代码说明:labels文件夹是工程下的一个文件夹,里面存放的是一些xml文件。
然后我们将这些xml文件中的内容取出来,放在路径path1的文件名下。这样也就完成了xml文件到txt文件的转化。
该代码用到了两个包,pathlib以及xml.etree.cElementTree。文档的后面会对这两个包的一些基本使用做一些说明。
实现效果:
首先看一下xml文件:
'''

<annotation>
<folder>VOC2012</folder>
<filename>2007_000027.jpg</filename>
<source>
	<database>The VOC2007 Database</database>
	<annotation>PASCAL VOC2007</annotation>
	<image>flickr</image>
</source>
<size>
	<width>486</width>
	<height>500</height>
	<depth>3</depth>
</size>
<segmented>0</segmented>
<object>
	<name>person</name>
	<pose>Unspecified</pose>
	<truncated>0</truncated>
	<difficult>0</difficult>
	<bndbox>
		<xmin>174</xmin>
		<ymin>101</ymin>
		<xmax>349</xmax>
		<ymax>351</ymax>
	</bndbox>
	<part>
		<name>head</name>
		<bndbox>
			<xmin>169</xmin>
			<ymin>104</ymin>
			<xmax>209</xmax>
			<ymax>146</ymax>
		</bndbox>
	</part>
	<part>
		<name>hand</name>
		<bndbox>
			<xmin>278</xmin>
			<ymin>210</ymin>
			<xmax>297</xmax>
			<ymax>233</ymax>
		</bndbox>
	</part>
	<part>
		<name>foot</name>
		<bndbox>
			<xmin>273</xmin>
			<ymin>333</ymin>
			<xmax>297</xmax>
			<ymax>354</ymax>
		</bndbox>
	</part>
	<part>
		<name>foot</name>
		<bndbox>
			<xmin>319</xmin>
			<ymin>307</ymin>
			<xmax>340</xmax>
			<ymax>326</ymax>
		</bndbox>
	</part>
</object>

转换后的txt:
'''

F:\Object detection\YunYang1994-tensorflow-yolov3-master\2007_000027.jpg 174,101,349,351,1
F:\Object detection\YunYang1994-tensorflow-yolov3-master\2007_000032.jpg 104,78,375,183,0 133,88,197,123,0 195,180,213,229,1 26,189,44,238,1
F:\Object detection\YunYang1994-tensorflow-yolov3-master\2007_000033.jpg 9,107,499,263,0 421,200,482,226,0 325,188,411,223,0
F:\Object detection\YunYang1994-tensorflow-yolov3-master\2007_000039.jpg 156,89,344,279,0
F:\Object detection\YunYang1994-tensorflow-yolov3-master\2007_000042.jpg 263,32,500,295,0 1,36,235,299,0
F:\Object detection\YunYang1994-tensorflow-yolov3-master\2007_000061.jpg 274,11,437,279,0 184,214,281,252,0
F:\Object detection\YunYang1994-tensorflow-yolov3-master\2007_000063.jpg 123,115,379,275,0 75,1,428,375,0
F:\Object detection\YunYang1994-tensorflow-yolov3-master\2007_000068.jpg 27,45,266,375,0
F:\Object detection\YunYang1994-tensorflow-yolov3-master\2007_000121.jpg 251,28,475,267,0 22,28,251,273,0
F:\Object detection\YunYang1994-tensorflow-yolov3-master\2007_000123.jpg 1,26,358,340,0
F:\Object detection\YunYang1994-tensorflow-yolov3-master\2007_000129.jpg 70,202,255,500,0 251,242,334,500,0 1,144,67,436,0 1,1,66,363,1     74,1,272,462,1 252,19,334,487,1
F:\Object detection\YunYang1994-tensorflow-yolov3-master\2007_000170.jpg 87,100,109,165,0 41,114,73,181,0 324,148,352,206,0 426,157,443,195,0     3,91,43,206,1 4,28,461,372,1
F:\Object detection\YunYang1994-tensorflow-yolov3-master\2007_000175.jpg 25,34,419,271,0
F:\Object detection\YunYang1994-tensorflow-yolov3-master\2007_000187.jpg 1,95,240,336,0
F:\Object detection\YunYang1994-tensorflow-yolov3-master\2007_000241.jpg 356,183,500,280,0 60,109,142,213,0 246,134,348,217,0
F:\Object detection\YunYang1994-tensorflow-yolov3-master\2007_000243.jpg 181,127,274,193,0
F:\Object detection\YunYang1994-tensorflow-yolov3-master\2007_000250.jpg 1,170,474,375,0 97,124,150,297,0
F:\Object detection\YunYang1994-tensorflow-yolov3-master\2007_000256.jpg 8,96,491,232,0
F:\Object detection\YunYang1994-tensorflow-yolov3-master\2007_000272.jpg 25,71,304,500,1
F:\Object detection\YunYang1994-tensorflow-yolov3-master\2007_000323.jpg 277,3,500,375,1 12,3,305,375,1
F:\Object detection\YunYang1994-tensorflow-yolov3-master\2007_000332.jpg 54,50,285,262,0

代码:
'''

from pathlib import Path
import os

try:
  import xml.etree.cElementTree as ET
except ImportError:
  import xml.etree.ElementTree as ET
import sys
path = Path('F:/Object detection/YunYang1994-tensorflow-yolov3-master/labels')
file_list=[]
for files in path.rglob('*.xml'):
    file_list.append(files)#存进file_list

for  file in file_list:#循环文件
    tree = ET.parse(file)  #打开xml文档
    root = tree.getroot()  #获得root节点
    print("*"*10)
    filename = root.find('filename').text
    filename = filename[:-4]
    path1 = "voc3.txt"
    with open(path1, "a") as f:  # "a"用于追加内容

    f.write(os.path.abspath(filename + '.jpg'))#写入路径
    for object in root.findall('object'):#找到root节点下的所有object节点,写入坐标信息
      name = object.find('name').text   #子节点下节点name的值
      bndbox = object.find('bndbox')    #子节点下属性bndbox的值
      #坐标值
      xmin = bndbox.find('xmin').text
      ymin = bndbox.find('ymin').text
      xmax = bndbox.find('xmax').text
      ymax = bndbox.find('ymax').text

      if name==("person"):#
          class_id=1
      else:
          class_id=0
      with open(path1,"a") as f:#"a"用于追加内容
        f.write(' '+str(xmin)+','+str(ymin)+','+str(xmax)+','+str(ymax)+','+str(class_id))
    with open(path1, "a") as f:
      f.write('\n')
    f.close()