pydbm.synapse.recurrenttemporalgraph.lstmgraph package

Submodules

pydbm.synapse.recurrenttemporalgraph.lstmgraph.attention_lstm_graph module

class pydbm.synapse.recurrenttemporalgraph.lstmgraph.attention_lstm_graph.AttentionLSTMGraph

Bases: pydbm.synapse.recurrenttemporalgraph.lstm_graph.LSTMGraph

Attention based on Long short term memory(LSTM) networks.

In relation to do transfer learning, this object is-a Synapse which can be delegated to AttentionLSTMModel.

attention_output_weight_arr

getter

create_rnn_cells

Create RNN cells for a LSTMModel.

Parameters:
  • input_neuron_count – The number of units in input layer.
  • hidden_neuron_count – The number of units in hidden layer.
  • output_neuron_count – The number of units in output layer.
  • 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.
get_attention_output_weight_arr

getter

set_attention_output_weight_arr

setter

Module contents