-
Notifications
You must be signed in to change notification settings - Fork 31
/
dataset.py
173 lines (141 loc) · 6.65 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
from torchvision import transforms
from PIL import Image
import os
import torch
import glob
from torchvision.datasets import MNIST, CIFAR10, FashionMNIST, ImageFolder
import numpy as np
def get_data_transforms(size, isize):
mean_train = [0.485, 0.456, 0.406]
std_train = [0.229, 0.224, 0.225]
data_transforms = transforms.Compose([
transforms.Resize((size, size)),
transforms.ToTensor(),
transforms.CenterCrop(isize),
#transforms.CenterCrop(args.input_size),
transforms.Normalize(mean=mean_train,
std=std_train)])
gt_transforms = transforms.Compose([
transforms.Resize((size, size)),
transforms.CenterCrop(isize),
transforms.ToTensor()])
return data_transforms, gt_transforms
class MVTecDataset(torch.utils.data.Dataset):
def __init__(self, root, transform, gt_transform, phase):
if phase == 'train':
self.img_path = os.path.join(root, 'train')
else:
self.img_path = os.path.join(root, 'test')
self.gt_path = os.path.join(root, 'ground_truth')
self.transform = transform
self.gt_transform = gt_transform
# load dataset
self.img_paths, self.gt_paths, self.labels, self.types = self.load_dataset() # self.labels => good : 0, anomaly : 1
def load_dataset(self):
img_tot_paths = []
gt_tot_paths = []
tot_labels = []
tot_types = []
defect_types = os.listdir(self.img_path)
for defect_type in defect_types:
if defect_type == 'good':
img_paths = glob.glob(os.path.join(self.img_path, defect_type) + "/*.png")
img_tot_paths.extend(img_paths)
gt_tot_paths.extend([0] * len(img_paths))
tot_labels.extend([0] * len(img_paths))
tot_types.extend(['good'] * len(img_paths))
else:
img_paths = glob.glob(os.path.join(self.img_path, defect_type) + "/*.png")
gt_paths = glob.glob(os.path.join(self.gt_path, defect_type) + "/*.png")
img_paths.sort()
gt_paths.sort()
img_tot_paths.extend(img_paths)
gt_tot_paths.extend(gt_paths)
tot_labels.extend([1] * len(img_paths))
tot_types.extend([defect_type] * len(img_paths))
assert len(img_tot_paths) == len(gt_tot_paths), "Something wrong with test and ground truth pair!"
return img_tot_paths, gt_tot_paths, tot_labels, tot_types
def __len__(self):
return len(self.img_paths)
def __getitem__(self, idx):
img_path, gt, label, img_type = self.img_paths[idx], self.gt_paths[idx], self.labels[idx], self.types[idx]
img = Image.open(img_path).convert('RGB')
img = self.transform(img)
if gt == 0:
gt = torch.zeros([1, img.size()[-2], img.size()[-2]])
else:
gt = Image.open(gt)
gt = self.gt_transform(gt)
assert img.size()[1:] == gt.size()[1:], "image.size != gt.size !!!"
return img, gt, label, img_type
def load_data(dataset_name='mnist',normal_class=0,batch_size='16'):
if dataset_name == 'cifar10':
img_transform = transforms.Compose([
transforms.Resize((32, 32)),
#transforms.CenterCrop(28),
transforms.ToTensor(),
transforms.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225))
])
os.makedirs("./Dataset/CIFAR10/train", exist_ok=True)
dataset = CIFAR10('./Dataset/CIFAR10/train', train=True, download=True, transform=img_transform)
print("Cifar10 DataLoader Called...")
print("All Train Data: ", dataset.data.shape)
dataset.data = dataset.data[np.array(dataset.targets) == normal_class]
dataset.targets = [normal_class] * dataset.data.shape[0]
print("Normal Train Data: ", dataset.data.shape)
os.makedirs("./Dataset/CIFAR10/test", exist_ok=True)
test_set = CIFAR10("./Dataset/CIFAR10/test", train=False, download=True, transform=img_transform)
print("Test Train Data:", test_set.data.shape)
elif dataset_name == 'mnist':
img_transform = transforms.Compose([
transforms.Resize((32, 32)),
transforms.ToTensor()
])
os.makedirs("./Dataset/MNIST/train", exist_ok=True)
dataset = MNIST('./Dataset/MNIST/train', train=True, download=True, transform=img_transform)
print("MNIST DataLoader Called...")
print("All Train Data: ", dataset.data.shape)
dataset.data = dataset.data[np.array(dataset.targets) == normal_class]
dataset.targets = [normal_class] * dataset.data.shape[0]
print("Normal Train Data: ", dataset.data.shape)
os.makedirs("./Dataset/MNIST/test", exist_ok=True)
test_set = MNIST("./Dataset/MNIST/test", train=False, download=True, transform=img_transform)
print("Test Train Data:", test_set.data.shape)
elif dataset_name == 'fashionmnist':
img_transform = transforms.Compose([
transforms.Resize((32, 32)),
transforms.ToTensor()
])
os.makedirs("./Dataset/FashionMNIST/train", exist_ok=True)
dataset = FashionMNIST('./Dataset/FashionMNIST/train', train=True, download=True, transform=img_transform)
print("FashionMNIST DataLoader Called...")
print("All Train Data: ", dataset.data.shape)
dataset.data = dataset.data[np.array(dataset.targets) == normal_class]
dataset.targets = [normal_class] * dataset.data.shape[0]
print("Normal Train Data: ", dataset.data.shape)
os.makedirs("./Dataset/FashionMNIST/test", exist_ok=True)
test_set = FashionMNIST("./Dataset/FashionMNIST/test", train=False, download=True, transform=img_transform)
print("Test Train Data:", test_set.data.shape)
elif dataset_name == 'retina':
data_path = 'Dataset/OCT2017/train'
orig_transform = transforms.Compose([
transforms.Resize([128, 128]),
transforms.ToTensor()
])
dataset = ImageFolder(root=data_path, transform=orig_transform)
test_data_path = 'Dataset/OCT2017/test'
test_set = ImageFolder(root=test_data_path, transform=orig_transform)
else:
raise Exception(
"You enter {} as dataset, which is not a valid dataset for this repository!".format(dataset_name))
train_dataloader = torch.utils.data.DataLoader(
dataset,
batch_size=batch_size,
shuffle=True,
)
test_dataloader = torch.utils.data.DataLoader(
test_set,
batch_size=1,
shuffle=False,
)
return train_dataloader, test_dataloader