-
Notifications
You must be signed in to change notification settings - Fork 4
/
Copy pathdatasets.py
240 lines (183 loc) · 8.15 KB
/
datasets.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
# minor modifications from main pytorch
import torch.utils.data as data
from PIL import Image
import os
import os.path
IMG_EXTENSIONS = ['.jpg', '.jpeg', '.png', '.ppm', '.bmp', '.pgm', '.tif']
def has_file_allowed_extension(filename, extensions):
"""Checks if a file is an allowed extension.
Args:
filename (string): path to a file
Returns:
bool: True if the filename ends with a known image extension
"""
filename_lower = filename.lower()
return any(filename_lower.endswith(ext) for ext in extensions)
def pil_loader(path):
# 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')
def accimage_loader(path):
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):
from torchvision import get_image_backend
if get_image_backend() == 'accimage':
return accimage_loader(path)
else:
return pil_loader(path)
def find_classes(dir):
classes = [d for d in os.listdir(dir) if os.path.isdir(os.path.join(dir, d))]
classes.sort()
class_to_idx = {classes[i]: i for i in range(len(classes))}
return classes, class_to_idx
def make_dataset(dir, class_to_idx, extensions):
images = []
dir = os.path.expanduser(dir)
dir_len = len(dir)+1
for target in sorted(os.listdir(dir)):
d = os.path.join(dir, target)
if not os.path.isdir(d):
continue
for root, _, fnames in sorted(os.walk(d)):
for fname in sorted(fnames):
if has_file_allowed_extension(fname, extensions):
path = os.path.join(root[dir_len:], fname)
item = (path, class_to_idx[target])
images.append(item)
return images
class ImageFolder(data.Dataset):
"""A generic data loader where the samples are arranged in this way: ::
root1/class_x/xxx.ext
root1/class_x/xxy.ext
root1/class_x/xxz.ext
root1/class_y/123.ext
root1/class_y/nsdf3.ext
root1/class_y/asd932_.ext
Args:
root1 (string): Root 1 directory path.
loader (callable): A function to load a sample given its path.
extensions (list[string]): A list of allowed extensions.
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.
return_path: also returns the name of the image
Attributes:
classes (list): List of the class names.
class_to_idx (dict): Dict with items (class_name, class_index).
samples (list): List of (sample path, class_index) tuples
"""
def __init__(self, root, loader=default_loader, extensions=IMG_EXTENSIONS, transform=None, target_transform=None, return_path=False):
classes, class_to_idx = find_classes(root)
samples = make_dataset(root, class_to_idx, extensions)
if len(samples) == 0:
raise(RuntimeError("Found 0 files in subfolders of: " + root + "\n"
"Supported extensions are: " + ",".join(extensions)))
self.root = root
self.loader = loader
self.extensions = extensions
self.classes = classes
self.class_to_idx = class_to_idx
self.samples = samples
self.transform = transform
self.target_transform = target_transform
self.return_path = return_path
def __getitem__(self, index):
"""
Args:
index (int): Index
Returns:
tuple: (sample, target) where target is class_index of the target class.
"""
path, target = self.samples[index]
sample = self.loader(os.path.join(self.root,path))
if self.transform is not None:
sample = self.transform(sample)
if self.target_transform is not None:
target = self.target_transform(target)
if self.return_path:
return sample, target, path
else:
return sample, target
def __len__(self):
return len(self.samples)
def __repr__(self):
fmt_str = 'Dataset ' + self.__class__.__name__ + '\n'
fmt_str += ' Number of datapoints: {}\n'.format(self.__len__())
fmt_str += ' Root Location: {}\n'.format(self.root)
tmp = ' Transforms (if any): '
fmt_str += '{0}{1}\n'.format(tmp, self.transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
tmp = ' Target Transforms (if any): '
fmt_str += '{0}{1}'.format(tmp, self.target_transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
return fmt_str
class PairedImageFolder(data.Dataset):
"""A generic data loader where the samples are arranged in this way: ::
root1/class_x/xxx.ext root2/class_x/xxx.ext
root1/class_x/xxy.ext root2/class_x/xxy.ext
root1/class_x/xxz.ext root2/class_x/xxz.ext
root1/class_y/123.ext root2/class_y/123.ext
root1/class_y/nsdf3.ext root2/class_y/nsdf3.ext
root1/class_y/asd932_.ext root2/class_y/asd932_.ext
Args:
root1 (string): Root 1 directory path.
root2 (string): Root 2 directory path.
loader (callable): A function to load a sample given its path.
extensions (list[string]): A list of allowed extensions.
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.
Attributes:
classes (list): List of the class names.
class_to_idx (dict): Dict with items (class_name, class_index).
samples (list): List of (sample path, class_index) tuples
"""
def __init__(self, root1, root2, loader=default_loader, extensions=IMG_EXTENSIONS, transform=None, target_transform=None):
classes, class_to_idx = find_classes(root1)
samples = make_dataset(root1, class_to_idx, extensions)
if len(samples) == 0:
raise(RuntimeError("Found 0 files in subfolders of: " + root + "\n"
"Supported extensions are: " + ",".join(extensions)))
self.root1 = root1
self.root2 = root2
self.loader = loader
self.extensions = extensions
self.classes = classes
self.class_to_idx = class_to_idx
self.samples = samples
self.transform = transform
self.target_transform = target_transform
def __getitem__(self, index):
"""
Args:
index (int): Index
Returns:
tuple: (sample, target) where target is class_index of the target class.
"""
path, target = self.samples[index]
sample1 = self.loader(os.path.join(self.root1,path))
sample2 = self.loader(os.path.join(self.root2,path))
if self.transform is not None:
sample1, sample2 = self.transform([sample1, sample2])
if self.target_transform is not None:
target = self.target_transform(target)
return [sample1, sample2], target
def __len__(self):
return len(self.samples)
def __repr__(self):
fmt_str = 'Dataset ' + self.__class__.__name__ + '\n'
fmt_str += ' Number of datapoints: {}\n'.format(self.__len__())
fmt_str += ' Root Location: {} {}\n'.format(self.root1, self.root2)
tmp = ' Transforms (if any): '
fmt_str += '{0}{1}\n'.format(tmp, self.transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
tmp = ' Target Transforms (if any): '
fmt_str += '{0}{1}'.format(tmp, self.target_transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
return fmt_str