yolov5半自动标注，测试好用
效果是检测一个文件夹里面的图片批量生成txt文件，再通过txt转xml可以直接在labelimg可视化微调，实现批量标注。
下载yolov5官方文件，然后修改detect.py文件。
import argparse
import os
import sys
from pathlib import Path
from dataread import MyData
import cv2
import numpy as np
import torch
import torch.backends.cudnn as cudnn
import threading
FILE = Path(__file__).resolve()
ROOT = FILE.parents[0] # YOLOv5 root directory
if str(ROOT) not in sys.path:
sys.path.append(str(ROOT)) # add ROOT to PATH
ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative
from models.common import DetectMultiBackend
from utils.datasets import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams
from utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr,
increment_path, non_max_suppression, print_args, scale_coords, strip_optimizer, xyxy2xywh)
from utils.plots import Annotator, colors, save_one_box
from utils.torch_utils import select_device, time_sync
mask_num=nomask_num=person=0
@torch.no_grad()
def run(weights=ROOT / 'yolov5s.pt', # model.pt path(s)
source=ROOT / 'data/images', # file/dir/URL/glob, 0 for webcam
imgsz=640, # inference size (pixels)
conf_thres=0.25, # confidence threshold
iou_thres=0.45, # NMS IOU threshold
max_det=1000, # maximum detections per image
device='0', # cuda device, i.e. 0 or 0,1,2,3 or cpu
view_img=True, # show results
save_txt=False, # save results to *.txt，改了这个
save_conf=False, # save confidences in --save-txt labels
save_crop=False, # save cropped prediction boxes
nosave=False, # do not save images/videos
classes=None, # filter by class: --class 0, or --class 0 2 3
agnostic_nms=False, # class-agnostic NMS
augment=False, # augmented inference
visualize=False, # visualize features
update=False, # update all models
project=ROOT / 'runs/detect', # save results to project/name
name='exp', # save results to project/name
exist_ok=False, # existing project/name ok, do not increment
line_thickness=3, # bounding box thickness (pixels)
hide_labels=False, # hide labels
hide_conf=False, # hide confidences
half=False, # use FP16 half-precision inference
dnn=False, # use OpenCV DNN for ONNX inference
):
source = str(source)#将文件强制变成字符串
save_img = not nosave and not source.endswith('.txt') #true和true就要把接过保存
is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)#前面表示jpg后缀是否在后面两个，表示true
is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))#转小写，后面判断网路地址
webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)#判断是不是数字，是不是0，是不是摄像头
if is_url and is_file:
source = check_file(source) # 判断是不是文件，然后下载
# Directories
save_dir = increment_path(Path(project) / name, exist_ok=True) # increment run，exp会增量保存改了这个
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir，可以新建文件夹
# Load model
device = select_device(device)#选择设备
model = DetectMultiBackend(weights, device=device, dnn=dnn)#加载模型
stride, names, pt, jit, onnx = model.stride, model.names, model.pt, model.jit, model.onnx#模型读取
imgsz = check_img_size(imgsz, s=stride) #检查图片大小，步长，帮忙修改
# Half
half &= pt and device.type != 'cpu' # half precision only supported by PyTorch on CUDA
if pt:
model.model.half() if half else model.model.float()
# Dataloader#数据加载
if webcam:
view_img = check_imshow()
cudnn.benchmark = True # set True to speed up constant image size inference
dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt and not jit)
bs = len(dataset) # batch_size
else:
# print('请输入X1，Y1')
# x1=input()
# x1=int(x1)
# y1=input()
# y1 = int(y1)
# print('请输入X2，Y2')
# x2 = input()
# x2 = int(x2)
# y2 = input()
# y2 = int(y2)
dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt and not jit)#改输入图片
bs = 1 # batch_size
vid_path, vid_writer = [None] * bs, [None] * bs
# Run inference
if pt and device.type != 'cpu':
model(torch.zeros(1, 3, *imgsz).to(device).type_as(next(model.model.parameters()))) # warmup
dt, seen = [0.0, 0.0, 0.0], 0
for path, im, im0s, vid_cap, s in dataset:
# mask for certain region
#1,2,3,4 分别对应左上，右上，右下，左下四个点
hl1 = 0 / 10 #监测区域高度距离图片顶部比例
wl1 = 0/ 10 #监测区域高度距离图片左部比例
hl2 = 0 / 10 # 监测区域高度距离图片顶部比例
wl2 = 10 / 10 # 监测区域高度距离图片左部比例
hl3 = 10 / 10 # 监测区域高度距离图片顶部比例
wl3 = 10/ 10 # 监测区域高度距离图片左部比例
hl4 = 10 / 10 # 监测区域高度距离图片顶部比例
wl4 = 0 / 10 # 监测区域高度距离图片左部比例
if webcam:
pass
# for b in range(0,im.shape[0]):
# mask = np.zeros([im[b].shape[1], im[b].shape[2]], dtype=np.uint8)
# #mask[round(img[b].shape[1] * hl1):img[b].shape[1], round(img[b].shape[2] * wl1):img[b].shape[2]] = 255
# pts = np.array([[int(im[b].shape[2] * wl1), int(im[b].shape[1] * hl1)], # pts1
# [int(im[b].shape[2] * wl2), int(im[b].shape[1] * hl2)], # pts2
# [int(im[b].shape[2] * wl3), int(im[b].shape[1] * hl3)], # pts3
# [int(im[b].shape[2] * wl4), int(im[b].shape[1] * hl4)]], np.int32)
# mask = cv2.fillPoly(mask,[pts],(255,255,255))
# imgc = im[b].transpose((1, 2, 0))
# imgc = cv2.add(imgc, np.zeros(np.shape(imgc), dtype=np.uint8), mask=mask)
# #cv2.imshow('1',imgc)
# im[b] = imgc.transpose((2, 0, 1))
else:
mask = np.zeros([im.shape[1], im.shape[2]], dtype=np.uint8)
#mask[round(img.shape[1] * hl1):img.shape[1], round(img.shape[2] * wl1):img.shape[2]] = 255
pts = np.array([[int(im.shape[2] * wl1), int(im.shape[1] * hl1)], # pts1
[int(im.shape[2] * wl2), int(im.shape[1] * hl2)], # pts2
[int(im.shape[2] * wl3), int(im.shape[1] * hl3)], # pts3
[int(im.shape[2] * wl4), int(im.shape[1] * hl4)]], np.int32)
mask = cv2.fillPoly(mask, [pts], (255,255,255))
im = im.transpose((1, 2, 0))
im = cv2.add(im, np.zeros(np.shape(im), dtype=np.uint8), mask=mask)
im = im.transpose((2, 0, 1))
t1 = time_sync()
im = torch.from_numpy(im).to(device)
im = im.half() if half else im.float() # uint8 to fp16/32
im /= 255 # 0 - 255 to 0.0 - 1.0
if len(im.shape) == 3:
im = im[None] # expand for batch dim
t2 = time_sync()
dt[0] += t2 - t1
# Inference
visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
pred = model(im, augment=augment, visualize=visualize)
t3 = time_sync()
dt[1] += t3 - t2
# NMS
pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
dt[2] += time_sync() - t3
# Second-stage classifier (optional)
# pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
# Process predictions
for i, det in enumerate(pred): # per image
seen += 1
if webcam: # batch_size >= 1
pass
