:py:mod:`mlair.model_modules.fully_connected_networks` ====================================================== .. py:module:: mlair.model_modules.fully_connected_networks Module Contents --------------- Classes ~~~~~~~ .. autoapisummary:: mlair.model_modules.fully_connected_networks.FCN mlair.model_modules.fully_connected_networks.FCN_64_32_16 Attributes ~~~~~~~~~~ .. autoapisummary:: mlair.model_modules.fully_connected_networks.__author__ mlair.model_modules.fully_connected_networks.__date__ .. py:data:: __author__ :annotation: = Lukas Leufen .. py:data:: __date__ :annotation: = 2021-02-18 .. py:class:: FCN(input_shape: list, output_shape: list, activation='relu', activation_output='linear', optimizer='adam', n_layer=1, n_hidden=10, regularizer=None, dropout=None, layer_configuration=None, batch_normalization=False, **kwargs) Bases: :py:obj:`mlair.model_modules.AbstractModelClass` A customisable fully connected network (64, 32, 16, window_lead_time), where the last layer is the output layer depending on the window_lead_time parameter. .. 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:method:: _set_activation(self, activation) .. py:method:: _set_optimizer(self, optimizer, **kwargs) .. py:method:: _set_regularizer(self, regularizer, **kwargs) .. py:method:: _set_dropout(self, activation, dropout_rate) .. py:method:: _update_model_name(self) .. py:method:: set_model(self) Build the model. .. 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:class:: FCN_64_32_16(input_shape: list, output_shape: list, **kwargs) Bases: :py:obj:`FCN` A customised model 4 Dense layers (64, 32, 16, window_lead_time), where the last layer is the output layer depending on the window_lead_time parameter. .. py:attribute:: _requirements :annotation: = ['lr', 'beta_1', 'beta_2', 'epsilon', 'decay', 'amsgrad'] .. 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:: _update_model_name(self)