File size: 7,648 Bytes
843bd97
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.

import itertools
from typing import Any, Optional
import warnings

import numpy as np
import torch
from torch.utils.data.sampler import Sampler

import dinov2.distributed as distributed


class EpochSampler(Sampler):
    def __init__(
        self,
        *,
        size: int,
        sample_count: int,
        shuffle: bool = False,
        seed: int = 0,
        start: Optional[int] = None,
        step: Optional[int] = None,
    ):
        self._size = size
        self._sample_count = sample_count
        self._shuffle = shuffle
        self._seed = seed
        self._start = distributed.get_global_rank() if start is None else start
        self._step = distributed.get_global_size() if step is None else step
        self._epoch = 0

    def __iter__(self):
        count = (self._size + self._sample_count - 1) // self._sample_count
        tiled_indices = np.tile(np.arange(self._sample_count), count)
        if self._shuffle:
            seed = self._seed * self._epoch if self._seed != 0 else self._epoch
            rng = np.random.default_rng(seed)
            iterable = rng.choice(tiled_indices, self._size, replace=False)
        else:
            iterable = tiled_indices[: self._size]

        yield from itertools.islice(iterable, self._start, None, self._step)

    def __len__(self):
        return (self._size - self._start + self._step - 1) // self._step

    def set_epoch(self, epoch):
        self._epoch = epoch


def _get_numpy_dtype(size: int) -> Any:
    return np.int32 if size <= 2**31 else np.int64


def _get_torch_dtype(size: int) -> Any:
    return torch.int32 if size <= 2**31 else torch.int64


def _generate_randperm_indices(*, size: int, generator: torch.Generator):
    """Generate the indices of a random permutation."""
    dtype = _get_torch_dtype(size)
    # This is actually matching PyTorch's CPU implementation, see: https://github.com/pytorch/pytorch/blob/master/aten/src/ATen/native/TensorFactories.cpp#L900-L921
    perm = torch.arange(size, dtype=dtype)
    for i in range(size):
        j = torch.randint(i, size, size=(1,), generator=generator).item()

        # Always swap even if no-op
        value = perm[j].item()
        perm[j] = perm[i].item()
        perm[i] = value
        yield value


class InfiniteSampler(Sampler):
    def __init__(
        self,
        *,
        sample_count: int,
        shuffle: bool = False,
        seed: int = 0,
        start: Optional[int] = None,
        step: Optional[int] = None,
        advance: int = 0,
    ):
        self._sample_count = sample_count
        self._seed = seed
        self._shuffle = shuffle
        self._start = distributed.get_global_rank() if start is None else start
        self._step = distributed.get_global_size() if step is None else step
        self._advance = advance

    def __iter__(self):
        if self._shuffle:
            iterator = self._shuffled_iterator()
        else:
            iterator = self._iterator()

        yield from itertools.islice(iterator, self._advance, None)

    def _iterator(self):
        assert not self._shuffle

        while True:
            iterable = range(self._sample_count)
            yield from itertools.islice(iterable, self._start, None, self._step)

    def _shuffled_iterator(self):
        assert self._shuffle

        # Instantiate a generator here (rather than in the ctor) to keep the class
        # picklable (requirement of mp.spawn)
        generator = torch.Generator().manual_seed(self._seed)

        while True:
            iterable = _generate_randperm_indices(size=self._sample_count, generator=generator)
            yield from itertools.islice(iterable, self._start, None, self._step)


# The following function is somewhat equivalent to _new_shuffle_tensor_slice below,
# but avoids a full in-place random permutation generation.
def _shuffle_tensor_slice(
    *, tensor: torch.Tensor, start: int = 0, step: int = 1, generator: torch.Generator
) -> np.ndarray:
    stop = len(tensor)
    count = stop // step
    drop_count = stop - step * count
    if drop_count:
        warnings.warn(f"# of dropped samples: {drop_count}")

    dtype = _get_numpy_dtype(stop)
    result = np.empty(count, dtype=dtype)

    for i in range(count):
        j = torch.randint(0, i + 1, size=(1,), generator=generator).item() if i > 0 else 0

        result[i] = result[j]
        result[j] = tensor[start + i * step].item()

    return result


def _new_shuffle_tensor_slice(
    *, tensor: torch.Tensor, start: int = 0, step: int = 1, generator: torch.Generator
) -> np.ndarray:
    stop = len(tensor)
    count = stop // step
    dtype = torch.int64  # Needed for using randperm result as indices
    count = stop // step
    drop_count = stop - step * count
    if drop_count:
        warnings.warn(f"# of dropped samples: {drop_count}")
    indices = torch.randperm(count, dtype=dtype, generator=generator)
    return tensor[start::step][indices].numpy()


def _make_seed(seed: int, start: int, iter_count: int) -> int:
    # NOTE: Tried a few variants (including iter_count << 32), this one worked best.
    return seed + start + (iter_count << 24)


class ShardedInfiniteSampler(Sampler):
    def __init__(
        self,
        *,
        sample_count: int,
        shuffle: bool = False,
        seed: int = 0,
        start: Optional[int] = None,
        step: Optional[int] = None,
        advance: int = 0,
        use_new_shuffle_tensor_slice: bool = False,
    ):
        self._sample_count = sample_count
        self._seed = seed
        self._shuffle = shuffle
        self._start = distributed.get_global_rank() if start is None else start
        self._step = distributed.get_global_size() if step is None else step
        self._advance = advance
        self._iter_count = 0
        self._shuffle_tensor_slice_fn = (
            _new_shuffle_tensor_slice if use_new_shuffle_tensor_slice else _shuffle_tensor_slice
        )

    def __iter__(self):
        iter_count = self._advance // self._sample_count
        if iter_count > 0:
            self._advance -= iter_count * self._sample_count
            self._iter_count += iter_count

        if self._shuffle:
            iterator = self._shuffled_iterator()
        else:
            iterator = self._iterator()

        yield from itertools.islice(iterator, self._advance, None)

    def _iterator(self):
        assert not self._shuffle

        while True:
            iterable = range(self._sample_count)
            yield from itertools.islice(iterable, self._start, None, self._step)

    def _shuffled_iterator(self):
        assert self._shuffle

        # Instantiate a generator here (rather than in the ctor) to be keep the class
        # picklable (requirement of mp.spawn)
        generator = torch.Generator()

        # Always shuffle everything first
        generator.manual_seed(self._seed)
        dtype = _get_torch_dtype(self._sample_count)
        perm = torch.randperm(self._sample_count, dtype=dtype, generator=generator)

        while True:
            # Re-seed on each iteration to allow skipping whole permutations
            seed = _make_seed(self._seed, self._start, self._iter_count)
            generator.manual_seed(seed)

            iterable = self._shuffle_tensor_slice_fn(
                tensor=perm, start=self._start, step=self._step, generator=generator
            )
            yield from iterable
            self._iter_count += 1