forked from yaircarmon/semisup-adv
-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathcifar_own.py
365 lines (312 loc) · 13.2 KB
/
cifar_own.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
# from __future__ import print_function
# import torch.utils.data as data
# from PIL import Image
# import os
# import os.path
# import errno
# import numpy as np
# import sys
# if sys.version_info[0] == 2:
# import cPickle as pickle
# else:
# import pickle
# class CIFAR10(data.Dataset):
# base_folder = 'cifar-10-batches-py'
# url = "http://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz"
# filename = "cifar-10-python.tar.gz"
# tgz_mdf = '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'],
# ]
# def __init__(self, root, train=True, transform=None, target_transform=None, download=False):
# self.root = root
# self.transform = transform
# self.target_transform = target_transform
# self.train = train # training set or test set
# print("init already")
# if download:
# self.download()
# if not self._check_integrity():
# raise RuntimeError('Dataset not found or corrupted.'
# + ' You can use download=True to download it')
# # now load the picked numpy arrays
# if self.train:
# self.train_data = []
# self.train_labels = []
# for fentry in self.train_list:
# f = fentry[0]
# file = os.path.join(root, self.base_folder, f)
# fo = open(file, 'rb')
# if sys.version_info[0] == 2:
# entry = pickle.load(fo)
# else:
# entry = pickle.load(fo, encoding='latin1')
# self.train_data.append(entry['data'])
# if 'labels' in entry:
# self.train_labels += entry['labels']
# else:
# self.train_labels += entry['fine_labels']
# fo.close()
# self.train_data = np.concatenate(self.train_data)
# self.train_data = self.train_data.reshape((50000, 3, 32, 32))
# else:
# f = self.test_list[0][0]
# file = os.path.join(root, self.base_folder, f)
# fo = open(file, 'rb')
# if sys.version_info[0] == 2:
# entry = pickle.load(fo)
# else:
# entry = pickle.load(fo, encoding='latin1')
# self.test_data = entry['data']
# if 'labels' in entry:
# self.test_labels = entry['labels']
# else:
# self.test_labels = entry['fine_labels']
# fo.close()
# self.test_data = self.test_data.reshape((10000, 3, 32, 32))
# def __getitem__(self, index):
# if self.train:
# img, target = self.train_data[index], self.train_labels[index]
# else:
# img, target = self.test_data[index], self.test_labels[index]
# # doing this so that it is consistent with all other datasets
# # to return a PIL Image
# # print("cifar image type %s" % (str(img.dtype)))
# img = Image.fromarray(np.transpose(img, (1, 2, 0)))
# # print("cifar image type %s" % (str(img.dtype)))
# if self.transform is not None:
# img = self.transform(img)
# if self.target_transform is not None:
# target = self.target_transform(target)
# # print("cifar image type %s"%(str(img.dtype)))
# # print("cifar image type %s" % (str(img.dtype)))
# # print("cifar target type %s" % (str(target.dtype)))
# return img, target
# def set_data(self, img, target, idx):
# if self.train:
# self.train_data[idx] = img
# self.train_labels[idx] = target
# else:
# self.test_data[idx] = img
# self.test_labels[idx] = target
# def __len__(self):
# if self.train:
# return 50000
# else:
# return 10000
# def _check_integrity(self):
# import hashlib
# 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 os.path.isfile(fpath):
# return False
# md5c = hashlib.md5(open(fpath, 'rb').read()).hexdigest()
# if md5c != md5:
# return False
# return True
# def download(self):
# from six.moves import urllib
# import tarfile
# import hashlib
# root = self.root
# fpath = os.path.join(root, self.filename)
# try:
# os.makedirs(root)
# except OSError as e:
# if e.errno == errno.EEXIST:
# pass
# else:
# raise
# if self._check_integrity():
# print('Files already downloaded and verified')
# return
# # downloads file
# if os.path.isfile(fpath) and \
# hashlib.md5(open(fpath, 'rb').read()).hexdigest() == self.tgz_md5:
# print('Using downloaded file: ' + fpath)
# else:
# print('Downloading ' + self.url + ' to ' + fpath)
# urllib.request.urlretrieve(self.url, fpath)
# # extract file
# cwd = os.getcwd()
# print('Extracting tar file')
# tar = tarfile.open(fpath, "r:gz")
# os.chdir(root)
# tar.extractall()
# tar.close()
# os.chdir(cwd)
# print('Done!')
# class CIFAR100(CIFAR10):
# base_folder = 'cifar-100-python'
# url = "http://www.cs.toronto.edu/~kriz/cifar-100-python.tar.gz"
# filename = "cifar-100-python.tar.gz"
# tgz_md5 = 'eb9058c3a382ffc7106e4002c42a8d85'
# train_list = [
# ['train', '16019d7e3df5f24257cddd939b257f8d'],
# ]
# test_list = [
# ['test', 'f0ef6b0ae62326f3e7ffdfab6717acfc'],
# ]
from PIL import Image
import os
import os.path
import numpy as np
import pickle
import logging
from torchvision.datasets import VisionDataset
from torchvision.datasets.utils import check_integrity, download_and_extract_archive
class CIFAR10(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'
even_odd_indices_filename = ['even_cifar_list', 'odd_cifar_list']
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, train=True, transform=None, target_transform=None,
download=False, even_odd = -1, random_split_version = 2):
super(CIFAR10, self).__init__(root, transform=transform,
target_transform=target_transform)
self.train = train # training set or test set
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 = []
logger = logging.getLogger()
# 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:
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'])
print(len(self.data))
self.data = np.vstack(self.data).reshape(-1, 3, 32, 32)
print(self.data.shape)
self.data = self.data.transpose((0, 2, 3, 1)) # convert to HWC
print(self.data.shape)
if even_odd >=0 :
even_odd = even_odd%2
select_indices_filepath = os.path.join(self.root, self.base_folder, self.even_odd_indices_filename[even_odd] + '_v'+ str(random_split_version))
with open (select_indices_filepath, 'rb') as fp:
select_indices = pickle.load(fp)
# self.data = self.data[even_odd::2]
# self.targets = self.targets[even_odd::2]
# select_indices = list(range(len(self.data)))
# np.random.shuffle(select_indices)
# select_indices = select_indices[0:int(len(select_indices)/2)]
self.data = self.data[select_indices]
self.targets = [self.targets[i] for i in select_indices]
logger.info("filtering even odd=%d for cifar dataset with remaning shape %s from filepath %s" %(even_odd, self.data.shape, select_indices_filepath))
logger.info(select_indices[0:5])
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:
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 = self.data[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 index < 10:
# img.save('selection_model/for_view/cifar10/'+str(index)+'.png')
if self.transform is not None:
img = self.transform(img)
if self.target_transform is not None:
target = self.target_transform(target)
# print(img.shape)
return img, target, index
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 CIFAR100(CIFAR10):
"""`CIFAR100 <https://www.cs.toronto.edu/~kriz/cifar.html>`_ Dataset.
This is a subclass of the `CIFAR10` Dataset.
"""
base_folder = 'cifar-100-python'
url = "https://www.cs.toronto.edu/~kriz/cifar-100-python.tar.gz"
filename = "cifar-100-python.tar.gz"
tgz_md5 = 'eb9058c3a382ffc7106e4002c42a8d85'
train_list = [
['train', '16019d7e3df5f24257cddd939b257f8d'],
]
test_list = [
['test', 'f0ef6b0ae62326f3e7ffdfab6717acfc'],
]
meta = {
'filename': 'meta',
'key': 'fine_label_names',
'md5': '7973b15100ade9c7d40fb424638fde48',
}