:py:mod:`mlair.model_modules.recurrent_networks`
================================================

.. py:module:: mlair.model_modules.recurrent_networks


Module Contents
---------------

Classes
~~~~~~~

.. autoapisummary::

   mlair.model_modules.recurrent_networks.RNN




Attributes
~~~~~~~~~~

.. autoapisummary::

   mlair.model_modules.recurrent_networks.__author__
   mlair.model_modules.recurrent_networks.__date__


.. py:data:: __author__
   :annotation: = Lukas Leufen

   

.. py:data:: __date__
   :annotation: = 2021-05-25

   

.. py:class:: RNN(input_shape: list, output_shape: list, activation='relu', activation_output='linear', activation_rnn='tanh', dropout_rnn=0, optimizer='adam', n_layer=1, n_hidden=10, regularizer=None, dropout=None, layer_configuration=None, batch_normalization=False, rnn_type='lstm', add_dense_layer=False, dense_layer_configuration=None, kernel_regularizer=None, **kwargs)

   Bases: :py:obj:`mlair.model_modules.AbstractModelClass`

   

   .. py:attribute:: _activation
      

      

   .. py:attribute:: _initializer
      

      

   .. py:attribute:: _optimizer
      

      

   .. py:attribute:: _regularizer
      

      

   .. py:attribute:: _requirements
      :annotation: = ['lr', 'beta_1', 'beta_2', 'epsilon', 'decay', 'amsgrad', 'momentum', 'nesterov', 'l1', 'l2']

      

   .. py:attribute:: _dropout
      

      

   .. py:attribute:: _rnn
      

      

   .. py:method:: set_model(self)

      Build the model.


   .. py:method:: _set_dropout(self, activation, dropout_rate)


   .. py:method:: _set_activation(self, activation)


   .. py:method:: set_compile_options(self)

      This method only has to be defined in child class, when additional compile options should be used ()
      (other options than optimizer and loss)
      Has to be set as dictionary: {'optimizer': None,
                                    'loss': None,
                                    'metrics': None,
                                    'loss_weights': None,
                                    'sample_weight_mode': None,
                                    'weighted_metrics': None,
                                    'target_tensors': None
                                    }

      :return:


   .. py:method:: _set_optimizer(self, optimizer, **kwargs)


   .. py:method:: _set_regularizer(self, regularizer: Union[None, str], **kwargs)


   .. py:method:: _update_model_name(self, rnn_type)