-
Notifications
You must be signed in to change notification settings - Fork 0
/
cifar10.py
178 lines (154 loc) · 5.63 KB
/
cifar10.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
from __future__ import print_function
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
import torch
import torch.utils.data as data
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.
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 = "http://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'],
]
def __init__(self, root, train=True, download=False):
self.root = os.path.expanduser(root)
self.train = train # training set or test set
# 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):
"""
Args:
index (int): Index
Returns:
tuple: (image, target) where target is index of the target class.
"""
if self.train:
img, target = self.train_data[index], self.train_labels[index]
img = normalize(img)
img = hflip(img)
img = translate(img)
else:
img, target = self.test_data[index], self.test_labels[index]
img = normalize(img)
img = torch.from_numpy(img)
return img, target
def __len__(self):
if self.train:
return 50000
else:
return 10000
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
root = self.root
download_url(self.url, root, self.filename, self.tgz_md5)
# extract file
cwd = os.getcwd()
tar = tarfile.open(os.path.join(root, self.filename), "r:gz")
os.chdir(root)
tar.extractall()
tar.close()
os.chdir(cwd)
def normalize(x):
mean = np.asarray([0.4914, 0.4822, 0.4465], np.float32)
std = np.asarray([0.2023, 0.1994, 0.2010], np.float32)
x = x.astype(np.float32)
x = x / 255
x -= mean.reshape((-1, 1, 1))
x /= std.reshape((-1, 1, 1))
return x
def hflip(x):
if np.random.rand() > 0.5:
x = x[:, :, ::-1]
return x
def translate(x):
new = np.zeros((3, 40, 40), np.float32)
h = np.random.randint(9)
w = np.random.randint(9)
new[:, h:h + 32, w:w + 32] = x
x = new[:, 4:36, 4:36]
return x
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'],
]