dlpy.layers.LayerNormalization¶

class dlpy.layers.LayerNormalization(name=None, act='AUTO', epsilon=1e-12, dropout=None, src_layers=None, **kwargs)¶

Bases: dlpy.layers.Layer

Layer normalization layer

Parameters:

name : string, optional Specifies the name of the layer. act : string, optional Specifies the activation function. Valid Values: AUTO, IDENTITY, LOGISTIC, SIGMOID, EXP, TANH, RECTIFIER, RELU, GELU Default: AUTO epsilon : float, optional Specifies the regularization constant. Default: 1e-12 dropout : float, optional Specifies the dropout rate. Default: 0 src_layers : iter-of-Layers, optional Specifies the layers directed to this layer.

Returns:

LayerNormalization

__init__(name=None, act='AUTO', epsilon=1e-12, dropout=None, src_layers=None, **kwargs)¶

Initialize self. See help(type(self)) for accurate signature.

Methods

__init__([name, act, epsilon, dropout, …])	Initialize self.
count_instances()
format_name([block_num, local_count])	Format the name of the layer
get_number_of_instances()
to_model_params()	Convert the model configuration to CAS action parameters