-
Notifications
You must be signed in to change notification settings - Fork 0
/
prepare_without_ddjt_yx_tg.py
162 lines (144 loc) · 6.26 KB
/
prepare_without_ddjt_yx_tg.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 xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
import random
from shutil import copyfile
#name of the classes
classes = ['cysb_qyb', 'cysb_sgz', 'SF6ylb', 'drq', 'ecjxh', 'drqgd','cysb_lqq', 'cysb_qtjdq', 'xldlb', 'sly_dmyw', 'ywj', 'ywb', 'jdyxx', 'fhz_f', 'bmwh', 'xmbhzc', 'pzq', 'jyh', 'ywc', 'cysb_cyg', 'bjzc']
#name of the directories
data_space_dir_name = "data"
work_space_dir_name = "缺陷识别raw/设备部件识别"
image_dir_name = "images"
annotation_dir_name = "labels"
yolo_labels_dir_name = "YOLOLabels"
yolov5_images_dir_name = "缺陷识别yolo/设备部件识别_without_ddjt_yx_tg/images"
yolov5_labels_dir_name = "缺陷识别yolo/设备部件识别_without_ddjt_yx_tg/labels"
yolov5_images_train_dir_name = "train"
yolov5_images_test_dir_name = "val"
yolov5_labels_train_dir_name = "train"
yolov5_labels_test_dir_name = "val"
#ratio of train and test dataset
TRAIN_RATIO = 80
def clear_hidden_files(path):#clear hidden files
dir_list = os.listdir(path)
for i in dir_list:
abspath = os.path.join(os.path.abspath(path), i)
if os.path.isfile(abspath):
if i.startswith("._"):
os.remove(abspath)
else:
clear_hidden_files(abspath)
#make directories
wd = os.getcwd()
data_base_dir = os.path.join(wd, data_space_dir_name)
if not os.path.isdir(data_base_dir):
os.mkdir(data_base_dir)
work_space_dir = os.path.join(data_base_dir, work_space_dir_name)
if not os.path.isdir(work_space_dir):
os.mkdir(work_space_dir)
annotation_dir = os.path.join(work_space_dir, annotation_dir_name)
if not os.path.isdir(annotation_dir):
os.mkdir(annotation_dir)
clear_hidden_files(annotation_dir)
image_dir = os.path.join(work_space_dir, image_dir_name)
if not os.path.isdir(image_dir):
os.mkdir(image_dir)
clear_hidden_files(image_dir)
yolo_labels_dir = os.path.join(work_space_dir, yolo_labels_dir_name)
if not os.path.isdir(yolo_labels_dir):
os.mkdir(yolo_labels_dir)
clear_hidden_files(yolo_labels_dir)
yolov5_images_dir = os.path.join(data_base_dir, yolov5_images_dir_name)
if not os.path.isdir(yolov5_images_dir):
os.mkdir(yolov5_images_dir)
clear_hidden_files(yolov5_images_dir)
yolov5_labels_dir = os.path.join(data_base_dir, yolov5_labels_dir_name)
if not os.path.isdir(yolov5_labels_dir):
os.mkdir(yolov5_labels_dir)
clear_hidden_files(yolov5_labels_dir)
yolov5_images_train_dir = os.path.join(yolov5_images_dir, yolov5_images_train_dir_name)
if not os.path.isdir(yolov5_images_train_dir):
os.mkdir(yolov5_images_train_dir)
clear_hidden_files(yolov5_images_train_dir)
yolov5_images_test_dir = os.path.join(yolov5_images_dir, yolov5_images_test_dir_name)
if not os.path.isdir(yolov5_images_test_dir):
os.mkdir(yolov5_images_test_dir)
clear_hidden_files(yolov5_images_test_dir)
yolov5_labels_train_dir = os.path.join(yolov5_labels_dir, yolov5_labels_train_dir_name)
if not os.path.isdir(yolov5_labels_train_dir):
os.mkdir(yolov5_labels_train_dir)
clear_hidden_files(yolov5_labels_train_dir)
yolov5_labels_test_dir = os.path.join(yolov5_labels_dir, yolov5_labels_test_dir_name)
if not os.path.isdir(yolov5_labels_test_dir):
os.mkdir(yolov5_labels_test_dir)
clear_hidden_files(yolov5_labels_test_dir)
def convert(size, box):#convert coord from xml to yolo txt format
dw = 1./size[0]
dh = 1./size[1]
x = (box[0] + box[1])/2.0
y = (box[2] + box[3])/2.0
w = box[1] - box[0]
h = box[3] - box[2]
x = x*dw
w = w*dw
y = y*dh
h = h*dh
return (x,y,w,h)
def convert_annotation(image_id):#convert annotation from xml to yolo txt format
in_file = open(os.path.join(annotation_dir,'%s.xml') %image_id)
out_file = open(os.path.join(yolo_labels_dir,'%s.txt') %image_id, 'w')
tree=ET.parse(in_file)
root = tree.getroot()
size = root.find('size')
w = int(size.find('width').text)
h = int(size.find('height').text)
for obj in root.iter('object'):
difficult = obj.find('difficult').text
cls = obj.find('name').text
if cls not in classes or int(difficult) == 1:
continue
cls_id = classes.index(cls)
xmlbox = obj.find('bndbox')
b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text))
bb = convert((w,h), b)
out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
in_file.close()
out_file.close()
train_file = open(os.path.join(wd, "data/yolov7_train.txt"), 'w')
test_file = open(os.path.join(wd, "data/yolov7_val.txt"), 'w')
train_file.close()
test_file.close()
train_file = open(os.path.join(wd, "data/yolov7_train.txt"), 'a')
test_file = open(os.path.join(wd, "data/yolov7_val.txt"), 'a')
list_imgs = os.listdir(image_dir) # list image files
prob = random.randint(1, 100)
print("Probability: %d" % prob)
for i in range(0,len(list_imgs)):
path = os.path.join(image_dir,list_imgs[i])
if os.path.isfile(path):
image_path = path
voc_path = list_imgs[i]
(nameWithoutExtention, extention) = os.path.splitext(os.path.basename(image_path))
(voc_nameWithoutExtention, voc_extention) = os.path.splitext(os.path.basename(voc_path))
annotation_name = nameWithoutExtention + '.xml'
annotation_path = os.path.join(annotation_dir, annotation_name)
label_name = nameWithoutExtention + '.txt'
label_path = os.path.join(yolo_labels_dir, label_name)
prob = random.randint(1, 100)
print("Probability: %d" % prob)
if(prob < TRAIN_RATIO): # train dataset
if os.path.exists(annotation_path):
train_file.write(image_path + '\n')
convert_annotation(nameWithoutExtention) # convert label
copyfile(image_path, os.path.join(yolov5_images_train_dir,voc_path))
copyfile(label_path, os.path.join(yolov5_labels_train_dir,label_name))
else: # test dataset
if os.path.exists(annotation_path):
test_file.write(image_path + '\n')
convert_annotation(nameWithoutExtention) # convert label
copyfile(image_path, os.path.join(yolov5_images_test_dir,voc_path))
copyfile(label_path, os.path.join(yolov5_labels_test_dir,label_name))
train_file.close()
test_file.close()