TensorFlow 1 version View source on GitHub

Normalizes along dimension axis using an L2 norm.

    x, axis=None, epsilon=1e-12, name=None

For a 1-D tensor with axis = 0, computes

output = x / sqrt(max(sum(x**2), epsilon))

For x with more dimensions, independently normalizes each 1-D slice along dimension axis.


  • x: A Tensor.
  • axis: Dimension along which to normalize. A scalar or a vector of integers.
  • epsilon: A lower bound value for the norm. Will use sqrt(epsilon) as the divisor if norm < sqrt(epsilon).
  • name: A name for this operation (optional).


A Tensor with the same shape as x.