Missed TensorFlow Dev Summit? Check out the video playlist. Watch recordings


TensorFlow 1 version View source on GitHub

Standard deviation of a tensor, alongside the specified axis.

    x, axis=None, keepdims=False

Used in the notebooks

Used in the guide

It is an alias to tf.math.reduce_std.


  • x: A tensor or variable. It should have numerical dtypes. Boolean type inputs will be converted to float.
  • axis: An integer, the axis to compute the standard deviation. If None (the default), reduces all dimensions. Must be in the range [-rank(x), rank(x)).
  • keepdims: A boolean, whether to keep the dimensions or not. If keepdims is False, the rank of the tensor is reduced by 1. If keepdims is True, the reduced dimension is retained with length 1.


A tensor with the standard deviation of elements of x with same dtype. Boolean type input will be converted to float.