<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/models/blob/v2.20.0/official/modeling/activations/swish.py#L41-L56) |

Computes a hard version of the swish function.

    tfm.utils.activations.hard_swish(
        features
    )

This operation can be used to reduce computational cost and improve
quantization for edge devices.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `features` | A `Tensor` representing preactivation values. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| The activation value. ||

<br />