Norms

Collection of Ivy normalization functions.

ivy.neural_net_functional.norms.layer_norm(x, normalized_idxs, epsilon=None, gamma=None, beta=None, new_std=None)[source]

Applies Layer Normalization over a mini-batch of inputs

Parameters
  • x (array) – Input array

  • normalized_idxs (int or sequence of ints) – Indices to apply the normalization to.

  • epsilon (float, optional) – small constant to add to the denominator, use global ivy._MIN_BASE by default.

  • gamma (array, optional) – Learnable gamma variables for post-multiplication, default is None.

  • beta (array, optional) – Learnable beta variables for post-addition, default is None.

  • new_std (float, optional) – The standard deviation of the new normalized values. Default is 1.

Returns

The layer after applying layer normalization.

Norms