def forward()

in torchmoji/lstm.py [0:0]

• 38 lines of code
• 8 McCabe index (conditional complexity)

    def forward(self, input, hx=None):
        is_packed = isinstance(input, PackedSequence)
        if is_packed:
            input, batch_sizes = input
            max_batch_size = batch_sizes[0]
        else:
            batch_sizes = None
            max_batch_size = input.size(0) if self.batch_first else input.size(1)

        if hx is None:
            num_directions = 2 if self.bidirectional else 1
            hx = torch.autograd.Variable(input.data.new(self.num_layers *
                                                        num_directions,
                                                        max_batch_size,
                                                        self.hidden_size).zero_(), requires_grad=False)
            hx = (hx, hx)

        has_flat_weights = list(p.data.data_ptr() for p in self.parameters()) == self._data_ptrs
        if has_flat_weights:
            first_data = next(self.parameters()).data
            assert first_data.storage().size() == self._param_buf_size
            flat_weight = first_data.new().set_(first_data.storage(), 0, torch.Size([self._param_buf_size]))
        else:
            flat_weight = None
        func = AutogradRNN(
            self.input_size,
            self.hidden_size,
            num_layers=self.num_layers,
            batch_first=self.batch_first,
            dropout=self.dropout,
            train=self.training,
            bidirectional=self.bidirectional,
            batch_sizes=batch_sizes,
            dropout_state=self.dropout_state,
            flat_weight=flat_weight
        )
        output, hidden = func(input, self.all_weights, hx)
        if is_packed:
            output = PackedSequence(output, batch_sizes)
        return output, hidden