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