DOTA数据集转VOC数据集，模仿DIOR数据集类型_dior-r数据集下载

DOTA文本数据集转XML格式

说明：由于本人比较喜欢DIOR数据集格式，所以仿照DIOR数据集转的相同格式

DOTA数据集下载链接：https://pan.baidu.com/s/1lksAYbogYT3OjTBzNuQuNA
提取码：7vwv

DOIR数据集下载链接：
https://pan.baidu.com/s/1QPALicrLHqhblnGu_EBjlw
提取码：jcpg

代码如下（改了网上的代码，此处贴上链接）

import os
from xml.dom.minidom import Document
from xml.dom.minidom import parse
import xml.dom.minidom
import numpy as np
import csv
import cv2
import string

def WriterXMLFiles(filename,img_name, path, box_list, label_list, w, h, d):

    # dict_box[filename]=json_dict[filename]
    doc = xml.dom.minidom.Document()
    root = doc.createElement('annotation')
    doc.appendChild(root)

    # foldername = doc.createElement("folder")
    # foldername.appendChild(doc.createTextNode("JPEGImages"))
    # root.appendChild(foldername)

    nodeFilename = doc.createElement('filename')
    nodeFilename.appendChild(doc.createTextNode(img_name))
    root.appendChild(nodeFilename)

    # pathname = doc.createElement("path")
    # pathname.appendChild(doc.createTextNode("xxxx"))
    # root.appendChild(pathname)

    sourcename=doc.createElement("source")

    databasename = doc.createElement("database")
    databasename.appendChild(doc.createTextNode("DOTA"))
    sourcename.appendChild(databasename)

    # annotationname = doc.createElement("annotation")
    # annotationname.appendChild(doc.createTextNode("xxx"))
    # sourcename.appendChild(annotationname)

    # imagename = doc.createElement("image")
    # imagename.appendChild(doc.createTextNode("xxx"))
    # sourcename.appendChild(imagename)

    # flickridname = doc.createElement("flickrid")
    # flickridname.appendChild(doc.createTextNode("0"))
    # sourcename.appendChild(flickridname)

    root.appendChild(sourcename)

    nodesize = doc.createElement('size')
    nodewidth = doc.createElement('width')
    nodewidth.appendChild(doc.createTextNode(str(w)))
    nodesize.appendChild(nodewidth)
    nodeheight = doc.createElement('height')
    nodeheight.appendChild(doc.createTextNode(str(h)))
    nodesize.appendChild(nodeheight)
    nodedepth = doc.createElement('depth')
    nodedepth.appendChild(doc.createTextNode(str(d)))
    nodesize.appendChild(nodedepth)
    root.appendChild(nodesize)

    segname = doc.createElement("segmented")
    segname.appendChild(doc.createTextNode("0"))
    root.appendChild(segname)

    for (box, label) in zip(box_list, label_list):

        nodeobject = doc.createElement('object')
        nodename = doc.createElement('name')
        nodename.appendChild(doc.createTextNode(str(label)))
        nodeobject.appendChild(nodename)
        nodebndbox = doc.createElement('bndbox')
        nodex1 = doc.createElement('x1')
        nodex1.appendChild(doc.createTextNode(str(box[0])))
        nodebndbox.appendChild(nodex1)
        nodey1 = doc.createElement('y1')
        nodey1.appendChild(doc.createTextNode(str(box[1])))
        nodebndbox.appendChild(nodey1)
        nodex2 = doc.createElement('x2')
        nodex2.appendChild(doc.createTextNode(str(box[2])))
        nodebndbox.appendChild(nodex2)
        nodey2 = doc.createElement('y2')
        nodey2.appendChild(doc.createTextNode(str(box[3])))
        nodebndbox.appendChild(nodey2)
        nodex3 = doc.createElement('x3')
        nodex3.appendChild(doc.createTextNode(str(box[4])))
        nodebndbox.appendChild(nodex3)
        nodey3 = doc.createElement('y3')
        nodey3.appendChild(doc.createTextNode(str(box[5])))
        nodebndbox.appendChild(nodey3)
        nodex4 = doc.createElement('x4')
        nodex4.appendChild(doc.createTextNode(str(box[6])))
        nodebndbox.appendChild(nodex4)
        nodey4 = doc.createElement('y4')
        nodey4.appendChild(doc.createTextNode(str(box[7])))
        nodebndbox.appendChild(nodey4)

        # ang = doc.createElement('angle')
        # ang.appendChild(doc.createTextNode(str(angle)))
        # nodebndbox.appendChild(ang)
        nodeobject.appendChild(nodebndbox)
        root.appendChild(nodeobject)
    fp = open(path + filename, 'w')
    doc.writexml(fp, indent='\n')
    fp.close()


def load_annoataion(p):
    '''
    load annotation from the text file
    :param p:
    :return:
    '''
    text_polys = []
    text_tags = []
    if not os.path.exists(p):
        return np.array(text_polys, dtype=np.float32)
    with open(p, 'r') as f:
        for line in f.readlines()[2:]:
            label = 'text'
            # strip BOM. \ufeff for python3,  \xef\xbb\bf for python2
            #line = [i.strip('\ufeff').strip('\xef\xbb\xbf') for i in line]
            #print(line)

            x1, y1, x2, y2, x3, y3, x4, y4 ,label= line.split(' ')[0:9]
            #print(label)
            text_polys.append([x1, y1, x2, y2, x3, y3, x4, y4])
            text_tags.append(label)

        return np.array(text_polys, dtype=np.float), np.array(text_tags, dtype=np.str)

txt_path = r'E:/baidudisk/DOTA/train/labelTxt-v1.5/DOTA-v1.5_train/'
xml_path = r'E:/baidudisk/DOTA/train/labelTxt-v1.5-voc/DOTA-v1.5_train/'
img_path = r'E:/baidudisk/DOTA/train/images/images/'
print(os.path.exists(txt_path))
txts = os.listdir(txt_path)
for count, t in enumerate(txts):
    path = os.path.join(txt_path,t)
    print(path)
    # boxes存储的是八个坐标
    # labels存储的是标签
    boxes, labels = load_annoataion(os.path.join(txt_path, t))
    # P0000.xml
    xml_name = t.replace('.txt', '.xml')
    img_name = t.replace('.txt', '.png')
    # P0000.png
    img = cv2.imread(os.path.join(img_path, img_name))
    h, w, d = img.shape
    #print(xml_name, xml_path, boxes, labels, w, h, d)
    WriterXMLFiles(xml_name,img_name, xml_path, boxes, labels, w, h, d)
    if count % 1000 == 0:
        print(count)
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

说明：
1：请务必将自己的文件路径进行修改
2：导包出现如下图横线，感觉也没有影响程序运行

3：文件转换最终如下图：