# p, s, im0, frame = path[i], f'{i}: ', im0s[i].copy(), dataset.count
# cv2.putText(im0, "Detection_Region", (int(im0.shape[1] * wl1 - 5), int(im0.shape[0] * hl1 - 5)),
# cv2.FONT_HERSHEY_SIMPLEX,
# 1.0, (255, 255, 0), 2, cv2.LINE_AA)
#
# pts = np.array([[int(im0.shape[1] * wl1), int(im0.shape[0] * hl1)], # pts1
# [int(im0.shape[1] * wl2), int(im0.shape[0] * hl2)], # pts2
# [int(im0.shape[1] * wl3), int(im0.shape[0] * hl3)], # pts3
# [int(im0.shape[1] * wl4), int(im0.shape[0] * hl4)]], np.int32) # pts4
# # pts = pts.reshape((-1, 1, 2))
# zeros = np.zeros((im0.shape), dtype=np.uint8)
# mask = cv2.fillPoly(zeros, [pts], color=(0, 165, 255))
# im0 = cv2.addWeighted(im0, 1, mask, 0.2, 0)
# cv2.polylines(im0, [pts], True, (255, 255, 0), 3)
# # plot_one_box(dr, im0, label='Detection_Region', color=(0, 255, 0), line_thickness=2)
else:
p, s, im0, frame = path, '', im0s.copy(), getattr(dataset, 'frame', 0)
cv2.putText(im0, "Detection_Region", (int(im0.shape[1] * wl1 - 5), int(im0.shape[0] * hl1 - 5)),
cv2.FONT_HERSHEY_SIMPLEX,
1.0, (255, 255, 0), 2, cv2.LINE_AA)
pts = np.array([[int(im0.shape[1] * wl1), int(im0.shape[0] * hl1)], # pts1
[int(im0.shape[1] * wl2), int(im0.shape[0] * hl2)], # pts2
[int(im0.shape[1] * wl3), int(im0.shape[0] * hl3)], # pts3
[int(im0.shape[1] * wl4), int(im0.shape[0] * hl4)]], np.int32) # pts4
# pts = pts.reshape((-1, 1, 2))
zeros = np.zeros((im0.shape), dtype=np.uint8)
mask = cv2.fillPoly(zeros, [pts], color=(0, 165, 255))
im0 = cv2.addWeighted(im0, 1, mask, 0.2, 0)
cv2.polylines(im0, [pts], True, (255, 255, 0), 3)
p = Path(p) # to Path
save_path = str(save_dir / p.name) # im.jpg
txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # im.txt
s += '%gx%g ' % im.shape[2:] # print string
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh
imc = im0.copy() if save_crop else im0 # for save_crop
annotator = Annotator(im0, line_width=line_thickness, example=str(names))
if len(det):
# Rescale boxes from img_size to im0 size
det[:, :4] = scale_coords(im.shape[2:], det[:, :4], im0.shape).round()
# Print results
for c in det[:, -1].unique():
n = (det[:, -1] == c).sum() # detections per class
s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string
# Write results
for *xyxy, conf, cls in reversed(det):
if save_txt: # Write to file
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
line = (cls, *xywh, conf) if save_conf else (cls, *xywh) # label format
with open(txt_path + '.txt', 'a') as f:
f.write(('%g ' * len(line)).rstrip() % line + '\n')
if save_img or save_crop or view_img: # Add bbox to image
c = int(cls) # integer class
label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
annotator.box_label(xyxy, label, color=colors(c, True))
global mask_num,nomask_num,person
if names[c]=="with_mask":
mask_num+=1
print('第'+str(mask_num)+'个'+'戴口罩的坐标')
p1, p2 = (int(xyxy[0]), int(xyxy[1])), (int(xyxy[2]), int(xyxy[3]))
print("左上点的坐标为：(" + str(p1[0]) + "," + str(p1[1]) + ")，右下点的坐标为(" + str(p2[0]) + "," + str(p2[1]) + ")")
if names[c]=="without_mask":
nomask_num+=1
print('第'+str(nomask_num)+'个'+'没戴口罩的坐标')
p1, p2 = (int(xyxy[0]), int(xyxy[1])), (int(xyxy[2]), int(xyxy[3]))
print("左上点的坐标为：(" + str(p1[0]) + "," + str(p1[1]) + ")，右下点的坐标为(" + str(
p2[0]) + "," + str(p2[1]) + ")")
if names[c] == "person":
person += 1
print('第' + str(person) + '个' + '人')
p1, p2 = (int(xyxy[0]), int(xyxy[1])), (int(xyxy[2]), int(xyxy[3]))
print("左上点的坐标为：(" + str(p1[0]) + "," + str(p1[1]) + ")，右下点的坐标为(" + str(
p2[0]) + "," + str(p2[1]) + ")")
if save_crop:
save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
