# tf.nn.relu

<br />

Computes rectified linear: `max(features, 0)`.

#### View aliases


**Compat aliases for migration**

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

[`tf.compat.v1.nn.relu`](https://www.tensorflow.org/api_docs/python/tf/nn/relu)

<br />

    tf.nn.relu(
        features: Annotated[Any, TV_Relu_T], name=None
    ) -> Annotated[Any, TV_Relu_T]

### Used in the notebooks

| Used in the guide | Used in the tutorials |
|---|---|
| - [Introduction to modules, layers, and models](https://www.tensorflow.org/guide/intro_to_modules) - [Multilayer perceptrons for digit recognition with Core APIs](https://www.tensorflow.org/guide/core/mlp_core) - [Understanding masking \& padding](https://www.tensorflow.org/guide/keras/understanding_masking_and_padding) | - [Custom layers](https://www.tensorflow.org/tutorials/customization/custom_layers) - [Generating Images with BigBiGAN](https://www.tensorflow.org/hub/tutorials/bigbigan_with_tf_hub) - [Examining the TensorFlow Graph](https://www.tensorflow.org/tensorboard/graphs) |

See: <https://en.wikipedia.org/wiki/Rectifier_(neural_networks)>
Example usage:

    >>> tf.nn.relu([-2., 0., 3.]).numpy()
    array([0., 0., 3.], dtype=float32)

<br />

<br />

<br />

| ## Args ||
|---|---|
| `features` | A `Tensor`. Must be one of the following types: `float32`, `float64`, `int32`, `uint8`, `int16`, `int8`, `int64`, `bfloat16`, `uint16`, `half`, `uint32`, `uint64`, `qint8`. |
| `name` | A name for the operation (optional). |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| A `Tensor`. Has the same type as `features`. ||

<br />