-
Notifications
You must be signed in to change notification settings - Fork 8
/
dataset.py
380 lines (297 loc) · 14.3 KB
/
dataset.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
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
# from __future__ import print_function
from torchvision.datasets.vision import VisionDataset
import warnings
from PIL import Image
import os
import os.path
import numpy as np
import torch
import codecs
import zipfile
import sys
if sys.version_info[0] == 2:
import cPickle as pickle
else:
import pickle
from torchvision.datasets.utils import download_url, download_and_extract_archive, extract_archive, makedir_exist_ok, verify_str_arg, check_integrity
class MNIST_soft(VisionDataset):
""" MNIST Dataset with soft targets.
Args:
root (string): Root directory of dataset where ``MNIST/processed/training.pt`` and ``MNIST/processed/test.pt`` exist.
targets: Soft targets.
train (bool, optional): If True, creates dataset from ``training.pt``, otherwise from ``test.pt``.
download (bool, optional): If true, downloads the dataset from the internet and puts it in root directory. If dataset is already downloaded, it is not downloaded again.
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.
"""
resources = [
("http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz", "f68b3c2dcbeaaa9fbdd348bbdeb94873"),
("http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz", "d53e105ee54ea40749a09fcbcd1e9432"),
("http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz", "9fb629c4189551a2d022fa330f9573f3"),
("http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz", "ec29112dd5afa0611ce80d1b7f02629c")
]
training_file = 'training.pt'
test_file = 'test.pt'
classes = ['0 - zero', '1 - one', '2 - two', '3 - three', '4 - four',
'5 - five', '6 - six', '7 - seven', '8 - eight', '9 - nine']
@property
def train_labels(self):
warnings.warn("train_labels has been renamed targets")
return self.targets
@property
def test_labels(self):
warnings.warn("test_labels has been renamed targets")
return self.targets
@property
def train_data(self):
warnings.warn("train_data has been renamed data")
return self.data
@property
def test_data(self):
warnings.warn("test_data has been renamed data")
return self.data
def __init__(self, root, targets_soft, train=True, transform=None, target_transform=None,
download=False):
super(MNIST_soft, self).__init__(root, transform=transform, target_transform=target_transform)
self.train = train # training set or test set
self.targets_soft = targets_soft
if download:
self.download()
if not self._check_exists():
raise RuntimeError('Dataset not found.' +
' You can use download=True to download it')
if self.train:
data_file = self.training_file
else:
data_file = self.test_file
self.data, self.targets = torch.load(os.path.join(self.processed_folder, data_file))
def __getitem__(self, index):
"""
Args:
index (int): Index
Returns:
tuple: (image, target) where target is index of the target class.
"""
img, target_soft, target = self.data[index], self.targets_soft[index], int(self.targets[index])
# doing this so that it is consistent with all other datasets
# to return a PIL Image
img = Image.fromarray(img.numpy(), mode='L')
if self.transform is not None:
img = self.transform(img)
if self.target_transform is not None:
target = self.target_transform(target)
return img, target_soft, target
def __len__(self):
return len(self.data)
@property
def raw_folder(self):
return os.path.join(self.root, 'MNIST', 'raw')
@property
def processed_folder(self):
return os.path.join(self.root, 'MNIST', 'processed')
@property
def class_to_idx(self):
return {_class: i for i, _class in enumerate(self.classes)}
def _check_exists(self):
return (os.path.exists(os.path.join(self.processed_folder,
self.training_file)) and
os.path.exists(os.path.join(self.processed_folder,
self.test_file)))
def download(self):
"""Download the MNIST data if it doesn't exist in processed_folder already."""
if self._check_exists():
return
makedir_exist_ok(self.raw_folder)
makedir_exist_ok(self.processed_folder)
# download files
for url, md5 in self.resources:
filename = url.rpartition('/')[2]
download_and_extract_archive(url, download_root=self.raw_folder, filename=filename, md5=md5)
# process and save as torch files
print('Processing...')
training_set = (
read_image_file(os.path.join(self.raw_folder, 'train-images-idx3-ubyte')),
read_label_file(os.path.join(self.raw_folder, 'train-labels-idx1-ubyte'))
)
test_set = (
read_image_file(os.path.join(self.raw_folder, 't10k-images-idx3-ubyte')),
read_label_file(os.path.join(self.raw_folder, 't10k-labels-idx1-ubyte'))
)
with open(os.path.join(self.processed_folder, self.training_file), 'wb') as f:
torch.save(training_set, f)
with open(os.path.join(self.processed_folder, self.test_file), 'wb') as f:
torch.save(test_set, f)
print('Done!')
def extra_repr(self):
return "Split: {}".format("Train" if self.train is True else "Test")
class CIFAR10_soft(VisionDataset):
"""`CIFAR10 <https://www.cs.toronto.edu/~kriz/cifar.html>`_ Dataset.
Args:
root (string): Root directory of dataset where directory ``cifar-10-batches-py`` exists or will be saved to if download is set to True.
train (bool, optional): If True, creates dataset from training set, otherwise creates from test set.
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.
download (bool, optional): If true, downloads the dataset from the internet and puts it in root directory. If dataset is already downloaded, it is not downloaded again.