# Print time (inference-only)
LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)')
# Stream results
# im0 = annotator.result()
# if view_img:
# cv2.imshow(str(p), im0)
# cv2.waitKey(1) # 1 millisecond
# Save results (image with detections)
if save_img:
print("戴口罩人数是"+str(mask_num)+"没戴口罩人数是"+str(nomask_num)+"无法判断的人数"+str(person)+"总人数"+str(person+mask_num+nomask_num))
if dataset.mode == 'image':
im0=cv2.putText(im0, f"{nomask_num}{'no'} {mask_num}{'yes'} {person}{'cannot'} {person+mask_num+nomask_num}{'all'}", (5, 50), cv2.FONT_HERSHEY_SIMPLEX, 1,
(0, 0, 255), 2)
# if mask_num == nomask_num == 0:
# os.remove(path)#删除检测不到的
# cv2.imwrite(save_path, im0)
# mask_num=nomask_num=person=0#上面3行注释
cv2.imwrite(save_path, im0)
mask_num = nomask_num = person = 0 # 上面2行注释
# img1 = cv2.resize(im0, (1100, 700))
# cv2.imshow('img', img1)
# cv2.waitKey(100)
# else: # 'video' or 'stream'
# if vid_path[i] != save_path: # new video
# vid_path[i] = save_path
# if isinstance(vid_writer[i], cv2.VideoWriter):
# vid_writer[i].release() # release previous video writer
# if vid_cap: # video
# fps = vid_cap.get(cv2.CAP_PROP_FPS)
# w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
# h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
# else: # stream
# fps, w, h = 30, im0.shape[1], im0.shape[0]
# save_path += '.mp4'
# vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
# vid_writer[i].write(im0)
#Print results
t = tuple(x / seen * 1E3 for x in dt) # speeds per image
LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t)
if save_txt or save_img:
s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
if update:
strip_optimizer(weights) # update model (to fix SourceChangeWarning)
def parse_opt():
parser = argparse.ArgumentParser()
parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'runs/train/exp4/exp4/weights/best.pt', help='model path(s)')
parser.add_argument('--source', type=str, default=ROOT / '1512629522879614977/1-1666145676282-5.jpg', help='file/dir/URL/glob, 0 for webcam')
parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
parser.add_argument('--conf-thres', type=float, default=0.25, help='confidence threshold')#置信度
parser.add_argument('--iou-thres', type=float, default=0.45, help='NMS IoU threshold')
parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per image')
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--view-img', action='store_true', help='show results')
parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
parser.add_argument('--save-crop', action='store_true', help='save cropped prediction boxes')
parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --classes 0, or --classes 0 2 3')
parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
parser.add_argument('--augment', action='store_true', help='augmented inference')
parser.add_argument('--visualize', action='store_true', help='visualize features')
parser.add_argument('--update', action='store_true', help='update all models')
parser.add_argument('--project', default=ROOT / 'runs/detect', help='save results to project/name')
parser.add_argument('--name', default='exp', help='save results to project/name')
parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
