prepare_detection_dataset/csv2voc.py at master · spytensor/prepare_detection_dataset · GitHub

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
import os
import numpy as np
import codecs
import pandas as pd
from glob import glob
import cv2
import shutil
from sklearn.model_selection import train_test_split
#1.标签路径
csv_file = "../csv/train_labels.csv"
saved_path = "./VOCdevkit/VOC2007/"                #保存路径
image_save_path = "./JPEGImages/"
image_raw_path = "../csv/images/"
#2.创建要求文件夹
if not os.path.exists(saved_path + "Annotations"):
    os.makedirs(saved_path + "Annotations")
if not os.path.exists(saved_path + "JPEGImages/"):
    os.makedirs(saved_path + "JPEGImages/")
if not os.path.exists(saved_path + "ImageSets/Main/"):
    os.makedirs(saved_path + "ImageSets/Main/")

#3.获取待处理文件
total_csv_annotations = {}
annotations = pd.read_csv(csv_file,header=None).values
for annotation in annotations:
    key = annotation[0].split(os.sep)[-1]
    value = np.array([annotation[1:]])
    if key in total_csv_annotations.keys():
        total_csv_annotations[key] = np.concatenate((total_csv_annotations[key],value),axis=0)
    else:
        total_csv_annotations[key] = value

#4.读取标注信息并写入 xml
for filename,label in total_csv_annotations.items():
    height, width, channels = cv2.imread(image_raw_path + filename).shape
    with codecs.open(saved_path + "Annotations/"+filename.replace(".jpg",".xml"),"w","utf-8") as xml:
        xml.write('<annotation>\n')
        xml.write('\t<folder>' + 'UAV_data' + '</folder>\n')
        xml.write('\t<filename>' + filename + '</filename>\n')
        xml.write('\t<source>\n')
        xml.write('\t\t<database>The UAV autolanding</database>\n')
        xml.write('\t\t<annotation>UAV AutoLanding</annotation>\n')
        xml.write('\t\t<image>flickr</image>\n')
        xml.write('\t\t<flickrid>NULL</flickrid>\n')
        xml.write('\t</source>\n')
        xml.write('\t<owner>\n')
        xml.write('\t\t<flickrid>NULL</flickrid>\n')
        xml.write('\t\t<name>ChaojieZhu</name>\n')
        xml.write('\t</owner>\n')
        xml.write('\t<size>\n')
        xml.write('\t\t<width>'+ str(width) + '</width>\n')
        xml.write('\t\t<height>'+ str(height) + '</height>\n')
        xml.write('\t\t<depth>' + str(channels) + '</depth>\n')
        xml.write('\t</size>\n')
        xml.write('\t\t<segmented>0</segmented>\n')
        if isinstance(label,float):
            ## 空白
            xml.write('</annotation>')
            continue
        for label_detail in label:
            labels = label_detail
            #embed()
            xmin = int(labels[0])
            ymin = int(labels[1])
            xmax = int(labels[2])
            ymax = int(labels[3])
            label_ = labels[-1]
            if xmax <= xmin:
                pass
            elif ymax <= ymin:
                pass
            else:
                xml.write('\t<object>\n')
                xml.write('\t\t<name>'+label_+'</name>\n')
                xml.write('\t\t<pose>Unspecified</pose>\n')
                xml.write('\t\t<truncated>1</truncated>\n')
                xml.write('\t\t<difficult>0</difficult>\n')
                xml.write('\t\t<bndbox>\n')
                xml.write('\t\t\t<xmin>' + str(xmin) + '</xmin>\n')
                xml.write('\t\t\t<ymin>' + str(ymin) + '</ymin>\n')
                xml.write('\t\t\t<xmax>' + str(xmax) + '</xmax>\n')
                xml.write('\t\t\t<ymax>' + str(ymax) + '</ymax>\n')
                xml.write('\t\t</bndbox>\n')
                xml.write('\t</object>\n')
                print(filename,xmin,ymin,xmax,ymax,labels)
        xml.write('</annotation>')


#6.split files for txt
txtsavepath = saved_path + "ImageSets/Main/"
ftrainval = open(txtsavepath+'/trainval.txt', 'w')
ftest = open(txtsavepath+'/test.txt', 'w')
ftrain = open(txtsavepath+'/train.txt', 'w')
fval = open(txtsavepath+'/val.txt', 'w')
total_files = glob(saved_path+"./Annotations/*.xml")
total_files = [os.path.basename(i).split(".xml")[0] for i in total_files]
#test_filepath = ""
for file in total_files:
    ftrainval.write(file + "\n")

# move images to voc JPEGImages folder
for image in glob(image_raw_path+"/*.jpg"):
    shutil.copy(image,saved_path+image_save_path)

train_files,val_files = train_test_split(total_files,test_size=0.15,random_state=42)

for file in train_files:
    ftrain.write(file + "\n")
#val
for file in val_files:
    fval.write(file + "\n")

ftrainval.close()
ftrain.close()
fval.close()
#ftest.close()