forked from NVIDIA/Megatron-LM
-
Notifications
You must be signed in to change notification settings - Fork 0
/
image_folder.py
302 lines (269 loc) · 12.4 KB
/
image_folder.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
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
# BSD 3-Clause License
#
# Copyright (c) Soumith Chintala 2016,
# All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:
#
# * Redistributions of source code must retain the above copyright notice, this
# list of conditions and the following disclaimer.
#
# * Redistributions in binary form must reproduce the above copyright notice,
# this list of conditions and the following disclaimer in the documentation
# and/or other materials provided with the distribution.
#
# * Neither the name of the copyright holder nor the names of its
# contributors may be used to endorse or promote products derived from
# this software without specific prior written permission.
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
# CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
# code taken from
# https://github.com/pytorch/vision/blob/main/torchvision/datasets/folder.py
# added support for classes_fraction and data_per_class_fraction
from torchvision.datasets import VisionDataset
from PIL import Image
import os
import os.path
from typing import Any, Callable, cast, Dict, List, Optional, Tuple
import numpy as np
def has_file_allowed_extension(filename: str, extensions: Tuple[str, ...]) -> bool:
"""Checks if a file is an allowed extension.
Args:
filename (string): path to a file
extensions (tuple of strings): extensions to consider (lowercase)
Returns:
bool: True if the filename ends with one of given extensions
"""
return filename.lower().endswith(extensions)
def is_image_file(filename: str) -> bool:
"""Checks if a file is an allowed image extension.
Args:
filename (string): path to a file
Returns:
bool: True if the filename ends with a known image extension
"""
return has_file_allowed_extension(filename, IMG_EXTENSIONS)
def make_dataset(
directory: str,
class_to_idx: Dict[str, int],
data_per_class_fraction: float,
extensions: Optional[Tuple[str, ...]] = None,
is_valid_file: Optional[Callable[[str], bool]] = None,
) -> List[Tuple[str, int]]:
"""Generates a list of samples of a form (path_to_sample, class).
Args:
directory (str): root dataset directory
class_to_idx (Dict[str, int]): dictionary mapping class name to class index
extensions (optional): A list of allowed extensions.
Either extensions or is_valid_file should be passed. Defaults to None.
is_valid_file (optional): A function that takes path of a file
and checks if the file is a valid file
(used to check of corrupt files) both extensions and
is_valid_file should not be passed. Defaults to None.
Raises:
ValueError: In case ``extensions`` and ``is_valid_file`` are None or both are not None.
Returns:
List[Tuple[str, int]]: samples of a form (path_to_sample, class)
"""
instances = []
directory = os.path.expanduser(directory)
both_none = extensions is None and is_valid_file is None
both_something = extensions is not None and is_valid_file is not None
if both_none or both_something:
raise ValueError("Both extensions and is_valid_file cannot be None or not None at the same time")
if extensions is not None:
def is_valid_file(x: str) -> bool:
return has_file_allowed_extension(x, cast(Tuple[str, ...], extensions))
is_valid_file = cast(Callable[[str], bool], is_valid_file)
for target_class in sorted(class_to_idx.keys()):
class_index = class_to_idx[target_class]
target_dir = os.path.join(directory, target_class)
if not os.path.isdir(target_dir):
continue
local_instances = []
for root, _, fnames in sorted(os.walk(target_dir, followlinks=True)):
for fname in sorted(fnames):
path = os.path.join(root, fname)
if is_valid_file(path):
item = path, class_index
local_instances.append(item)
instances.extend(local_instances[0:int(len(local_instances) * data_per_class_fraction)])
return instances
class DatasetFolder(VisionDataset):
"""A generic data loader where the samples are arranged in this way: ::
root/class_x/xxx.ext
root/class_x/xxy.ext
root/class_x/[...]/xxz.ext
root/class_y/123.ext
root/class_y/nsdf3.ext
root/class_y/[...]/asd932_.ext
Args:
root (string): Root directory path.
loader (callable): A function to load a sample given its path.
extensions (tuple[string]): A list of allowed extensions.
both extensions and is_valid_file should not be passed.
transform (callable, optional): A function/transform that takes in
a sample and returns a transformed version.
E.g, ``transforms.RandomCrop`` for images.
target_transform (callable, optional): A function/transform that takes
in the target and transforms it.
is_valid_file (callable, optional): A function that takes path of a file
and check if the file is a valid file (used to check of corrupt files)
both extensions and is_valid_file should not be passed.
