def _forward_padded()

in drqa/reader/layers.py [0:0]

• 36 lines of code
• 11 McCabe index (conditional complexity)

    def _forward_padded(self, x, x_mask):
        """Slower (significantly), but more precise, encoding that handles
        padding.
        """
        # Compute sorted sequence lengths
        lengths = x_mask.data.eq(0).long().sum(1).squeeze()
        _, idx_sort = torch.sort(lengths, dim=0, descending=True)
        _, idx_unsort = torch.sort(idx_sort, dim=0)
        lengths = list(lengths[idx_sort])

        # Sort x
        x = x.index_select(0, idx_sort)

        # Transpose batch and sequence dims
        x = x.transpose(0, 1)

        # Pack it up
        rnn_input = nn.utils.rnn.pack_padded_sequence(x, lengths)

        # Encode all layers
        outputs = [rnn_input]
        for i in range(self.num_layers):
            rnn_input = outputs[-1]

            # Apply dropout to input
            if self.dropout_rate > 0:
                dropout_input = F.dropout(rnn_input.data,
                                          p=self.dropout_rate,
                                          training=self.training)
                rnn_input = nn.utils.rnn.PackedSequence(dropout_input,
                                                        rnn_input.batch_sizes)
            outputs.append(self.rnns[i](rnn_input)[0])

        # Unpack everything
        for i, o in enumerate(outputs[1:], 1):
            outputs[i] = nn.utils.rnn.pad_packed_sequence(o)[0]

        # Concat hidden layers or take final
        if self.concat_layers:
            output = torch.cat(outputs[1:], 2)
        else:
            output = outputs[-1]

        # Transpose and unsort
        output = output.transpose(0, 1)
        output = output.index_select(0, idx_unsort)

        # Pad up to original batch sequence length
        if output.size(1) != x_mask.size(1):
            padding = torch.zeros(output.size(0),
                                  x_mask.size(1) - output.size(1),
                                  output.size(2)).type(output.data.type())
            output = torch.cat([output, padding], 1)

        # Dropout on output layer
        if self.dropout_output and self.dropout_rate > 0:
            output = F.dropout(output,
                               p=self.dropout_rate,
                               training=self.training)
        return output