pydbm package¶
Subpackages¶
- pydbm.activation package
- Subpackages
- Submodules
- pydbm.activation.identity_function module
- pydbm.activation.logistic_function module
- pydbm.activation.relu_function module
- pydbm.activation.sign_function module
- pydbm.activation.softmax_function module
- pydbm.activation.tanh_function module
- Module contents
- pydbm.approximation package
- pydbm.clustering package
- Subpackages
- pydbm.clustering.autoencodable package
- pydbm.clustering.computableclusteringloss package
- Subpackages
- Submodules
- pydbm.clustering.computableclusteringloss.balanced_assignments_loss module
- pydbm.clustering.computableclusteringloss.k_means_loss module
- pydbm.clustering.computableclusteringloss.reconstruction_loss module
- pydbm.clustering.computableclusteringloss.repelling_loss module
- Module contents
- pydbm.clustering.interface package
- Submodules
- pydbm.clustering.deep_embedded_clustering module
- pydbm.clustering.reconstruction_classification_networks module
- pydbm.clustering.sklearn_kmeans module
- Module contents
- Subpackages
- pydbm.cnn package
- Subpackages
- pydbm.cnn.convolutionalneuralnetwork package
- Subpackages
- pydbm.cnn.convolutionalneuralnetwork.convolutionalautoencoder package
- Submodules
- pydbm.cnn.convolutionalneuralnetwork.convolutionalautoencoder.contractive_convolutional_auto_encoder module
- pydbm.cnn.convolutionalneuralnetwork.convolutionalautoencoder.convolutional_ladder_networks module
- pydbm.cnn.convolutionalneuralnetwork.convolutionalautoencoder.repelling_convolutional_auto_encoder module
- Module contents
- pydbm.cnn.convolutionalneuralnetwork.convolutionalautoencoder package
- Submodules
- pydbm.cnn.convolutionalneuralnetwork.convolutional_auto_encoder module
- pydbm.cnn.convolutionalneuralnetwork.residual_learning module
- Module contents
- Subpackages
- pydbm.cnn.featuregenerator package
- pydbm.cnn.layerablecnn package
- pydbm.cnn.convolutionalneuralnetwork package
- Submodules
- pydbm.cnn.convolutional_neural_network module
- pydbm.cnn.feature_generator module
- pydbm.cnn.layerable_cnn module
- pydbm.cnn.spatio_temporal_auto_encoder module
- Module contents
- Subpackages
- pydbm.dbm package
- Subpackages
- Submodules
- pydbm.dbm.dbm_director module
- pydbm.dbm.deep_boltzmann_machine module
- pydbm.dbm.recurrent_temporal_rbm module
- pydbm.dbm.restricted_boltzmann_machines module
- pydbm.dbm.rtrbm_director module
- Module contents
- pydbm.loss package
- pydbm.nn package
- pydbm.optimization package
- pydbm.rnn package
- pydbm.synapse package
- Subpackages
- Submodules
- pydbm.synapse.cnn_graph module
- pydbm.synapse.cnn_output_graph module
- pydbm.synapse.complete_bipartite_graph module
- pydbm.synapse.nn_graph module
- pydbm.synapse.recurrent_temporal_graph module
- Module contents
- pydbm.verification package
Submodules¶
pydbm.params_initializer module¶
pydbm.synapse_list module¶
-
class
pydbm.synapse_list.
Synapse
¶ Bases:
object
The object of synapse.
-
create_node
¶ Set links of nodes to the graphs.
Parameters: - shallower_neuron_count – The number of neurons in shallower layer.
- deeper_neuron_count – The number of neurons in deeper layer.
- shallower_activating_function – The activation function in shallower layer.
- deeper_activating_function – The activation function in deeper layer.
- weights_arr – The pre-learned weights of links. If this array is not empty, ParamsInitializer.sample_f will not be called and weights_arr will be refered as initial weights.
- scale – Scale of parameters which will be ParamsInitializer.
- params_initializer – is-a ParamsInitializer.
- params_dict – dict of parameters other than size to be input to function ParamsInitializer.sample_f.
-
deeper_activating_function
¶ getter
-
diff_weights_arr
¶ getter
-
get_deeper_activating_function
¶ getter
-
get_diff_weights_arr
¶ getter
-
get_shallower_activating_function
¶ getter
-
get_weights_arr
¶ getter
-
learn_weights
¶ Update the weights of links.
-
load_pre_learned_params
¶ Load pre-learned parameters.
If you want to load pre-learned parameters simultaneously with stacked graphs, call method stack_graph and setup the graphs before calling this method.
If this class’s subclass has a ActivatingFunctionInterface which has a BatchNorm, and your file stores appropriate data, this class set BatchNorm’s beta_arr and gamma_arr.
Parameters: file_path – File path.
-
save_pre_learned_params
¶ Save pre-learned parameters.
If you want to save pre-learned parameters simultaneously with stacked graphs, call method stack_graph and setup the graphs before calling this method.
If this class’s subclass has a ActivatingFunctionInterface which has a BatchNorm, this class store BatchNorm’s beta_arr and gamma_arr to your file.
Parameters: file_path – File path.
-
set_deeper_activating_function
¶ setter
-
set_diff_weights_arr
¶ setter
-
set_shallower_activating_function
¶ setter
-
set_weights_arr
¶ setter
-
shallower_activating_function
¶ getter
-
weights_arr
¶ getter
-