tf.nn.relu

Computes rectified linear: max(features, 0).

Compat aliases for migration

tf.compat.v1.nn.relu

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

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

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).

Returns
A `Tensor`. Has the same type as `features`.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.

Last updated 2024-01-23 UTC.

Args