需在目标文件夹中创建三个子文件夹,如:
20190822_Artificial_Flower_YOLO-TXT_convert_to_PascalVOC-XML
├─20190822_Artificial_Flower
├─20190822_Artificial_Flower_txt
└─20190822_Artificial_Flower_xml
其中20190822_Artificial_Flower
存放我们的图片,20190822_Artificial_Flower_txt
存放我们用(yolo)已经生成的.txt
文件,20190822_Artificial_Flower_xml
(空文件夹)存放我们将要生成的.xml
文件。然后还有一个obj.names
文件,存放我们的标注类名。
import os
import xml.etree.ElementTree as ET
from PIL import Image
import numpy as np
# img_path = 'C:/Users/jsb/Desktop/TFRecord/JPEGImages/' #原图.jpg文件的路径
img_path = 'D:/Yolov3_Tensorflow/LabelImg/YOLO-TXT_convert_to_PascalVOC-XML/20190822_Artificial_Flower_YOLO-TXT_convert_to_PascalVOC-XML/20190822_Artificial_Flower/' #原图.jpg文件的路径
# labels_path = 'C:/Users/jsb/Desktop/TFRecord/labels/' #labels中.txt文件的路径
labels_path = 'D:/Yolov3_Tensorflow/LabelImg/YOLO-TXT_convert_to_PascalVOC-XML/20190822_Artificial_Flower_YOLO-TXT_convert_to_PascalVOC-XML/20190822_Artificial_Flower_txt/' #labels中.txt文件的路径
# annotations_path = 'C:/Users/jsb/Desktop/TFRecord/Annotations/' #生成的xml文件需要保存的路径
annotations_path = 'D:/Yolov3_Tensorflow\LabelImg/YOLO-TXT_convert_to_PascalVOC-XML/20190822_Artificial_Flower_YOLO-TXT_convert_to_PascalVOC-XML/20190822_Artificial_Flower_xml/' #生成的xml文件需要保存的路径
labels = os.listdir(labels_path)
clsnames_path = 'D:/Yolov3_Tensorflow/LabelImg/YOLO-TXT_convert_to_PascalVOC-XML/20190822_Artificial_Flower_YOLO-TXT_convert_to_PascalVOC-XML/obj.names' #names文件的路径
with open(clsnames_path,'r') as f:
classes = f.readlines()
classes = [cls.strip('\n') for cls in classes]
def write_xml(imgname,filepath,labeldicts): #参数imagename是图片名(无后缀)
root = ET.Element('Annotation') #创建Annotation根节点
ET.SubElement(root, 'filename').text = str(imgname) #创建filename子节点(无后缀)
sizes = ET.SubElement(root,'size') #创建size子节点
ET.SubElement(sizes, 'width').text = '1280' #没带脑子直接写了原图片的尺寸......
ET.SubElement(sizes, 'height').text = '720'
ET.SubElement(sizes, 'depth').text = '3' #图片的通道数:img.shape[2]
for labeldict in labeldicts:
objects = ET.SubElement(root, 'object') #创建object子节点
ET.SubElement(objects, 'name').text = labeldict['name'] #BDD100K_10.names文件中
#的类别名
ET.SubElement(objects, 'pose').text = 'Unspecified'
ET.SubElement(objects, 'truncated').text = '0'
ET.SubElement(objects, 'difficult').text = '0'
bndbox = ET.SubElement(objects,'bndbox')
ET.SubElement(bndbox, 'xmin').text = str(int(labeldict['xmin']))
ET.SubElement(bndbox, 'ymin').text = str(int(labeldict['ymin']))
ET.SubElement(bndbox, 'xmax').text = str(int(labeldict['xmax']))
ET.SubElement(bndbox, 'ymax').text = str(int(labeldict['ymax']))
tree = ET.ElementTree(root)
tree.write(filepath, encoding='utf-8')
for label in labels: #批量读.txt文件
with open(labels_path + label, 'r') as f:
img_id = os.path.splitext(label)[0]
contents = f.readlines()
labeldicts = []
for content in contents:
img = np.array(Image.open(img_path+label.strip('.txt') + '.jpg'))
sh,sw = img.shape[0],img.shape[1] #img.shape[0]是图片的高度720
#img.shape[1]是图片的宽度720
content = content.strip('\n').split()
x=float(content[1])*sw
y=float(content[2])*sh
w=float(content[3])*sw
h=float(content[4])*sh
new_dict = {
'name': classes[int(content[0])],
'difficult': '0',
'xmin': x+1-w/2, #坐标转换公式看另一篇文章....
'ymin': y+1-h/2,
'xmax': x+1+w/2,
'ymax': y+1+h/2
}
labeldicts.append(new_dict)
write_xml(img_id, annotations_path + label.strip('.txt') + '.xml', labeldicts)
需修改代码中四个路径:
img_path = 'D:/Yolov3_Tensorflow/LabelImg/YOLO-TXT_convert_to_PascalVOC-XML/20190822_Artificial_Flower_YOLO-TXT_convert_to_PascalVOC-XML/20190822_Artificial_Flower/'
labels_path = 'D:/Yolov3_Tensorflow/LabelImg/YOLO-TXT_convert_to_PascalVOC-XML/20190822_Artificial_Flower_YOLO-TXT_convert_to_PascalVOC-XML/20190822_Artificial_Flower_txt/'
annotations_path = 'D:/Yolov3_Tensorflow\LabelImg/YOLO-TXT_convert_to_PascalVOC-XML/20190822_Artificial_Flower_YOLO-TXT_convert_to_PascalVOC-XML/20190822_Artificial_Flower_xml/'
clsnames_path = 'D:/Yolov3_Tensorflow/LabelImg/YOLO-TXT_convert_to_PascalVOC-XML/20190822_Artificial_Flower_YOLO-TXT_convert_to_PascalVOC-XML/obj.names'
修改成与自己的路径相对应的即可,需注意的是路径中要用“/”
分隔符而不要用“\”
分隔符,因为它有可能会被识别成转义字符。
然后运行代码,它就会在20190822_Artificial_Flower_xml
哗啦哗啦地生成对应的xml文件了:
参考文章:Python将VOC数据集归一化后的labels(.txt)文件批量转成xml文件
貌似代码中有点bug,计算出来的坐标数值比用LabelImg转换出来的值大1。如图框选部分实际应为[563, 495, 696, 618]
这是程序生成的:
这是用LabelImg转换得到的: