-
Notifications
You must be signed in to change notification settings - Fork 21
/
Copy pathsamplers.py
210 lines (177 loc) · 8.26 KB
/
samplers.py
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
# Copyright (c) 2015-present, Facebook, Inc.
# All rights reserved.
import torch
import torch.distributed as dist
import math
import os
from torch.utils.data.sampler import Sampler
class RASampler(torch.utils.data.Sampler):
"""Sampler that restricts data loading to a subset of the dataset for distributed,
with repeated augmentation.
It ensures that different each augmented version of a sample will be visible to a
different process (GPU)
Heavily based on torch.utils.data.DistributedSampler
"""
def __init__(self, dataset, num_replicas=None, rank=None, shuffle=True):
if num_replicas is None:
if not dist.is_available():
raise RuntimeError("Requires distributed package to be available")
num_replicas = dist.get_world_size()
if rank is None:
if not dist.is_available():
raise RuntimeError("Requires distributed package to be available")
rank = dist.get_rank()
self.dataset = dataset
self.num_replicas = num_replicas
self.rank = rank
self.epoch = 0
self.num_samples = int(math.ceil(len(self.dataset) * 3.0 / self.num_replicas))
self.total_size = self.num_samples * self.num_replicas
# self.num_selected_samples = int(math.ceil(len(self.dataset) / self.num_replicas))
self.num_selected_samples = int(math.floor(len(self.dataset) // 256 * 256 / self.num_replicas))
self.shuffle = shuffle
def __iter__(self):
# deterministically shuffle based on epoch
g = torch.Generator()
g.manual_seed(self.epoch)
if self.shuffle:
indices = torch.randperm(len(self.dataset), generator=g).tolist()
else:
indices = list(range(len(self.dataset)))
# add extra samples to make it evenly divisible
indices = [ele for ele in indices for i in range(3)]
indices += indices[:(self.total_size - len(indices))]
assert len(indices) == self.total_size
# subsample
indices = indices[self.rank:self.total_size:self.num_replicas]
assert len(indices) == self.num_samples
return iter(indices[:self.num_selected_samples])
def __len__(self):
return self.num_selected_samples
def set_epoch(self, epoch):
self.epoch = epoch
# The following code is adapted from deformable detr.
# ------------------------------------------------------------------------
# Deformable DETR
# Copyright (c) 2020 SenseTime. All Rights Reserved.
# Licensed under the Apache License, Version 2.0 [see LICENSE for details]
# ------------------------------------------------------------------------
# Modified from codes in torch.utils.data.distributed
# ------------------------------------------------------------------------
class DistributedSampler(Sampler):
"""Sampler that restricts data loading to a subset of the dataset.
It is especially useful in conjunction with
:class:`torch.nn.parallel.DistributedDataParallel`. In such case, each
process can pass a DistributedSampler instance as a DataLoader sampler,
and load a subset of the original dataset that is exclusive to it.
.. note::
Dataset is assumed to be of constant size.
Arguments:
dataset: Dataset used for sampling.
num_replicas (optional): Number of processes participating in
distributed training.
rank (optional): Rank of the current process within num_replicas.
"""
def __init__(self, dataset, num_replicas=None, rank=None, local_rank=None, local_size=None, shuffle=True):
if num_replicas is None:
if not dist.is_available():
raise RuntimeError("Requires distributed package to be available")
num_replicas = dist.get_world_size()
if rank is None:
if not dist.is_available():
raise RuntimeError("Requires distributed package to be available")
rank = dist.get_rank()
self.dataset = dataset
self.num_replicas = num_replicas
self.rank = rank
self.epoch = 0
self.num_samples = int(math.ceil(len(self.dataset) * 1.0 / self.num_replicas))
self.total_size = self.num_samples * self.num_replicas
self.shuffle = shuffle
def __iter__(self):
if self.shuffle:
# deterministically shuffle based on epoch
g = torch.Generator()
g.manual_seed(self.epoch)
indices = torch.randperm(len(self.dataset), generator=g).tolist()
else:
indices = torch.arange(len(self.dataset)).tolist()
# add extra samples to make it evenly divisible
indices += indices[: (self.total_size - len(indices))]
assert len(indices) == self.total_size
# subsample
offset = self.num_samples * self.rank
indices = indices[offset : offset + self.num_samples]
# following https://github.com/pytorch/pytorch/issues/23430
# to make it compatible with sampler as input
if isinstance(self.dataset, Sampler):
orig_indices = list(iter(self.dataset))
indices = [orig_indices[i] for i in indices]
assert len(indices) == self.num_samples
return iter(indices)
def __len__(self):
return self.num_samples
def set_epoch(self, epoch):
self.epoch = epoch
class NodeDistributedSampler(Sampler):
"""Sampler that restricts data loading to a subset of the dataset.
It is especially useful in conjunction with
:class:`torch.nn.parallel.DistributedDataParallel`. In such case, each
process can pass a DistributedSampler instance as a DataLoader sampler,
and load a subset of the original dataset that is exclusive to it.
.. note::
Dataset is assumed to be of constant size.
Arguments:
dataset: Dataset used for sampling.
num_replicas (optional): Number of processes participating in
distributed training.
rank (optional): Rank of the current process within num_replicas.
"""
def __init__(self, dataset, num_replicas=None, rank=None, local_rank=None, local_size=None, shuffle=True):
if num_replicas is None:
if not dist.is_available():
raise RuntimeError("Requires distributed package to be available")
num_replicas = dist.get_world_size()
if rank is None:
if not dist.is_available():
raise RuntimeError("Requires distributed package to be available")
rank = dist.get_rank()
if local_rank is None:
local_rank = int(os.environ.get('LOCAL_RANK', 0))
if local_size is None:
local_size = int(os.environ.get('LOCAL_SIZE', 1))
self.dataset = dataset
self.shuffle = shuffle
self.num_replicas = num_replicas
self.num_parts = local_size
self.rank = rank
self.local_rank = local_rank
self.epoch = 0
self.num_samples = int(math.ceil(len(self.dataset) * 1.0 / self.num_replicas))
self.total_size = self.num_samples * self.num_replicas
self.total_size_parts = self.num_samples * self.num_replicas // self.num_parts
def __iter__(self):
if self.shuffle:
# deterministically shuffle based on epoch
g = torch.Generator()
g.manual_seed(self.epoch)
indices = torch.randperm(len(self.dataset), generator=g).tolist()
else:
indices = torch.arange(len(self.dataset)).tolist()
indices = [i for i in indices if i % self.num_parts == self.local_rank]
# add extra samples to make it evenly divisible
indices += indices[:(self.total_size_parts - len(indices))]
assert len(indices) == self.total_size_parts
# subsample
indices = indices[self.rank // self.num_parts:self.total_size_parts:self.num_replicas // self.num_parts]
# following https://github.com/pytorch/pytorch/issues/23430
# to make it compatible with sampler as input
if isinstance(self.dataset, Sampler):
orig_indices = list(iter(self.dataset))
indices = [orig_indices[i] for i in indices]
assert len(indices) == self.num_samples
return iter(indices)
def __len__(self):
return self.num_samples
def set_epoch(self, epoch):
self.epoch = epoch