Package Oger :: Package nodes :: Class MaxVotingNode
[hide private]
[frames] | no frames]

NodeMetaclass MaxVotingNode

object --+    
         |    
  mdp.Node --+
             |
            Oger.nodes.MaxVotingNode

This node finds the maximum value of all input channels at each timestep, and returns the corresponding label.

If no labels are supplied, the index of the channel is returned.

Instance Methods [hide private]
 
__init__(self, labels=None, input_dim=None, dtype='float64')
If the input dimension and the output dimension are unspecified, they will be set when the train or execute method is called for the first time. If dtype is unspecified, it will be inherited from the data it receives at the first call of train or execute.
 
_execute(self, x)
 
_get_supported_dtypes(self)
Return the list of dtypes supported by this node.
 
is_invertible(self)
Return True if the node can be inverted, False otherwise.
 
is_trainable(self)
Return True if the node can be trained, False otherwise.

Inherited from mdp.Node: __add__, __call__, __repr__, __str__, copy, execute, get_current_train_phase, get_dtype, get_input_dim, get_output_dim, get_remaining_train_phase, get_supported_dtypes, has_multiple_training_phases, inverse, is_training, save, set_dtype, set_input_dim, set_output_dim, stop_training, train

Inherited from mdp.Node (private): _check_input, _check_output, _check_train_args, _get_train_seq, _if_training_stop_training, _inverse, _pre_execution_checks, _pre_inversion_checks, _refcast, _set_dtype, _set_input_dim, _set_output_dim, _stop_training, _train

Properties [hide private]

Inherited from mdp.Node: dtype, input_dim, output_dim, supported_dtypes

Inherited from mdp.Node (private): _train_seq

Method Details [hide private]

__init__(self, labels=None, input_dim=None, dtype='float64')
(Constructor)

 

If the input dimension and the output dimension are unspecified, they will be set when the train or execute method is called for the first time. If dtype is unspecified, it will be inherited from the data it receives at the first call of train or execute.

Every subclass must take care of up- or down-casting the internal structures to match this argument (use \_refcast private method when possible).

Overrides: mdp.Node.__init__
(inherited documentation)

_execute(self, x)

 
Overrides: mdp.Node._execute

_get_supported_dtypes(self)

 
Return the list of dtypes supported by this node.

The types can be specified in any format allowed by :numpy:`dtype`.

Overrides: mdp.Node._get_supported_dtypes
(inherited documentation)

is_invertible(self)

 
Return True if the node can be inverted, False otherwise.
Overrides: mdp.Node.is_invertible
(inherited documentation)

is_trainable(self)

 
Return True if the node can be trained, False otherwise.
Overrides: mdp.Node.is_trainable
(inherited documentation)