forked from tbmoon/facenet
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathdata_loader.py
137 lines (102 loc) · 5.49 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
import os
import numpy as np
import pandas as pd
from skimage import io
import torch
from torchvision import transforms
from torch.utils.data import Dataset
class TripletFaceDataset(Dataset):
def __init__(self, root_dir, csv_name, num_triplets, transform = None):
self.root_dir = root_dir
self.df = pd.read_csv(csv_name)
self.num_triplets = num_triplets
self.transform = transform
self.training_triplets = self.generate_triplets(self.df, self.num_triplets)
@staticmethod
def generate_triplets(df, num_triplets):
def make_dictionary_for_face_class(df):
'''
- face_classes = {'class0': [class0_id0, ...], 'class1': [class1_id0, ...], ...}
'''
face_classes = dict()
for idx, label in enumerate(df['class']):
if label not in face_classes:
face_classes[label] = []
face_classes[label].append(df.iloc[idx, 0])
return face_classes
triplets = []
classes = df['class'].unique()
face_classes = make_dictionary_for_face_class(df)
for _ in range(num_triplets):
'''
- randomly choose anchor, positive and negative images for triplet loss
- anchor and positive images in pos_class
- negative image in neg_class
- at least, two images needed for anchor and positive images in pos_class
- negative image should have different class as anchor and positive images by definition
'''
pos_class = np.random.choice(classes)
neg_class = np.random.choice(classes)
while len(face_classes[pos_class]) < 2:
pos_class = np.random.choice(classes)
while pos_class == neg_class:
neg_class = np.random.choice(classes)
pos_name = df.loc[df['class'] == pos_class, 'name'].values[0]
neg_name = df.loc[df['class'] == neg_class, 'name'].values[0]
if len(face_classes[pos_class]) == 2:
ianc, ipos = np.random.choice(2, size = 2, replace = False)
else:
ianc = np.random.randint(0, len(face_classes[pos_class]))
ipos = np.random.randint(0, len(face_classes[pos_class]))
while ianc == ipos:
ipos = np.random.randint(0, len(face_classes[pos_class]))
ineg = np.random.randint(0, len(face_classes[neg_class]))
triplets.append([face_classes[pos_class][ianc], face_classes[pos_class][ipos], face_classes[neg_class][ineg],
pos_class, neg_class, pos_name, neg_name])
return triplets
def __getitem__(self, idx):
anc_id, pos_id, neg_id, pos_class, neg_class, pos_name, neg_name = self.training_triplets[idx]
anc_img = os.path.join(self.root_dir, str(pos_name), str(anc_id) + '.png')
pos_img = os.path.join(self.root_dir, str(pos_name), str(pos_id) + '.png')
neg_img = os.path.join(self.root_dir, str(neg_name), str(neg_id) + '.png')
anc_img = io.imread(anc_img)
pos_img = io.imread(pos_img)
neg_img = io.imread(neg_img)
pos_class = torch.from_numpy(np.array([pos_class]).astype('long'))
neg_class = torch.from_numpy(np.array([neg_class]).astype('long'))
sample = {'anc_img': anc_img, 'pos_img': pos_img, 'neg_img': neg_img, 'pos_class': pos_class, 'neg_class': neg_class}
if self.transform:
sample['anc_img'] = self.transform(sample['anc_img'])
sample['pos_img'] = self.transform(sample['pos_img'])
sample['neg_img'] = self.transform(sample['neg_img'])
return sample
def __len__(self):
return len(self.training_triplets)
def get_dataloader(train_root_dir, valid_root_dir,
train_csv_name, valid_csv_name,
num_train_triplets, num_valid_triplets,
batch_size, num_workers):
data_transforms = {
'train': transforms.Compose([
transforms.ToPILImage(),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize(mean = [0.5, 0.5, 0.5], std = [0.5, 0.5, 0.5])]),
'valid': transforms.Compose([
transforms.ToPILImage(),
transforms.ToTensor(),
transforms.Normalize(mean = [0.5, 0.5, 0.5], std = [0.5, 0.5, 0.5])])}
face_dataset = {
'train' : TripletFaceDataset(root_dir = train_root_dir,
csv_name = train_csv_name,
num_triplets = num_train_triplets,
transform = data_transforms['train']),
'valid' : TripletFaceDataset(root_dir = valid_root_dir,
csv_name = valid_csv_name,
num_triplets = num_valid_triplets,
transform = data_transforms['valid'])}
dataloaders = {
x: torch.utils.data.DataLoader(face_dataset[x], batch_size = batch_size, shuffle = False, num_workers = num_workers)
for x in ['train', 'valid']}
data_size = {x: len(face_dataset[x]) for x in ['train', 'valid']}
return dataloaders, data_size