forked from thuml/TCL
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathdata.py
188 lines (170 loc) · 6.84 KB
/
data.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
#from __future__ import print_function, division
import torch
import numpy as np
from sklearn.preprocessing import StandardScaler
import random
from PIL import Image
import torch.utils.data as data
import os
import os.path
class TextData():
def __init__(self, text_file, label_file, source_batch_size=64, target_batch_size=64, val_batch_size=4):
all_text = np.load(text_file)
self.source_text = all_text[0:92664, :]
self.target_text = all_text[92664:, :]
self.val_text = all_text[0:92664, :]
all_label = np.load(label_file)
self.label_source = all_label[0:92664, :]
self.label_target = all_label[92664:, :]
self.label_val = all_label[0:92664, :]
self.scaler = StandardScaler().fit(all_text)
self.source_id = 0
self.target_id = 0
self.val_id = 0
self.source_size = self.source_text.shape[0]
self.target_size = self.target_text.shape[0]
self.val_size = self.val_text.shape[0]
self.source_batch_size = source_batch_size
self.target_batch_size = target_batch_size
self.val_batch_size = val_batch_size
self.source_list = random.sample(range(self.source_size), self.source_size)
self.target_list = random.sample(range(self.target_size), self.target_size)
self.val_list = random.sample(range(self.val_size), self.val_size)
self.feature_dim = self.source_text.shape[1]
def next_batch(self, train=True):
data = []
label = []
if train:
remaining = self.source_size - self.source_id
start = self.source_id
if remaining <= self.source_batch_size:
for i in self.source_list[start:]:
data.append(self.source_text[i, :])
label.append(self.label_source[i, :])
self.source_id += 1
self.source_list = random.sample(range(self.source_size), self.source_size)
self.source_id = 0
for i in self.source_list[0:(self.source_batch_size-remaining)]:
data.append(self.source_text[i, :])
label.append(self.label_source[i, :])
self.source_id += 1
else:
for i in self.source_list[start:start+self.source_batch_size]:
data.append(self.source_text[i, :])
label.append(self.label_source[i, :])
self.source_id += 1
remaining = self.target_size - self.target_id
start = self.target_id
if remaining <= self.target_batch_size:
for i in self.target_list[start:]:
data.append(self.target_text[i, :])
# no target label
#label.append(self.label_target[i, :])
self.target_id += 1
self.target_list = random.sample(range(self.target_size), self.target_size)
self.target_id = 0
for i in self.target_list[0:self.target_batch_size-remaining]:
data.append(self.target_text[i, :])
#label.append(self.label_target[i, :])
self.target_id += 1
else:
for i in self.target_list[start:start+self.target_batch_size]:
data.append(self.target_text[i, :])
#label.append(self.label_target[i, :])
self.target_id += 1
else:
remaining = self.val_size - self.val_id
start = self.val_id
if remaining <= self.val_batch_size:
for i in self.val_list[start:]:
data.append(self.val_text[i, :])
label.append(self.label_val[i, :])
self.val_id += 1
self.val_list = random.sample(range(self.val_size), self.val_size)
self.val_id = 0
for i in self.val_list[0:self.val_batch_size-remaining]:
data.append(self.val_text[i, :])
label.append(self.label_val[i, :])
self.val_id += 1
else:
for i in self.val_list[start:start+self.val_batch_size]:
data.append(self.val_text[i, :])
label.append(self.label_val[i, :])
self.val_id += 1
data = self.scaler.transform(np.vstack(data))
label = np.aavstack(label)
return torch.from_numpy(data).float(),torch.from_numpy(label).float()
def make_dataset(image_list, labels):
if labels:
len_ = len(image_list)
images = [(image_list[i].strip(), labels[i, :]) for i in xrange(len_)]
else:
if len(image_list[0].split()) > 2:
images = [(val.split()[0], np.array([int(la) for la in val.split()[1:]])) for val in image_list]
else:
images = [(val.split()[0], int(val.split()[1])) for val in image_list]
return images
def pil_loader(path):
# open path as file to avoid ResourceWarning (https://github.com/python-pillow/Pillow/issues/835)
with open(path, 'rb') as f:
with Image.open(f) as img:
return img.convert('RGB')
def accimage_loader(path):
import accimage
try:
return accimage.Image(path)
except IOError:
# Potentially a decoding problem, fall back to PIL.Image
return pil_loader(path)
def default_loader(path):
#from torchvision import get_image_backend
#if get_image_backend() == 'accimage':
# return accimage_loader(path)
#else:
return pil_loader(path)
class ImageList(object):
"""A generic data loader where the images are arranged in this way: ::
root/dog/xxx.png
root/dog/xxy.png
root/dog/xxz.png
root/cat/123.png
root/cat/nsdf3.png
root/cat/asd932_.png
Args:
root (string): Root directory path.
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.
loader (callable, optional): A function to load an image given its path.
Attributes:
classes (list): List of the class names.
class_to_idx (dict): Dict with items (class_name, class_index).
imgs (list): List of (image path, class_index) tuples
"""
def __init__(self, image_list, labels=None, transform=None, target_transform=None,
loader=default_loader):
imgs = make_dataset(image_list, labels)
if len(imgs) == 0:
raise(RuntimeError("Found 0 images in subfolders of: " + root + "\n"
"Supported image extensions are: " + ",".join(IMG_EXTENSIONS)))
self.imgs = imgs
self.transform = transform
self.target_transform = target_transform
self.loader = loader
def __getitem__(self, index):
"""
Args:
index (int): Index
Returns:
tuple: (image, target) where target is class_index of the target class.
"""
path, target = self.imgs[index]
img = self.loader(path)
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.imgs)