dlpy.layers.Proj¶
-
class
dlpy.layers.
Proj
(embedding_size, alphabet_size, name=None, init=None, std=None, mean=None, truncation_factor=None, src_layers=None, **kwargs)¶ Bases: dlpy.layers.Layer
Projection layer
Parameters: - embedding_size : int
Specifies the size of the embedding.
- alphabet_size : int
Specifies the size of the alphabet.
- name : string, optional
Specifies the name of the layer.
- init : string, optional
Specifies the initialization scheme for the layer.
Valid Values: XAVIER, UNIFORM, NORMAL, CAUCHY, XAVIER1, XAVIER2, MSRA, MSRA1, MSRA2
Default: XAVIER- std : float, optional
Specifies the standard deviation value when the init parameter is set to NORMAL.
- mean : float, optional
Specifies the mean value when the init parameter is set to NORMAL.
- truncation_factor : float, optional
Specifies the truncation threshold (truncationFactor x std), when the init parameter is set to NORMAL
- src_layers : iter-of-Layers, optional
Specifies the layers directed to this layer.
Returns: -
__init__
(embedding_size, alphabet_size, name=None, init=None, std=None, mean=None, truncation_factor=None, src_layers=None, **kwargs)¶ Initialize self. See help(type(self)) for accurate signature.
Methods
__init__(embedding_size, alphabet_size[, …]) 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