在使用yolov5制作数据集时，yolov5使用txt格式的标签，打标签的工具如labelimg使用的是xml格式的标签，需要进行数据集格式的转换：
yolov5保存检测结果的txt标签 python3.8 detect.py --weights '/homeimages'# txt文件夹，后面的/不能省labels_path = '/home'# xml存放的文件夹，后面的/不能省annotations_path = '/home'labels = os.listdir(labels_path)# 类别classes = ["**"] #类别名# 图片的高度、宽度、深度sh = sw = sd = 0def write_xml(imgname, sw, sh, sd, filepath, labeldicts): ''' imgname: 没有扩展名的图片名称 ''' # 创建Annotation根节点 root = ET.Element('Annotation') # 创建filename子节点，无扩展名 ET.SubElement(root, 'filename').text = str(imgname) # 创建size子节点 sizes = ET.SubElement(root,'size') ET.SubElement(sizes, 'width').text = str(sw) ET.SubElement(sizes, 'height').text = str(sh) ET.SubElement(sizes, 'depth').text = str(sd) for labeldict in labeldicts: objects = ET.SubElement(root, 'object') ET.SubElement(objects, 'name').text = labeldict['name'] 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: with open(labels_path + label, 'r') as f: img_id = os.path.splitext(label)[0] contents = f.readlines() labeldicts = [] for content in contents: # !!!这里要看你的图片格式了，我这里是png，注意修改 img = np.array(Image.open(img_path + label.strip('.txt') + '.png')) # 图片的高度和宽度 sh, sw, sd = img.shape[0], img.shape[1], img.shape[2] 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 # 坐标的转换，x_center y_center width height -> xmin ymin xmax ymax new_dict = {'name': classes[int(content[0])], 'difficult': '0', 'xmin': x+1-w/2, 'ymin': y+1-h/2, 'xmax': x+1+w/2, 'ymax': y+1+h/2 } labeldicts.append(new_dict) write_xml(img_id, sw, sh, sd, annotations_path + label.strip('.txt') + '.xml', labeldicts)#[转载链接](https://zhuanlan.zhihu.com/p/383660741)- xml格式的数据集标签转为txt格式
import osimport xml.etree.ElementTree as ETfrom decimal import Decimal dirpath = '/home' # 修改label后形成的txt目录 if not os.path.exists(newdir): os.makedirs(newdir) for fp in os.listdir(dirpath): root = ET.parse(os.path.join(dirpath, fp)).getroot() xmin, ymin, xmax, ymax = 0, 0, 0, 0 sz = root.find('size') width = float(sz[0].text) height = float(sz[1].text) filename = root.find('filename').text print(fp) with open(os.path.join(newdir, fp.split('.')[0] + '.txt'), 'a+') as f: for child in root.findall('object'): # 找到图片中的所有框 sub = child.find('bndbox') # 找到框的标注值并进行读取 sub_label = child.find('name') xmin = float(sub[0].text) ymin = float(sub[1].text) xmax = float(sub[2].text) ymax = float(sub[3].text) try: # 转换成yolov的标签格式，需要归一化到（0-1）的范围内 x_center = Decimal(str(round(float((xmin + xmax) / (2 * width)),6))).quantize(Decimal('0.000000')) y_center = Decimal(str(round(float((ymin + ymax) / (2 * height)),6))).quantize(Decimal('0.000000')) w = Decimal(str(round(float((xmax - xmin) / width),6))).quantize(Decimal('0.000000')) h = Decimal(str(round(float((ymax - ymin) / height),6))).quantize(Decimal('0.000000')) print(str(x_center) + ' ' + str(y_center)+ ' '+str(w)+ ' '+str(h)) #读取需要的标签 #if sub_label.text == 'armor': f.write(' '.join([str(0), str(x_center), str(y_center), str(w), str(h) + '\n'])) except ZeroDivisionError: print(' width有问题') '''有其他标签选用if sub_label.text == 'xxx': f.write(' '.join([str(1), str(x_center), str(y_center), str(w), str(h) + '\n']))if sub_label.text == 'xxx': f.write(' '.join([str(2), str(x_center), str(y_center), str(w), str(h) + '\n']))''' # with open(os.path.join(newdir, fp.split('.')[0] + '.txt'), 'a+') as f: # f.write(' '.join([str(2), str(x_center), str(y_center), str(w), str(h) + '\n']))
