-
Notifications
You must be signed in to change notification settings - Fork 6
/
CIFAR100.py
226 lines (194 loc) · 8.27 KB
/
CIFAR100.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
from __future__ import print_function
from PIL import Image
import os
import os.path
import numpy as np
import sys
if sys.version_info[0] == 2:
import cPickle as pickle
else:
import pickle
import torch.utils.data as data
#from torch.utils import download_url, check_integrity
import pdb
class CIFAR10(data.Dataset):
"""`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, train=True,
transform=None, target_transform=None,
download=False, index=None,num_instance_per_class=0):
self.root = os.path.expanduser(root)
self.transform = transform
self.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 = []
# 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.data = self.data/255.
#pdb.set_trace()
self.targets = np.asarray(self.targets)
#index_sort = np.argsort(self.targets)
# Sort label and corresponding data from 0-9
#self.data = self.data[index_sort]
#self.targets=np.asarray(sorted(self.targets))
self.targets = target_transform[self.targets]
if num_instance_per_class==0:
self.data,self.targets = self.RandomPercentage(self.data,self.targets,index)
else:
self.data,self.targets = self.RandomExempalers(self.data,self.targets,index,num_instance_per_class)
self._load_meta()
def RandomPercentage(self, data,targets,index):
data_tmp = []
targets_tmp = []
for i in index:
ind_cl = np.where(i == targets)[0]
if data_tmp==[]:
data_tmp = data[ind_cl]
targets_tmp = targets[ind_cl]
else:
data_tmp = np.vstack((data_tmp,data[ind_cl]))
targets_tmp = np.hstack((targets_tmp,targets[ind_cl]))
return data_tmp,targets_tmp
def RandomExempalers(self, data,targets,index,num):
data_tmp = []
targets_tmp = []
for i in index:
ind_cl = np.where(i == targets)[0][:num]
if data_tmp==[]:
data_tmp = data[ind_cl]
targets_tmp = targets[ind_cl]
else:
data_tmp = np.vstack((data_tmp,data[ind_cl]))
targets_tmp = np.hstack((targets_tmp,targets[ind_cl]))
return data_tmp,targets_tmp
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 = 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 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.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):
# import tarfile
# # if self._check_integrity():
# # print('Files already downloaded and verified')
# # return
# download_url(self.url, self.root, self.filename, self.tgz_md5)
# # extract file
# with tarfile.open(os.path.join(self.root, self.filename), "r:gz") as tar:
# tar.extractall(path=self.root)
def __repr__(self):
fmt_str = 'Dataset ' + self.__class__.__name__ + '\n'
fmt_str += ' Number of datapoints: {}\n'.format(self.__len__())
tmp = 'train' if self.train is True else 'test'
fmt_str += ' Split: {}\n'.format(tmp)
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 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',
}