【Python 实操】labelImg标注的xml格式转换为yolo的txt文件
背景
YOLO家族开枝散叶(尤其是YOLOv5)的广泛应用就涉及到图像的标注与文件格式转换，常用的标注工具有LabelMe，labelImg等。用
labelImg标注完后，需要将voc格式的xml转换为yolo格式的txt; 废话不多说，直接上菜。
上菜
vocxml2yolotxt.py# filename: vocxml2yolotxt.pyimport xml.etree.ElementTree as ETimport pickleimport osfrom os import listdir, getcwdfrom os.path import join# 根据自己情况修改classes = ["Head","Helmet","WorkCloth","NormalCloth"]imgspath = "."imgsuffixlist = ['jpg', 'png', 'jpeg', 'bmp'] # 检查图像列表def checkimgslist(imgspath):imgslist = os.listdir(imgspath)newimgslist = []for imname in imgslist:suffix = imname.split(".")[-1]if suffix in imgsuffixlist:newimgslist.append(imname)return newimgslist# 转换尺寸和矩形框def convert(size, box):dw = 1. / size[0]dh = 1. / size[1]x = (box[0] + box[1]) / 2.0y = (box[2] + box[3]) / 2.0w = box[1] - box[0]h = box[3] - box[2]x = x * dww = w * dwy = y * dhh = h * dhreturn (x, y, w, h)# 转换标注信息def convert_annotation(image_id):# 如果找不到对应的xml，那么就直接新建一个文件即可print(image_id)# 直接创建文件out_file = open('labels/%s.txt' % image_id, 'w')# 找不到对应的xml文件，就直接新建一个txt文件，并退出if not os.path.exists('Annotations/%s.xml' % image_id):passelse:# UnicodeDecodeError: 'gbk' codec can't decode byte 0x80, 所以用 with open UTF-8 编码格式打开with open('Annotations/%s.xml' % image_id, 'r', encoding='UTF-8') as xml_file:tree = ET.parse(xml_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'):cls = obj.find('name').textif cls not in classes:continuecls_id = classes.index(cls)bbox = obj.find('bndbox')b = (float(bbox.find('xmin').text), float(bbox.find('xmax').text), float(bbox.find('ymin').text), float(bbox.find('ymax').text))bb = convert((w, h), b)out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')# 写完就关闭该文件out_file.close()# 将类别信息写入到文件中def print_classesname(classes):classesname = 'classes_name.txt'out_file = open(classesname, 'w')for cls in classes:out_file.write(str(cls)+"\n")out_file.close()if __name__ == '__main__':print("In main")i = 0# 找到图像文件列表imgslist = checkimgslist(imgspath=imgspath)# 打印类别信息到文件print_classesname(classes=classes)# 遍历图像文件列表并转换数据for imname in imgslist:# 调试用# i += 1# if i > 5:#break# print(imname)## 找到文件后缀最后一个位置suffix = imname.split(".")[-1]idx = imname.index(suffix) imnameid = imname[0:idx-1]# 转换生成文件convert_annotation(imnameid)
如果觉得《【Python 实操】labelImg标注的xml格式转换为yolo的txt文件》对你有帮助，请点赞、收藏，并留下你的观点哦！