parser.add_argument('--line-thickness', default=2, type=int, help='bounding box thickness (pixels)')
parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels')
parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences')
parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference')
opt = parser.parse_args()
opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand
print_args(FILE.stem, opt)
return opt
def main(opt):
check_requirements(exclude=('tensorboard', 'thop'))
run(**vars(opt))
# class MyThread(threading.Thread):
# def run(self):
# for i in range(5):
# opt = parse_opt()
# root_dir = "" # 当前根目录，在当前文件夹就不写
# image = "runs/detect/Images"+str(i) # 图片文件夹名字，需要跟detect.py同一个文件夹下面
# img = MyData(root_dir, image)
# for i in range(len(img)):
# opt.source = img[i]
# main(opt)#多线程
# 命令使用
# python detect.py --weights runs/train/exp_yolov5s/weights/best.pt --source data/images/fishman.jpg # webcam
if __name__ == "__main__":
# for i in range(5):
# t = MyThread()
# t.start()#多线程
opt = parse_opt()
root_dir = "" # 当前根目录，在当前文件夹就不写
image = "runs/detect/Images0" # 图片文件夹名字，需要跟detect.py同一个文件夹下面
img = MyData(root_dir, image)
for i in range(len(img)):
opt.source = img[i]
main(opt)
# opt = parse_opt()
# main(opt)#单张图片新创建一个文件叫dataread.py
from torch.utils.data import Dataset
import os
class MyData(Dataset):
def __init__(self, root_dir, image_dir):
self.root_dir = root_dir
self.image_dir = image_dir
self.image_path = os.path.join(self.root_dir, self.image_dir)
self.image_list = os.listdir(self.image_path)
self.image_list.sort()
def __getitem__(self, idx):
img_name = self.image_list[idx]
img_item_path = os.path.join(self.root_dir, self.image_dir, img_name)
img_item_path.replace("\\", "/")
return img_item_path
def __len__(self):
return len(self.image_list)
if __name__ == '__main__':
root_dir = ""#当前根目录，在当前文件夹就不写
image_ants = "1512629522879614977"#图片文件夹名字，需要跟detect.py同一个文件夹下面
ants_dataset = MyData(root_dir, image_ants)
print(ants_dataset[1])
然后我是在runs/detect/Images0这个目录放图片，没有这个目录自己创建一个，然后再创一个runs/detect/exp/labels以及runs/detect/Annotations。
然后在python终端运行python detect.py --save-txt ,开始自动标注。
生成txt结果
txt转xml
创建一个python文件，代码里面自己改自动标成什么名字。
# 将 txt 标签 文件转换为 xml 标签文件, 修改dict中的类，以及xml txt 和jpg 路径。
from xml.dom.minidom import Document
import os
import cv2
# 'person','head','helmet','lifejacket'
def makexml(txtPath,xmlPath,picPath): #读取txt路径，xml保存路径，数据集图片所在路径
dict = {'2': "person", #字典对类型进行转换，自己的标签的类。
'0': "with_mask",
'1': "without_mask",
'3': "with_mask"
}
files = os.listdir(txtPath)
for i, name in enumerate(files):
xmlBuilder = Document()
annotation = xmlBuilder.createElement("annotation") # 创建annotation标签
xmlBuilder.appendChild(annotation)
txtFile=open(txtPath+name)
txtList = txtFile.readlines()
img = cv2.imread(picPath+name[0:-4]+".jpg")
Pheight,Pwidth,Pdepth=img.shape
for i in txtList:
oneline = i.strip().split(" ")
folder = xmlBuilder.createElement("folder")#folder标签
folderContent = xmlBuilder.createTextNode("VOC2007")
folder.appendChild(folderContent)
annotation.appendChild(folder)
filename = xmlBuilder.createElement("filename")#filename标签
filenameContent = xmlBuilder.createTextNode(name[0:-4]+".png")
filename.appendChild(filenameContent)
annotation.appendChild(filename)
