PackedSequence for seq2seq model

There’s a work-in-progress batched version of the tutorial coming up, the easiest way I could find was to do packing and unpacking within the encoder:

class EncoderRNN(nn.Module):
    def __init__(self, input_size, hidden_size, n_layers=1, dropout=0.1):
        super(EncoderRNN, self).__init__()
        
        self.input_size = input_size
        self.hidden_size = hidden_size
        self.n_layers = n_layers
        self.dropout = dropout
        
        self.embedding = nn.Embedding(input_size, hidden_size)
        self.gru = nn.GRU(hidden_size, hidden_size, n_layers, dropout=self.dropout, bidirectional=True)
        
    def forward(self, input_seqs, input_lengths, hidden=None):
        # Note: we run this all at once (over multiple batches of multiple sequences)
        embedded = self.embedding(input_seqs)
        packed = torch.nn.utils.rnn.pack_padded_sequence(embedded, input_lengths)
        outputs, hidden = self.gru(packed, hidden)
        outputs, output_lengths = torch.nn.utils.rnn.pad_packed_sequence(outputs) # unpack (back to padded)
        outputs = outputs[:, :, :self.hidden_size] + outputs[:, : ,self.hidden_size:] # Sum bidirectional outputs
        return outputs, hidden

It would be nice if other layers had support for PackedSequence…

2 Likes