dlpy.layers.EmbeddingLoss¶
-
class
dlpy.layers.
EmbeddingLoss
(name=None, margin=2, src_layers=None, **kwargs)¶ Bases: dlpy.layers.Layer
EmbeddingLoss layer
Parameters: - name : string, optional
Specifies the name of the layer.
- margin : double, optional
Specifies the margin value that defines a radius for dissimilar pair contributions.
Default: 2- src_layers : iter-of-Layers, optional
Specifies the layers directed to this layer.
Returns: -
__init__
(name=None, margin=2, src_layers=None, **kwargs)¶ Initialize self. See help(type(self)) for accurate signature.
Methods
__init__([name, margin, src_layers]) 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