size = xmlBuilder.createElement("size") # size标签
width = xmlBuilder.createElement("width") # size子标签width
widthContent = xmlBuilder.createTextNode(str(Pwidth))
width.appendChild(widthContent)
size.appendChild(width)
height = xmlBuilder.createElement("height") # size子标签height
heightContent = xmlBuilder.createTextNode(str(Pheight))
height.appendChild(heightContent)
size.appendChild(height)
depth = xmlBuilder.createElement("depth") # size子标签depth
depthContent = xmlBuilder.createTextNode(str(Pdepth))
depth.appendChild(depthContent)
size.appendChild(depth)
annotation.appendChild(size)
object = xmlBuilder.createElement("object")
picname = xmlBuilder.createElement("name")
nameContent = xmlBuilder.createTextNode(dict[oneline[0]])
picname.appendChild(nameContent)
object.appendChild(picname)
pose = xmlBuilder.createElement("pose")
poseContent = xmlBuilder.createTextNode("Unspecified")
pose.appendChild(poseContent)
object.appendChild(pose)
truncated = xmlBuilder.createElement("truncated")
truncatedContent = xmlBuilder.createTextNode("0")
truncated.appendChild(truncatedContent)
object.appendChild(truncated)
difficult = xmlBuilder.createElement("difficult")
difficultContent = xmlBuilder.createTextNode("0")
difficult.appendChild(difficultContent)
object.appendChild(difficult)
bndbox = xmlBuilder.createElement("bndbox")
xmin = xmlBuilder.createElement("xmin")
mathData=int(((float(oneline[1]))*Pwidth+1)-(float(oneline[3]))*0.5*Pwidth)
xminContent = xmlBuilder.createTextNode(str(mathData))
xmin.appendChild(xminContent)
bndbox.appendChild(xmin)
ymin = xmlBuilder.createElement("ymin")
mathData = int(((float(oneline[2]))*Pheight+1)-(float(oneline[4]))*0.5*Pheight)
yminContent = xmlBuilder.createTextNode(str(mathData))
ymin.appendChild(yminContent)
bndbox.appendChild(ymin)
xmax = xmlBuilder.createElement("xmax")
mathData = int(((float(oneline[1]))*Pwidth+1)+(float(oneline[3]))*0.5*Pwidth)
xmaxContent = xmlBuilder.createTextNode(str(mathData))
xmax.appendChild(xmaxContent)
bndbox.appendChild(xmax)
ymax = xmlBuilder.createElement("ymax")
mathData = int(((float(oneline[2]))*Pheight+1)+(float(oneline[4]))*0.5*Pheight)
ymaxContent = xmlBuilder.createTextNode(str(mathData))
ymax.appendChild(ymaxContent)
bndbox.appendChild(ymax)
object.appendChild(bndbox)
annotation.appendChild(object)
f = open(xmlPath+name[0:-4]+".xml", 'w')
xmlBuilder.writexml(f, indent='\t', newl='\n', addindent='\t', encoding='utf-8')
f.close()
makexml("runs/detect/exp/labels/", # txt文件夹
"runs/detect/Annotations/", # xml文件夹
"runs/detect/Images0/") # 图片数据文件夹
运行过后，标注完成
查看使用labelimg打开。可以看到自动标注成功
想要删除一类标签，再创建一个python文件
import os
import xml.etree.ElementTree as ET
yuan_dir = 'runs/detect/Annotations' # 设置原始标签路径为 Annos
new_dir = 'runs/detect/Annotations' # 设置新标签路径 Annotations
for filename in os.listdir(yuan_dir):
file_path = os.path.join(yuan_dir, filename)
new_path=os.path.join(new_dir,filename)
dom = ET.parse(file_path)
root = dom.getroot()
for obj in root.iter('object'): # 获取object节点中的name子节点
if obj.find('name').text== 'with_mask':
root.remove(obj)
#print("change %s to %s." % (yuan_name, new_name1))
elif obj.find('name').text== 'a':
root.remove(obj)
##可以继续删除，继续用elif语句
# 保存到指定文件
dom.write(new_path, xml_declaration=True)
可以看到自动删完啦