当前位置：首页 > news >正文

数据集格式转化 xml转换txt xml转换txt 转换代码示例参考 VOC（xml）格式如何转换yolo（txt ）格式 (1)

news 2026/8/7 7:43:52

如何三图一套代码来进行xml转换txt 转换代码示例参考。VOC（xml）格式如何转换yolo（txt ）格式的转换？

首先你得有数据集吧。

然后先进行数据集的标注，在分类到训练集测试集，验证集。最起码要搞个yaml,里面路径和yaml搞好，对不。然后训练不会出现路径报错类似于这样的问题，对不对？

答疑解惑同学经常问的问题：

另外VOC格式（XML）和YOLO(txt)格式，可以互转,不要忘记了！还有，YOLO数据集通用YOLOV5-YOLOV12都可以。
另外呢，附一个代码，让你知道如何XML格式，转换TXT的yolo格式。

这里以帽子和人 CLASSES = [“hat”, “person”] 两类数据集作为示例：如何转换格式：

第一步：

第二步：这里假设hat person 是smoke 和 fire

第三步：修改路径

importxml.etree.ElementTree as ETimportpickleimportos from osimportlistdir, getcwd from os.pathimportjoinimportrandom from shutilimportcopyfile from PILimportImage

只要改下面的CLASSES和PATH就可以了，其他的不用改，这个脚本会自动划分数据集，生成YOLO格式的标签文件

分类名称这里改成数据集的分类名称，一定要改！！！请查看数据集目录下的txt文件

CLASSES=["hat","person"]

数据集目录这里改成数据集的根目录，根目录下有两个文件夹Annotations和JPEGImages，一定要改！！！

PATH=r'C:\Users\87018\Desktop\xml2txt'

训练集占比80% 训练集:验证集=8:2 这里划分数据集不用改

TRAIN_RATIO=80def clear_hidden_files(path): dir_list=os.listdir(path)foriindir_list: abspath=os.path.join(os.path.abspath(path), i)ifos.path.isfile(abspath):ifi.startswith("._"): os.remove(abspath)else: clear_hidden_files(abspath)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 * dw w=w * dw y=y * dh h=h * dhreturn(x, y, w, h)def convert_annotation(image_id):# Assuming the image format is jpgimage_path=os.path.join(image_dir, f"{image_id}.jpg")img=Image.open(image_path)w, h=img.size in_file=open(PATH+'/Annotations/%s.xml'% image_id,encoding='utf-8')out_file=open(PATH+'/YOLOLabels/%s.txt'% image_id,'w',encoding='utf-8')tree=ET.parse(in_file)root=tree.getroot()size=root.find('size')# w = int(size.find('width').text)# h = int(size.find('height').text)difficult=0forobjinroot.iter('object'):ifobj.find('difficult'): difficult=obj.find('difficult').text cls=obj.find('name').textifcls notinCLASSES or int(difficult)==1:continuecls_id=CLASSES.index(cls)xmlbox=obj.find('bndbox')b=(float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text))bb=convert((w,h),b)out_file.write(str(cls_id)+" "+" ".join([str(a)for a in bb])+'\n')in_file.close()out_file.close()wd=os.getcwd()wd=os.getcwd()work_sapce_dir=os.path.join(wd,PATH+"/")annotation_dir=os.path.join(work_sapce_dir,"Annotations/")if not os.path.isdir(annotation_dir):os.mkdir(annotation_dir)clear_hidden_files(annotation_dir)image_dir=os.path.join(work_sapce_dir,"JPEGImages/")if not os.path.isdir(image_dir):os.mkdir(image_dir)clear_hidden_files(image_dir)yolo_labels_dir=os.path.join(work_sapce_dir,"YOLOLabels/")if not os.path.isdir(yolo_labels_dir):os.mkdir(yolo_labels_dir)clear_hidden_files(yolo_labels_dir)yolov5_train_dir=os.path.join(work_sapce_dir,"train/")if not os.path.isdir(yolov5_train_dir):os.mkdir(yolov5_train_dir)clear_hidden_files(yolov5_train_dir)yolov5_images_train_dir=os.path.join(yolov5_train_dir,"images/")if not os.path.isdir(yolov5_images_train_dir):os.mkdir(yolov5_images_train_dir)clear_hidden_files(yolov5_images_train_dir)yolov5_labels_train_dir=os.path.join(yolov5_train_dir,"labels/")if not os.path.isdir(yolov5_labels_train_dir):os.mkdir(yolov5_labels_train_dir)clear_hidden_files(yolov5_labels_train_dir)yolov5_test_dir=os.path.join(work_sapce_dir,"val/")if not os.path.isdir(yolov5_test_dir):os.mkdir(yolov5_test_dir)clear_hidden_files(yolov5_test_dir)yolov5_images_test_dir=os.path.join(yolov5_test_dir,"images/")if not os.path.isdir(yolov5_images_test_dir):os.mkdir(yolov5_images_test_dir)clear_hidden_files(yolov5_images_test_dir)yolov5_labels_test_dir=os.path.join(yolov5_test_dir,"labels/")if not os.path.isdir(yolov5_labels_test_dir):os.mkdir(yolov5_labels_test_dir)clear_hidden_files(yolov5_labels_test_dir)train_file=open(os.path.join(wd,"yolov5_train.txt"),'w',encoding='utf-8')test_file=open(os.path.join(wd,"yolov5_valid.txt"),'w',encoding='utf-8')train_file.close()test_file.close()train_file=open(os.path.join(wd,"yolov5_train.txt"),'a',encoding='utf-8')test_file=open(os.path.join(wd,"yolov5_valid.txt"),'a',encoding='utf-8')list_imgs=os.listdir(image_dir)# list image files prob=random.randint(1,100)print("数据集:%d个"%len(list_imgs))foriinrange(0, len(list_imgs)): path=os.path.join(image_dir, list_imgs[i])ifos.path.isfile(path): image_path=image_dir + list_imgs[i]voc_path=list_imgs[i](nameWithoutExtention, extention)=os.path.splitext(os.path.basename(image_path))(voc_nameWithoutExtention, voc_extention)=os.path.splitext(os.path.basename(voc_path))annotation_name=nameWithoutExtention +'.xml'annotation_path=os.path.join(annotation_dir, annotation_name)label_name=nameWithoutExtention +'.txt'label_path=os.path.join(yolo_labels_dir, label_name)prob=random.randint(1,100)print("Probability: %d"% prob, i, list_imgs[i])if(prob<TRAIN_RATIO):# train datasetifos.path.exists(annotation_path): train_file.write(image_path +'\n')convert_annotation(nameWithoutExtention)# convert labelcopyfile(image_path, yolov5_images_train_dir + voc_path)copyfile(label_path, yolov5_labels_train_dir + label_name)else:# test datasetifos.path.exists(annotation_path): test_file.write(image_path +'\n')convert_annotation(nameWithoutExtention)# convert labelcopyfile(image_path, yolov5_images_test_dir + voc_path)copyfile(label_path, yolov5_labels_test_dir + label_name)train_file.close()test_file.close()