dialogue_personalization/utils/beam_omt.py [241:287]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
def sequence_mask(sequence_length, max_len=None):
    if max_len is None:
        max_len = sequence_length.data.max()
    batch_size = sequence_length.size(0)
    seq_range = torch.arange(0, max_len).long()
    seq_range_expand = seq_range.unsqueeze(0).expand(batch_size, max_len)
    seq_range_expand = seq_range_expand
    if sequence_length.is_cuda:
        seq_range_expand = seq_range_expand.cuda()
    seq_length_expand = (sequence_length.unsqueeze(1)
                        .expand_as(seq_range_expand))
    return seq_range_expand < seq_length_expand
    
def get_input_from_batch(batch):
    enc_batch = batch["input_batch"].transpose(0,1)
    enc_lens = batch["input_lengths"]
    batch_size, max_enc_len = enc_batch.size()
    assert enc_lens.size(0) == batch_size

    enc_padding_mask = sequence_mask(enc_lens, max_len=max_enc_len).float()

    extra_zeros = None
    enc_batch_extend_vocab = None

    if config.pointer_gen:
        enc_batch_extend_vocab = batch["input_ext_vocab_batch"].transpose(0,1)
        # max_art_oovs is the max over all the article oov list in the batch
        if batch["max_art_oovs"] > 0:
            extra_zeros = torch.zeros((batch_size, batch["max_art_oovs"]))

    c_t_1 = torch.zeros((batch_size, 2 * config.hidden_dim))

    coverage = None
    if config.is_coverage:
        coverage = torch.zeros(enc_batch.size())

    if config.USE_CUDA:
        if enc_batch_extend_vocab is not None:
                enc_batch_extend_vocab = enc_batch_extend_vocab.cuda()
        if extra_zeros is not None:
            extra_zeros = extra_zeros.cuda()
        c_t_1 = c_t_1.cuda()

        if coverage is not None:
            coverage = coverage.cuda()

    return enc_batch, enc_padding_mask, enc_lens, enc_batch_extend_vocab, extra_zeros, c_t_1, coverage
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



dialogue_personalization/utils/beam_ptr.py [192:238]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
def sequence_mask(sequence_length, max_len=None):
    if max_len is None:
        max_len = sequence_length.data.max()
    batch_size = sequence_length.size(0)
    seq_range = torch.arange(0, max_len).long()
    seq_range_expand = seq_range.unsqueeze(0).expand(batch_size, max_len)
    seq_range_expand = seq_range_expand
    if sequence_length.is_cuda:
        seq_range_expand = seq_range_expand.cuda()
    seq_length_expand = (sequence_length.unsqueeze(1)
                        .expand_as(seq_range_expand))
    return seq_range_expand < seq_length_expand

def get_input_from_batch(batch):
    enc_batch = batch["input_batch"].transpose(0,1)
    enc_lens = batch["input_lengths"]
    batch_size, max_enc_len = enc_batch.size()
    assert enc_lens.size(0) == batch_size

    enc_padding_mask = sequence_mask(enc_lens, max_len=max_enc_len).float()

    extra_zeros = None
    enc_batch_extend_vocab = None

    if config.pointer_gen:
        enc_batch_extend_vocab = batch["input_ext_vocab_batch"].transpose(0,1)
        # max_art_oovs is the max over all the article oov list in the batch
        if batch["max_art_oovs"] > 0:
            extra_zeros = torch.zeros((batch_size, batch["max_art_oovs"]))

    c_t_1 = torch.zeros((batch_size, 2 * config.hidden_dim))

    coverage = None
    if config.is_coverage:
        coverage = torch.zeros(enc_batch.size())

    if config.USE_CUDA:
        if enc_batch_extend_vocab is not None:
                enc_batch_extend_vocab = enc_batch_extend_vocab.cuda()
        if extra_zeros is not None:
            extra_zeros = extra_zeros.cuda()
        c_t_1 = c_t_1.cuda()

        if coverage is not None:
            coverage = coverage.cuda()

    return enc_batch, enc_padding_mask, enc_lens, enc_batch_extend_vocab, extra_zeros, c_t_1, coverage
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -