-
Notifications
You must be signed in to change notification settings - Fork 321
/
cifar10_datamodule.py
234 lines (195 loc) · 7.21 KB
/
cifar10_datamodule.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
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
import os
from typing import Optional, Sequence
import torch
from pytorch_lightning import LightningDataModule
from torch.utils.data import DataLoader, random_split
from pl_bolts.datasets.cifar10_dataset import TrialCIFAR10
from pl_bolts.transforms.dataset_normalizations import cifar10_normalization
from pl_bolts.utils.warnings import warn_missing_pkg
try:
from torchvision import transforms as transform_lib
from torchvision.datasets import CIFAR10
except ModuleNotFoundError:
warn_missing_pkg('torchvision') # pragma: no-cover
_TORCHVISION_AVAILABLE = False
else:
_TORCHVISION_AVAILABLE = True
class CIFAR10DataModule(LightningDataModule):
"""
.. figure:: https://3qeqpr26caki16dnhd19sv6by6v-wpengine.netdna-ssl.com/wp-content/uploads/2019/01/
Plot-of-a-Subset-of-Images-from-the-CIFAR-10-Dataset.png
:width: 400
:alt: CIFAR-10
Specs:
- 10 classes (1 per class)
- Each image is (3 x 32 x 32)
Standard CIFAR10, train, val, test splits and transforms
Transforms::
mnist_transforms = transform_lib.Compose([
transform_lib.ToTensor(),
transforms.Normalize(
mean=[x / 255.0 for x in [125.3, 123.0, 113.9]],
std=[x / 255.0 for x in [63.0, 62.1, 66.7]]
)
])
Example::
from pl_bolts.datamodules import CIFAR10DataModule
dm = CIFAR10DataModule(PATH)
model = LitModel()
Trainer().fit(model, dm)
Or you can set your own transforms
Example::
dm.train_transforms = ...
dm.test_transforms = ...
dm.val_transforms = ...
"""
name = 'cifar10'
extra_args = {}
def __init__(
self,
data_dir: Optional[str] = None,
val_split: int = 5000,
num_workers: int = 16,
batch_size: int = 32,
seed: int = 42,
*args,
**kwargs,
):
"""
Args:
data_dir: where to save/load the data
val_split: how many of the training images to use for the validation split
num_workers: how many workers to use for loading data
batch_size: number of examples per training/eval step
"""
super().__init__(*args, **kwargs)
if not _TORCHVISION_AVAILABLE:
raise ModuleNotFoundError( # pragma: no-cover
'You want to use CIFAR10 dataset loaded from `torchvision` which is not installed yet.'
)
self.dims = (3, 32, 32)
self.DATASET = CIFAR10
self.val_split = val_split
self.num_workers = num_workers
self.batch_size = batch_size
self.seed = seed
self.data_dir = data_dir if data_dir is not None else os.getcwd()
self.num_samples = 60000 - val_split
@property
def num_classes(self):
"""
Return:
10
"""
return 10
def prepare_data(self):
"""
Saves CIFAR10 files to data_dir
"""
self.DATASET(self.data_dir, train=True, download=True, transform=transform_lib.ToTensor(), **self.extra_args)
self.DATASET(self.data_dir, train=False, download=True, transform=transform_lib.ToTensor(), **self.extra_args)
def train_dataloader(self):
"""
CIFAR train set removes a subset to use for validation
"""
transforms = self.default_transforms() if self.train_transforms is None else self.train_transforms
dataset = self.DATASET(self.data_dir, train=True, download=False, transform=transforms, **self.extra_args)
train_length = len(dataset)
dataset_train, _ = random_split(
dataset,
[train_length - self.val_split, self.val_split],
generator=torch.Generator().manual_seed(self.seed)
)
loader = DataLoader(
dataset_train,
batch_size=self.batch_size,
shuffle=True,
num_workers=self.num_workers,
drop_last=True,
pin_memory=True
)
return loader
def val_dataloader(self):
"""
CIFAR10 val set uses a subset of the training set for validation
"""
transforms = self.default_transforms() if self.val_transforms is None else self.val_transforms
dataset = self.DATASET(self.data_dir, train=True, download=False, transform=transforms, **self.extra_args)
train_length = len(dataset)
_, dataset_val = random_split(
dataset,
[train_length - self.val_split, self.val_split],
generator=torch.Generator().manual_seed(self.seed)
)
loader = DataLoader(
dataset_val,
batch_size=self.batch_size,
shuffle=False,
num_workers=self.num_workers,
pin_memory=True,
drop_last=True
)
return loader
def test_dataloader(self):
"""
CIFAR10 test set uses the test split
"""
transforms = self.default_transforms() if self.test_transforms is None else self.test_transforms
dataset = self.DATASET(self.data_dir, train=False, download=False, transform=transforms, **self.extra_args)
loader = DataLoader(
dataset,
batch_size=self.batch_size,
shuffle=False,
num_workers=self.num_workers,
drop_last=True,
pin_memory=True
)
return loader
def default_transforms(self):
cf10_transforms = transform_lib.Compose([
transform_lib.ToTensor(),
cifar10_normalization()
])
return cf10_transforms
class TinyCIFAR10DataModule(CIFAR10DataModule):
"""
Standard CIFAR10, train, val, test splits and transforms
Transforms::
mnist_transforms = transform_lib.Compose([
transform_lib.ToTensor(),
transforms.Normalize(mean=[x / 255.0 for x in [125.3, 123.0, 113.9]],
std=[x / 255.0 for x in [63.0, 62.1, 66.7]])
])
Example::
from pl_bolts.datamodules import CIFAR10DataModule
dm = CIFAR10DataModule(PATH)
model = LitModel(datamodule=dm)
"""
def __init__(
self,
data_dir: str,
val_split: int = 50,
num_workers: int = 16,
num_samples: int = 100,
labels: Optional[Sequence] = (1, 5, 8),
*args,
**kwargs,
):
"""
Args:
data_dir: where to save/load the data
val_split: how many of the training images to use for the validation split
num_workers: how many workers to use for loading data
num_samples: number of examples per selected class/label
labels: list selected CIFAR10 classes/labels
"""
super().__init__(data_dir, val_split, num_workers, *args, **kwargs)
self.dims = (3, 32, 32)
self.DATASET = TrialCIFAR10
self.num_samples = num_samples
self.labels = sorted(labels) if labels is not None else set(range(10))
self.extra_args = dict(num_samples=self.num_samples, labels=self.labels)
@property
def num_classes(self) -> int:
"""Return number of classes."""
return len(self.labels)