rnn.py 文件源码

def exe_gru(use_embedd, length, num_units, position, binominal, reset_input):
    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=(batch_size, 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 = 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_gru = GRULayer_ANA(layer_input, num_units, resetgate=resetgate, updategate=updategate, hidden_update=hiden_update,
                         reset_input=reset_input, only_return_final=True, name='GRU')

    # 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_gru, num_units=1, nonlinearity=nonlinearities.sigmoid, name='output')

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