File size: 3,822 Bytes
6fc683c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
# Copyright (c) Facebook, Inc. and its affiliates.
#
# This source code is licensed under the MIT license found in the
# LICENSE file in the root directory of this source tree.

import logging

import numpy as np
import torch
from fairseq.data import Dictionary, FairseqDataset
from fairseq.tasks import LegacyFairseqTask, register_task


logger = logging.getLogger(__name__)


@register_task("dummy_masked_lm")
class DummyMaskedLMTask(LegacyFairseqTask):
    @staticmethod
    def add_args(parser):
        """Add task-specific arguments to the parser."""
        parser.add_argument("--dict-size", default=49995, type=int)
        parser.add_argument("--dataset-size", default=100000, type=int)
        parser.add_argument(
            "--tokens-per-sample",
            default=512,
            type=int,
            help="max number of total tokens over all segments "
            "per sample for BERT dataset",
        )

    def __init__(self, args, dictionary):
        super().__init__(args)
        self.dictionary = dictionary

        # add mask token
        self.mask_idx = dictionary.add_symbol("<mask>")
        dictionary.pad_to_multiple_(8)  # often faster if divisible by 8

        mask_idx = 0
        pad_idx = 1
        seq = torch.arange(args.tokens_per_sample) + pad_idx + 1
        mask = torch.arange(2, args.tokens_per_sample, 7)  # ~15%
        src = seq.clone()
        src[mask] = mask_idx
        tgt = torch.full_like(seq, pad_idx)
        tgt[mask] = seq[mask]

        self.dummy_src = src
        self.dummy_tgt = tgt

    @classmethod
    def setup_task(cls, args, **kwargs):
        """Setup the task. """
        dictionary = Dictionary()
        for i in range(args.dict_size):
            dictionary.add_symbol("word{}".format(i))
        logger.info("dictionary: {} types".format(len(dictionary)))
        return cls(args, dictionary)

    def load_dataset(self, split, epoch=1, combine=False, **kwargs):
        """Load a given dataset split.
        Args:
            split (str): name of the split (e.g., train, valid, test)
        """
        if self.args.batch_size is not None:
            bsz = self.args.batch_size
        else:
            bsz = max(1, self.args.max_tokens // self.args.tokens_per_sample)
        self.datasets[split] = DummyDataset(
            {
                "id": 1,
                "net_input": {
                    "src_tokens": torch.stack([self.dummy_src for _ in range(bsz)]),
                    "src_lengths": torch.full(
                        (bsz,), self.args.tokens_per_sample, dtype=torch.long
                    ),
                },
                "target": torch.stack([self.dummy_tgt for _ in range(bsz)]),
                "nsentences": bsz,
                "ntokens": bsz * self.args.tokens_per_sample,
            },
            num_items=self.args.dataset_size,
            item_size=self.args.tokens_per_sample,
        )

    @property
    def source_dictionary(self):
        return self.dictionary

    @property
    def target_dictionary(self):
        return self.dictionary


class DummyDataset(FairseqDataset):
    def __init__(self, batch, num_items, item_size):
        super().__init__()
        self.batch = batch
        self.num_items = num_items
        self.item_size = item_size

    def __getitem__(self, index):
        return index

    def __len__(self):
        return self.num_items

    def collater(self, samples):
        return self.batch

    @property
    def sizes(self):
        return np.array([self.item_size] * self.num_items)

    def num_tokens(self, index):
        return self.item_size

    def size(self, index):
        return self.item_size

    def ordered_indices(self):
        return np.arange(self.num_items)

    @property
    def supports_prefetch(self):
        return False