<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/ops/nn.py#L509-L543) |

Hard SiLU activation function, also known as Hard Swish.

#### View aliases


**Main aliases**

[`tf.keras.ops.hard_swish`](https://www.tensorflow.org/api_docs/python/tf/keras/ops/hard_silu), [`tf.keras.ops.nn.hard_silu`](https://www.tensorflow.org/api_docs/python/tf/keras/ops/hard_silu), [`tf.keras.ops.nn.hard_swish`](https://www.tensorflow.org/api_docs/python/tf/keras/ops/hard_silu)

<br />

    tf.keras.ops.hard_silu(
        x
    )

#### It is defined as:

- `0` if `if x < -3`
- `x` if `x > 3`
- `x * (x + 3) / 6` if `-3 <= x <= 3`

It's a faster, piecewise linear approximation of the silu activation.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `x` | Input tensor. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| A tensor with the same shape as `x`. ||

<br />

#### Example:

    x = keras.ops.convert_to_tensor([-3.0, -1.0, 0.0, 1.0, 3.0])
    keras.ops.hard_silu(x)
    array([-0.0, -0.3333333, 0.0, 0.6666667, 3.0], shape=(5,), dtype=float32)