rnn.py 文件源码

def exe_lstm(use_embedd, length, num_units, position, binominal):
    batch_size = BATCH_SIZE

    input_var = T.tensor3(name='inputs', dtype=theano.config.floatX)
    target_var = T.ivector(name='targets')

    layer_input = lasagne.layers.InputLayer(shape=(None, length, 1), input_var=input_var, name='input')
    if use_embedd:
        layer_position = construct_position_input(batch_size, length, num_units)
        layer_input = lasagne.layers.concat([layer_input, layer_position], axis=2)

    ingate = Gate(W_in=lasagne.init.GlorotUniform(), W_hid=lasagne.init.GlorotUniform(),
                  W_cell=lasagne.init.Uniform(range=0.1))

    outgate = Gate(W_in=lasagne.init.GlorotUniform(), W_hid=lasagne.init.GlorotUniform(),
                   W_cell=lasagne.init.Uniform(range=0.1))
    # according to Jozefowicz et al.(2015), init bias of forget gate to 1.
    forgetgate = Gate(W_in=lasagne.init.GlorotUniform(), W_hid=lasagne.init.GlorotUniform(),
                      W_cell=lasagne.init.Uniform(range=0.1), b=lasagne.init.Constant(1.))
    # now use tanh for nonlinear function of cell, need to try pure linear cell
    cell = Gate(W_in=lasagne.init.GlorotUniform(), W_hid=lasagne.init.GlorotUniform(), W_cell=None,
                b=lasagne.init.Constant(0.), nonlinearity=nonlinearities.tanh)

    layer_lstm = LSTMLayer(layer_input, num_units, ingate=ingate, forgetgate=forgetgate, cell=cell, outgate=outgate,
                           peepholes=False, nonlinearity=nonlinearities.tanh, only_return_final=True, name='LSTM')

    # W = layer_lstm.W_hid_to_cell.sum()
    # U = layer_lstm.W_in_to_cell.sum()
    # b = layer_lstm.b_cell.sum()

    layer_output = DenseLayer(layer_lstm, num_units=1, nonlinearity=nonlinearities.sigmoid, name='output')

    return train(layer_output, layer_lstm, input_var, target_var, batch_size, length, position, binominal)