Attributes:
classes (list): List of the class names sorted alphabetically.
class_to_idx (dict): Dict with items (class_name, class_index).
samples (list): List of (sample path, class_index) tuples
targets (list): The class_index value for each image in the dataset
"""
def __init__(
self,
root: str,
loader: Callable[[str], Any],
extensions: Optional[Tuple[str, ...]] = None,
transform: Optional[Callable] = None,
target_transform: Optional[Callable] = None,
classes_fraction=1.0,
data_per_class_fraction=1.0,
is_valid_file: Optional[Callable[[str], bool]] = None,
) -> None:
super(DatasetFolder, self).__init__(root, transform=transform,
target_transform=target_transform)
self.classes_fraction = classes_fraction
self.data_per_class_fraction = data_per_class_fraction
classes, class_to_idx = self._find_classes(self.root)
samples = self.make_dataset(self.root,
class_to_idx,
self.data_per_class_fraction,
extensions,
is_valid_file)
if len(samples) == 0:
msg = "Found 0 files in subfolders of: {}\n".format(self.root)
if extensions is not None:
msg += "Supported extensions are: {}".format(",".join(extensions))
raise RuntimeError(msg)
self.loader = loader
self.extensions = extensions
self.total = len(samples)
self.classes = classes
self.class_to_idx = class_to_idx
self.samples = samples
self.targets = [s[1] for s in samples]
@staticmethod
def make_dataset(
directory: str,
class_to_idx: Dict[str, int],
data_per_class_fraction: float,
extensions: Optional[Tuple[str, ...]] = None,
is_valid_file: Optional[Callable[[str], bool]] = None,
) -> List[Tuple[str, int]]:
return make_dataset(directory,
class_to_idx,
data_per_class_fraction,
extensions=extensions,
is_valid_file=is_valid_file)
def _find_classes(self, dir: str) -> Tuple[List[str], Dict[str, int]]:
"""
Finds the class folders in a dataset.
Args:
dir (string): Root directory path.
Returns:
tuple: (classes, class_to_idx) where classes are relative to (dir), and class_to_idx is a dictionary.
Ensures:
No class is a subdirectory of another.
"""
all_classes = [d.name for d in os.scandir(dir) if d.is_dir()]
classes = all_classes[0:int(len(all_classes) * self.classes_fraction)]
classes.sort()
class_to_idx = {cls_name: i for i, cls_name in enumerate(classes)}
return classes, class_to_idx
def __getitem__(self, index: int) -> Tuple[Any, Any]:
"""
Args:
index (int): Index
Returns:
tuple: (sample, target) where target is class_index of the target class.
"""
curr_index = index
for x in range(self.total):
try:
path, target = self.samples[curr_index]
sample = self.loader(path)
break
except Exception as e:
curr_index = np.random.randint(0, self.total)
if self.transform is not None:
sample = self.transform(sample)
if self.target_transform is not None:
target = self.target_transform(target)
return sample, target
def __len__(self) -> int:
return len(self.samples)
IMG_EXTENSIONS = ('.jpg', '.jpeg', '.png', '.ppm', '.bmp', '.pgm', '.tif', '.tiff', '.webp')
def pil_loader(path: str) -> Image.Image:
# open path as file to avoid ResourceWarning (https://github.com/python-pillow/Pillow/issues/835)
with open(path, 'rb') as f:
img = Image.open(f)
return img.convert('RGB')
# TODO: specify the return type
def accimage_loader(path: str) -> Any:
import accimage
try:
return accimage.Image(path)
except IOError:
# Potentially a decoding problem, fall back to PIL.Image
return pil_loader(path)
def default_loader(path: str) -> Any:
from torchvision import get_image_backend
if get_image_backend() == 'accimage':
return accimage_loader(path)
else:
return pil_loader(path)
class ImageFolder(DatasetFolder):
"""A generic data loader where the images are arranged in this way: ::
root/dog/xxx.png
root/dog/xxy.png
root/dog/[...]/xxz.png
root/cat/123.png
root/cat/nsdf3.png
root/cat/[...]/asd932_.png
Args:
root (string): Root directory path.
transform (callable, optional): A function/transform that takes in an PIL image
and returns a transformed version. E.g, ``transforms.RandomCrop``
target_transform (callable, optional): A function/transform that takes in the
target and transforms it.
loader (callable, optional): A function to load an image given its path.
is_valid_file (callable, optional): A function that takes path of an Image file
and check if the file is a valid file (used to check of corrupt files)
Attributes:
classes (list): List of the class names sorted alphabetically.
class_to_idx (dict): Dict with items (class_name, class_index).
imgs (list): List of (image path, class_index) tuples
"""
def __init__(
self,
root: str,
transform: Optional[Callable] = None,
target_transform: Optional[Callable] = None,
classes_fraction=1.0,
data_per_class_fraction=1.0,
loader: Callable[[str], Any] = default_loader,
is_valid_file: Optional[Callable[[str], bool]] = None,
):
super(ImageFolder, self).__init__(root, loader, IMG_EXTENSIONS if is_valid_file is None else None,
transform=transform,
target_transform=target_transform,
classes_fraction=classes_fraction,
data_per_class_fraction=data_per_class_fraction,
is_valid_file=is_valid_file)
self.imgs = self.samples