def AutogradRNN()

in torchmoji/lstm.py [0:0]

• 25 lines of code
• 7 McCabe index (conditional complexity)

def AutogradRNN(input_size, hidden_size, num_layers=1, batch_first=False,
                dropout=0, train=True, bidirectional=False, batch_sizes=None,
                dropout_state=None, flat_weight=None):

    cell = LSTMCell

    if batch_sizes is None:
        rec_factory = Recurrent
    else:
        rec_factory = variable_recurrent_factory(batch_sizes)

    if bidirectional:
        layer = (rec_factory(cell), rec_factory(cell, reverse=True))
    else:
        layer = (rec_factory(cell),)

    func = StackedRNN(layer,
                      num_layers,
                      True,
                      dropout=dropout,
                      train=train)

    def forward(input, weight, hidden):
        if batch_first and batch_sizes is None:
            input = input.transpose(0, 1)

        nexth, output = func(input, hidden, weight)

        if batch_first and batch_sizes is None:
            output = output.transpose(0, 1)

        return output, nexth

    return forward