"""
base_folder = 'cifar-10-batches-py'
url = "https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz"
filename = "cifar-10-python.tar.gz"
tgz_md5 = 'c58f30108f718f92721af3b95e74349a'
train_list = [
['data_batch_1', 'c99cafc152244af753f735de768cd75f'],
['data_batch_2', 'd4bba439e000b95fd0a9bffe97cbabec'],
['data_batch_3', '54ebc095f3ab1f0389bbae665268c751'],
['data_batch_4', '634d18415352ddfa80567beed471001a'],
['data_batch_5', '482c414d41f54cd18b22e5b47cb7c3cb'],
]
test_list = [
['test_batch', '40351d587109b95175f43aff81a1287e'],
]
meta = {
'filename': 'batches.meta',
'key': 'label_names',
'md5': '5ff9c542aee3614f3951f8cda6e48888',
}
def __init__(self, root, targets_soft, train=True, transform=None, target_transform=None,
download=False):
super(CIFAR10_soft, self).__init__(root, transform=transform, target_transform=target_transform)
self.train = train # training set or test set
self.targets_soft = targets_soft
if download:
self.download()
if not self._check_integrity():
raise RuntimeError('Dataset not found or corrupted.' +
' You can use download=True to download it')
if self.train:
downloaded_list = self.train_list
else:
downloaded_list = self.test_list
self.data = []
self.targets = []
# now load the picked numpy arrays
for file_name, checksum in downloaded_list:
file_path = os.path.join(self.root, self.base_folder, file_name)
with open(file_path, 'rb') as f:
if sys.version_info[0] == 2:
entry = pickle.load(f)
else:
entry = pickle.load(f, encoding='latin1')
self.data.append(entry['data'])
if 'labels' in entry:
self.targets.extend(entry['labels'])
else:
self.targets.extend(entry['fine_labels'])
self.data = np.vstack(self.data).reshape(-1, 3, 32, 32)
self.data = self.data.transpose((0, 2, 3, 1)) # convert to HWC
self._load_meta()
def _load_meta(self):
path = os.path.join(self.root, self.base_folder, self.meta['filename'])
if not check_integrity(path, self.meta['md5']):
raise RuntimeError('Dataset metadata file not found or corrupted.' +
' You can use download=True to download it')
with open(path, 'rb') as infile:
if sys.version_info[0] == 2:
data = pickle.load(infile)
else:
data = pickle.load(infile, encoding='latin1')
self.classes = data[self.meta['key']]
self.class_to_idx = {_class: i for i, _class in enumerate(self.classes)}
def __getitem__(self, index):
"""
Args:
index (int): Index
Returns:
tuple: (image, target) where target is index of the target class.
"""
img, target_soft, target = self.data[index], self.targets_soft[index], self.targets[index]
# doing this so that it is consistent with all other datasets
# to return a PIL Image
img = Image.fromarray(img)
if self.transform is not None:
img = self.transform(img)
if self.target_transform is not None:
target = self.target_transform(target)
return img, target_soft, target
def __len__(self):
return len(self.data)
def _check_integrity(self):
root = self.root
for fentry in (self.train_list + self.test_list):
filename, md5 = fentry[0], fentry[1]
fpath = os.path.join(root, self.base_folder, filename)
if not check_integrity(fpath, md5):
return False
return True
def download(self):
if self._check_integrity():
print('Files already downloaded and verified')
return
download_and_extract_archive(self.url, self.root, filename=self.filename, md5=self.tgz_md5)
def extra_repr(self):
return "Split: {}".format("Train" if self.train is True else "Test")
class Clothing1M(VisionDataset):
def __init__(self, root, mode='train', transform=None, target_transform=None):
super(Clothing1M, self).__init__(root, transform=transform, target_transform=target_transform)
if mode=='train':
flist = os.path.join(root, "annotations/noisy_train.txt")
if mode=='val':
flist = os.path.join(root, "annotations/clean_val.txt")
if mode=='test':
flist = os.path.join(root, "annotations/clean_test.txt")
if not os.path.exists(flist):
raise RuntimeError('Dataset not found or not extracted.' +
' You can contact the author of Clothing1M for the download link. <Xiao, Tong, et al. (2015). Learning from massive noisy labeled data for image classification>')
self.imlist = self.flist_reader(flist)
def __getitem__(self, index):
impath, target = self.imlist[index]
img = Image.open(impath).convert("RGB")
if self.transform is not None:
img = self.transform(img)
if self.target_transform is not None:
target = self.target_transform(target)
return img, target
def __len__(self):
return len(self.imlist)
def flist_reader(self, flist):
imlist = []
with open(flist, 'r') as rf:
for line in rf.readlines():
row = line.split(" ")
impath = self.root + '/' + row[0]
imlabel = row[1]
imlist.append((impath, int(imlabel)))
return imlist
class Clothing1M_soft(VisionDataset):
def __init__(self, root, targets_soft, mode='train', transform=None, target_transform=None):
super(Clothing1M_soft, self).__init__(root, transform=transform, target_transform=target_transform)
if mode=='train':
flist = os.path.join(root, "annotations/noisy_train.txt")
if mode=='val':
flist = os.path.join(root, "annotations/clean_val.txt")
if mode=='test':
flist = os.path.join(root, "annotations/clean_test.txt")
if not os.path.exists(flist):
raise RuntimeError('Dataset not found or not extracted.' +
' You can contact the author of Clothing1M for the download link. <Xiao, Tong, et al. (2015). Learning from massive noisy labeled data for image classification>')
self.imlist = self.flist_reader(flist)
self.targets_soft = targets_soft
def __getitem__(self, index):
impath, target = self.imlist[index]
img = Image.open(impath).convert("RGB")
target_soft = self.targets_soft[index]
if self.transform is not None:
img = self.transform(img)
if self.target_transform is not None:
target = self.target_transform(target)
return img, target_soft, target
def __len__(self):
return len(self.imlist)
def flist_reader(self, flist):
imlist = []
with open(flist, 'r') as rf:
for line in rf.readlines():
row = line.split(" ")
impath = self.root + '/' + row[0]
imlabel = row[1]
imlist.append((impath, int(imlabel)))
return imlist