-
Notifications
You must be signed in to change notification settings - Fork 0
/
dataset.py
235 lines (185 loc) · 7.86 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
import os.path
import albumentations
import pickle
import torch.utils.data as data
import torchvision.transforms as transforms
from PIL import Image
import numpy as np
import torch.utils.data as data
from PIL import Image
import numpy as np
import os.path
import torchvision
from torchvision.datasets import MNIST, EMNIST, CIFAR10, CIFAR100, SVHN, FashionMNIST, ImageFolder, DatasetFolder, utils
from torchvision.datasets.utils import download_file_from_google_drive, check_integrity
import os
import os.path
import pandas as pd
import torch
from typing import Any, Callable, Optional, Tuple
class CIFAR10(data.Dataset):
def __init__(self,url="./data/cifar-10-batches-py/", train=True,transform=None, target_transform=None,dataidxs=None):
self.dataidxs=dataidxs
self.transform=transform
self.target_transform=target_transform
self.url=url
self.train_list = ["data_batch_1","data_batch_2","data_batch_3","data_batch_4","data_batch_5"]
self.test_list = ["test_batch"]
self.data=[]
self.targets=[]
if train:
for file in self.train_list:
path=self.url+file
with open(path, "rb") as f:
entry = pickle.load(f, encoding="latin1")
self.data.append(entry["data"])
self.targets.extend(entry["labels"])
else:
for file in self.test_list:
path=self.url+file
with open(path, "rb") as f:
entry = pickle.load(f, encoding="latin1")
self.data.append(entry["data"])
self.targets.extend(entry["labels"])
self.data = np.vstack(self.data).reshape(-1, 3, 32, 32)
self.data = self.data.transpose((0, 2, 3, 1))
self.targets=np.array(self.targets)
if self.dataidxs is not None:
self.data = self.data[self.dataidxs]
self.targets = self.targets[self.dataidxs]
def __getitem__(self, index):
img, target = self.data[index], self.targets[index]
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) -> int:
return len(self.data)
class CIFAR100(data.Dataset):
def __init__(self,url="./data/cifar100/", train=True,transform=None, target_transform=None,dataidxs=None):
self.dataidxs = dataidxs
self.transform=transform
self.target_transform=target_transform
self.url=url
self.train_list = ["train"]
self.test_list = ["test"]
self.data=[]
self.targets=[]
if train:
for file in self.train_list:
path=self.url+file
with open(path, "rb") as f:
entry = pickle.load(f, encoding="latin1")
self.data.append(entry["data"])
self.targets.extend(entry["fine_labels"])
else:
for file in self.test_list:
path=self.url+file
with open(path, "rb") as f:
entry = pickle.load(f, encoding="latin1")
self.data.append(entry["data"])
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))
self.targets = np.array(self.targets)
if self.dataidxs is not None:
self.data = self.data[self.dataidxs]
self.targets = self.targets[self.dataidxs]
def __getitem__(self, index):
img, target = self.data[index], self.targets[index]
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) -> int:
return len(self.data)
class FashionMNIST_truncated(data.Dataset):
def __init__(self, dataidxs=None, train=True, transform=None, target_transform=None):
self.dataidxs = dataidxs
self.train = train
self.transform = transform
self.target_transform = target_transform
self.data, self.target = self.__build_truncated_dataset__()
def __build_truncated_dataset__(self):
mnist_dataobj = FashionMNIST("../", self.train, self.transform, self.target_transform, True)
data = mnist_dataobj.data
target = mnist_dataobj.targets
if self.dataidxs is not None:
data = data[self.dataidxs]
target = target[self.dataidxs]
return data, target
def __getitem__(self, index):
img, target = self.data[index], self.target[index]
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
def __len__(self):
return len(self.data)
class MNIST_truncated(data.Dataset):
def __init__(self, dataidxs=None, train=True, transform=None, target_transform=None):
self.dataidxs = dataidxs
self.train = train
self.transform = transform
self.target_transform = target_transform
self.data, self.target = self.__build_truncated_dataset__()
def __build_truncated_dataset__(self):
mnist_dataobj = MNIST("../", self.train, self.transform, self.target_transform, True)
data = mnist_dataobj.data
target = mnist_dataobj.targets
if self.dataidxs is not None:
data = data[self.dataidxs]
target = target[self.dataidxs]
return data, target
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.target[index]
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
def __len__(self):
return len(self.data)
class SVHN_custom(data.Dataset):
def __init__(self, dataidxs=None, train=True, transform=None, target_transform=None):
self.dataidxs = dataidxs
self.train = train
self.transform = transform
self.target_transform = target_transform
self.data, self.target = self.__build_truncated_dataset__()
def __build_truncated_dataset__(self):
if self.train is True:
svhn_dataobj = SVHN("../SVHN", 'train', self.transform, self.target_transform,True)
data = svhn_dataobj.data
target = svhn_dataobj.labels
else:
svhn_dataobj = SVHN("../SVHN", 'test', self.transform, self.target_transform,True)
data = svhn_dataobj.data
target = svhn_dataobj.labels
if self.dataidxs is not None:
data = data[self.dataidxs]
target = target[self.dataidxs]
return data, target
def __getitem__(self, index):
img, target = self.data[index], self.target[index]
img = Image.fromarray(np.transpose(img, (1, 2, 0)))
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)