def LSTM_sequence_classifer_net(feature, num_output_classes, embedding_dim, LSTM_dim, cell_dim): embedding_function = embedding(feature, embedding_dim) LSTM_function = LSTMP_component_with_self_stabilization( embedding_function.output, LSTM_dim, cell_dim)[0] thought_vector = sequence.last(LSTM_function) return linear_layer(thought_vector, num_output_classes)
def LSTM_sequence_classifer_net(input, num_output_classes, embedding_dim, LSTM_dim, cell_dim): embedding_function = embedding(input, embedding_dim) LSTM_function = LSTMP_component_with_self_stabilization( embedding_function.output, LSTM_dim, cell_dim)[0] thought_vector = sequence.last(LSTM_function) return linear_layer(thought_vector, num_output_classes)
def LSTM_sequence_classifer_net(input, num_output_classes, embedding_dim, LSTM_dim, cell_dim): embedded_inputs = embedding(input, embedding_dim) lstm_outputs = simple_lstm(embedded_inputs, LSTM_dim, cell_dim)[0] thought_vector = sequence.last(lstm_outputs) return linear_layer(thought_vector, num_output_classes)
def LSTM_sequence_classifer_net(input, num_output_classes, embedding_dim, LSTM_dim, cell_dim): embedded_inputs = embedding(input, embedding_dim) lstm_outputs = simple_lstm(embedded_inputs, LSTM_dim, cell_dim)[0] thought_vector = sequence.last(lstm_outputs) return linear_layer(thought_vector, num_output_classes)