rnn.py 文件源码

def exe_sgru(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)

    resetgate_input = Gate(W_in=lasagne.init.GlorotUniform(), W_hid=lasagne.init.GlorotUniform(), W_cell=None)

    resetgate_hidden = Gate(W_in=lasagne.init.GlorotUniform(), W_hid=lasagne.init.GlorotUniform(), W_cell=None)

    updategate = Gate(W_in=lasagne.init.GlorotUniform(), W_hid=lasagne.init.GlorotUniform(), W_cell=None)

    hiden_update = Gate(W_in=lasagne.init.GlorotUniform(), W_hid=lasagne.init.GlorotUniform(), W_cell=None,
                        b=lasagne.init.Constant(0.), nonlinearity=nonlinearities.tanh)

    layer_sgru = SGRULayer(layer_input, num_units, resetgate_input=resetgate_input, resetgate_hidden=resetgate_hidden,
                           updategate=updategate, hidden_update=hiden_update, only_return_final=True, name='SGRU')

    # W = layer_gru.W_hid_to_hidden_update.sum()
    # U = layer_gru.W_in_to_hidden_update.sum()
    # b = layer_gru.b_hidden_update.sum()

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

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