-
Notifications
You must be signed in to change notification settings - Fork 7
/
dataloaders.py
163 lines (133 loc) · 6.78 KB
/
dataloaders.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
import torch
from torchvision import datasets, transforms
def minst(args):
train_loader = torch.utils.data.DataLoader(
datasets.MNIST('./data', train=True, download=True,
transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])),
batch_size=args.batch_size*args.num_users, shuffle=True,)
test_loader = torch.utils.data.DataLoader(
datasets.MNIST('./data', train=False, transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])),
batch_size=args.test_batch_size, shuffle=True,)
return train_loader, test_loader
def cifar10(args):
transform_train = transforms.Compose([
transforms.RandomCrop(32, padding=4), # 先四周填充0,在吧图像随机裁剪成32*32
transforms.RandomHorizontalFlip(), # 图像一半的概率翻转,一半的概率不翻转
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465),
(0.2023, 0.1994, 0.2010)), # R,G,B每层的归一化用到的均值和方差
])
transform_test = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465),
(0.2023, 0.1994, 0.2010)),
])
trainset = datasets.CIFAR10(
root='./data', train=True, download=True, transform=transform_train) # 训练数据集
train_loader = torch.utils.data.DataLoader(
trainset, batch_size=args.batch_size*args.num_users, shuffle=True, num_workers=2) # 生成一个个batch进行批训练,组成batch的时候顺序打乱取
testset = datasets.CIFAR10(
root='./data', train=False, download=True, transform=transform_test)
test_loader = torch.utils.data.DataLoader(
testset, args.test_batch_size, shuffle=False, num_workers=2)
return train_loader, test_loader
def cifar100(args):
transform_train = transforms.Compose([
transforms.RandomCrop(32, padding=4), # 先四周填充0,在吧图像随机裁剪成32*32
transforms.RandomHorizontalFlip(), # 图像一半的概率翻转,一半的概率不翻转
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465),
(0.2023, 0.1994, 0.2010)), # R,G,B每层的归一化用到的均值和方差
])
transform_test = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465),
(0.2023, 0.1994, 0.2010)),
])
trainset = datasets.CIFAR100(
root='./data', train=True, download=True, transform=transform_train) # 训练数据集
train_loader = torch.utils.data.DataLoader(
trainset, batch_size=args.batch_size*args.num_users, shuffle=True, num_workers=2) # 生成一个个batch进行批训练,组成batch的时候顺序打乱取
testset = datasets.CIFAR100(
root='./data', train=False, download=True, transform=transform_test)
test_loader = torch.utils.data.DataLoader(
testset, args.test_batch_size, shuffle=False, num_workers=2)
return train_loader, test_loader
def stl10(args):
transform_train = transforms.Compose([
transforms.RandomCrop(96, padding=4), # 先四周填充0,在吧图像随机裁剪成32*32
transforms.RandomHorizontalFlip(), # 图像一半的概率翻转,一半的概率不翻转
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465),
(0.2023, 0.1994, 0.2010)), # R,G,B每层的归一化用到的均值和方差
])
transform_test = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465),
(0.2023, 0.1994, 0.2010)),
])
trainset = datasets.STL10(
root='./data', split='train', download=True, transform=transform_train) # 训练数据集
train_loader = torch.utils.data.DataLoader(
trainset, batch_size=args.batch_size*args.num_users, shuffle=True, num_workers=2) # 生成一个个batch进行批训练,组成batch的时候顺序打乱取
testset = datasets.STL10(
root='./data', split='test', download=True, transform=transform_test)
test_loader = torch.utils.data.DataLoader(
testset, args.test_batch_size, shuffle=False, num_workers=2)
return train_loader, test_loader
def svhn(args):
transform_train = transforms.Compose([
transforms.RandomCrop(32, padding=4), # 先四周填充0,在吧图像随机裁剪成32*32
transforms.RandomHorizontalFlip(), # 图像一半的概率翻转,一半的概率不翻转
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465),
(0.2023, 0.1994, 0.2010)), # R,G,B每层的归一化用到的均值和方差
])
transform_test = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465),
(0.2023, 0.1994, 0.2010)),
])
trainset = datasets.SVHN(
root='./data', split='train', download=True, transform=transform_train) # 训练数据集
train_loader = torch.utils.data.DataLoader(
trainset, batch_size=args.batch_size*args.num_users, shuffle=True, num_workers=2) # 生成一个个batch进行批训练,组成batch的时候顺序打乱取
testset = datasets.SVHN(
root='./data', split='test', download=True, transform=transform_test)
test_loader = torch.utils.data.DataLoader(
testset, args.test_batch_size, shuffle=False, num_workers=2)
return train_loader, test_loader
def tinyimgnet(args):
traindir = './tinyimgnet/train'
testdir = './tinyimgnet/val'
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
train_dataset = datasets.ImageFolder(
traindir,
transforms.Compose([
transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
normalize,
])
)
train_sampler = None
train_loader = torch.utils.data.DataLoader(
train_dataset, batch_size=args.batch_size*args.num_users, shuffle=(train_sampler is None),
num_workers=8, pin_memory=True, sampler=train_sampler)
test_loader = torch.utils.data.DataLoader(
datasets.ImageFolder(testdir, transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
normalize,
])),
batch_size=args.test_batch_size, shuffle=False,
num_workers=8, pin_memory=True)
return train_loader, test_loader