    )

`loss = mean(square(maximum(1 - y_true * y_pred, 0)), axis=-1)`

#### Standalone usage:

    y_true = np.random.choice([-1, 1], size=(2, 3))
    y_pred = np.random.random(size=(2, 3))
    loss = tf.keras.losses.squared_hinge(y_true, y_pred)
    assert loss.shape == (2,)
    assert np.array_equal(
        loss.numpy(),
        np.mean(np.square(np.maximum(1. - y_true * y_pred, 0.)), axis=-1))

<br />

<br />

<br />

| ## Args ||
|---|---|
| `y_true` | The ground truth values. `y_true` values are expected to be -1 or <br /> 1. If binary (0 or 1) labels are provided we will convert them to -1 or 2. shape = `[batch_size, d0, .. dN]`. |
| `y_pred` | The predicted values. shape = `[batch_size, d0, .. dN]`. |

<br />

<br />

<br />

| ## Returns ||
|---|---|
| Squared hinge loss values. shape = `[batch_size, d0, .. dN-1]`. ||

<br />