tf.keras.ops.fabs

Compute the absolute values element-wise.

Main aliases

tf.keras.ops.numpy.fabs

tf.keras.ops.fabs(
    x
)

Integer or boolean inputs are automatically promoted to the default floating-point type. Complex values are not supported.

Args
`x`	Input tensor.

Returns
An array containing the absolute value of each element in `x`.

Example
>>> x = keras.ops.convert_to_tensor([-1, 2], dtype="int32") </td> </tr> </table> >>> keras.ops.fabs(x) array([1., 2.], dtype=float32) ``` 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 2026-10-31 UTC. Stay connected Blog GitHub Twitter 哔哩哔哩 Support Issue tracker Release notes Stack Overflow Brand guidelines Cite TensorFlow Terms Privacy ICP证合字B2-20070004号 Sign up for the TensorFlow newsletter Subscribe English 中文 – 简体

Example

>>> x = keras.ops.convert_to_tensor([-1, 2], dtype="int32")
</td>
</tr>

</table>


>>> keras.ops.fabs(x)
array([1., 2.], dtype=float32)
 ```

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 2026-10-31 UTC.