tf.keras.ops.nanstd

Compute the standard deviation along the specified axes, ignoring NaNs.

Main aliases

tf.keras.ops.numpy.nanstd

tf.keras.ops.nanstd(
    x, axis=None, keepdims=False
)

Args
`x`	Input tensor.
`axis`	Axis or axes along which the standard deviation is computed. The default is to compute the std of the flattened tensor.
`keepdims`	If `True`, the axes which are reduced are left in the result as dimensions with size one. Defaults to `False`.

Returns
Output tensor containing the standard deviation ignoring NaNs.

import numpy as np
from keras import ops
x = np.array([[1.0, np.nan, 3.0],
              [np.nan, 2.0, 1.0]])

ops.nanstd(x)
0.8291562

ops.nanstd(x, axis=1)
array([1. , 0.5])

ops.nanstd(x, axis=1, keepdims=True)
array([[1. ],
       [0.5]])

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.

tf.keras.ops.nanstd Stay organized with collections Save and categorize content based on your preferences.