-
Notifications
You must be signed in to change notification settings - Fork 1
/
data_loader.py
190 lines (166 loc) · 6.29 KB
/
data_loader.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
"""
Create train, valid, test iterators for CIFAR-10 [1].
Easily extended to MNIST, CIFAR-100 and Imagenet.
[1]: https://discuss.pytorch.org/t/feedback-on-pytorch-for-kaggle-competitions/2252/4
"""
import numpy as np
#from utils import plot_images
from torchvision import datasets
from torchvision import transforms
from torch.utils.data.sampler import SubsetRandomSampler
import torch.utils.data as tdata
import torchvision
def get_train_valid_loader(data_dir,
batch_size,
augment,
random_seed,
valid_size=0.2,
shuffle=True,
show_sample=False,
num_workers=4,
pin_memory=False):
"""
Utility function for loading and returning train and valid
multi-process iterators over the CIFAR-10 dataset. A sample
9x9 grid of the images can be optionally displayed.
If using CUDA, num_workers should be set to 1 and pin_memory to True.
Params
------
- data_dir: path directory to the dataset.
- batch_size: how many samples per batch to load.
- augment: whether to apply the data augmentation scheme
mentioned in the paper. Only applied on the train split.
- random_seed: fix seed for reproducibility.
- valid_size: percentage split of the training set used for
the validation set. Should be a float in the range [0, 1].
- shuffle: whether to shuffle the train/validation indices.
- show_sample: plot 9x9 sample grid of the dataset.
- num_workers: number of subprocesses to use when loading the dataset.
- pin_memory: whether to copy tensors into CUDA pinned memory. Set it to
True if using GPU.
Returns
-------
- train_loader: training set iterator.
- valid_loader: validation set iterator.
"""
error_msg = "[!] valid_size should be in the range [0, 1]."
assert ((valid_size >= 0) and (valid_size <= 1)), error_msg
#cifar10
# normalize = transforms.Normalize(
# mean=[0.4914, 0.4822, 0.4465],
# std=[0.2023, 0.1994, 0.2010],
# )
#cinic10
normalize = transforms.Normalize(
mean=[0.47889522, 0.47227842, 0.43047404],
std=[0.24205776, 0.23828046, 0.25874835],
)
# define transforms
valid_transform = transforms.Compose([
transforms.ToTensor(),
normalize,
])
if augment:
train_transform = transforms.Compose([
transforms.RandomCrop(32, padding=4),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
normalize,
])
else:
train_transform = transforms.Compose([
transforms.ToTensor(),
normalize,
])
# load the dataset
#cifar10
# train_dataset = datasets.CIFAR10(
# root=data_dir, train=True,
# download=True, transform=train_transform,
# )
# valid_dataset = datasets.CIFAR10(
# root=data_dir, train=True,
# download=True, transform=valid_transform,
# )
#cinic10
train_dataset = torchvision.datasets.ImageFolder(
root=data_dir + '/train', transform=train_transform,
)
valid_dataset = torchvision.datasets.ImageFolder(
root=data_dir + '/valid', transform=valid_transform,
)
num_train = len(train_dataset)
indices = list(range(num_train))
split = int(np.floor(valid_size * num_train))
if shuffle:
#np.random.seed(random_seed)
np.random.shuffle(indices)
train_idx, valid_idx = indices[split:], indices[:split]
train_sampler = SubsetRandomSampler(train_idx)
valid_sampler = SubsetRandomSampler(valid_idx)
train_loader = tdata.DataLoader(
train_dataset, batch_size=batch_size, sampler=train_sampler,
num_workers=num_workers, pin_memory=pin_memory,
)
valid_loader = tdata.DataLoader(
valid_dataset, batch_size=batch_size, sampler=valid_sampler,
num_workers=num_workers, pin_memory=pin_memory,
)
# visualize some images
# if show_sample:
# sample_loader = torch.utils.data.DataLoader(
# train_dataset, batch_size=9, shuffle=shuffle,
# num_workers=num_workers, pin_memory=pin_memory,
# )
# data_iter = iter(sample_loader)
# images, labels = data_iter.next()
# X = images.numpy().transpose([0, 2, 3, 1])
# plot_images(X, labels)
return (train_loader, valid_loader)
def get_test_loader(data_dir,
batch_size,
shuffle=True,
num_workers=4,
pin_memory=False):
"""
Utility function for loading and returning a multi-process
test iterator over the CIFAR-10 dataset.
If using CUDA, num_workers should be set to 1 and pin_memory to True.
Params
------
- data_dir: path directory to the dataset.
- batch_size: how many samples per batch to load.
- shuffle: whether to shuffle the dataset after every epoch.
- num_workers: number of subprocesses to use when loading the dataset.
- pin_memory: whether to copy tensors into CUDA pinned memory. Set it to
True if using GPU.
Returns
-------
- data_loader: test set iterator.
"""
normalize = transforms.Normalize(
mean=[0.47889522, 0.47227842, 0.43047404],
std=[0.24205776, 0.23828046, 0.25874835],
)
# define transform
transform = transforms.Compose([
transforms.ToTensor(),
normalize,
])
# dataset = datasets.CIFAR10(
# root=data_dir, train=False,
# download=True, transform=transform,
# )
# data_loader = tdata.DataLoader(
# dataset, batch_size=batch_size, shuffle=shuffle,
# num_workers=num_workers, pin_memory=pin_memory,
# )
dataset = torchvision.datasets.ImageFolder(
root=data_dir + '/test', transform=transform,
)
data_loader = tdata.DataLoader(
dataset, batch_size=batch_size, shuffle=shuffle,
num_workers=num_workers, pin_memory=pin_memory,
)
return data_loader
trainloader, validate_loader = get_train_valid_loader('/home/user/Documents/ea-cnn/DS_10283_3192/CINIC-10', batch_size=128, augment=True, valid_size=0.1, shuffle=True, random_seed=2312390, show_sample=False, num_workers=1, pin_memory=True)