Collection of Ivy normalization classes.
- class ivy.stateful.norms.LayerNorm(normalized_shape, epsilon=None, elementwise_affine=True, new_std=None, device=None, v=None, dtype=None)
- __init__(normalized_shape, epsilon=None, elementwise_affine=True, new_std=None, device=None, v=None, dtype=None)
Class for applying Layer Normalization over a mini-batch of inputs
normalized_shape – Trailing shape to applying the normalization to.
epsilon – small constant to add to the denominator, use global ivy._MIN_BASE by default.
elementwise_affine – Whether to include learnable affine parameters, default is True.
new_std – The standard deviation of the new normalized values. Default is 1.
device – device on which to create the layer’s variables ‘cuda:0’, ‘cuda:1’, ‘cpu’ etc. (Default value = None)
v – the variables for each submodule in the sequence, constructed internally by default.