利用YOLOV5模型进行数据半自动标注
前言
利用训练好的yolo权重进行未标注图像的自动打标签功能，标签格式为txt格式，接着将txt格式的标签转换为xml格式。
一、YOLOV5模型进行数据半自动标注是什么？
将部分打完标签的数据利用YOLOV5模型进行训练，利用训练好的权重进行未标注图像的自动打标签功能，标注错误或漏标的框可以在LabelImg中手动调整。
二、使用步骤
1.YOLOV5进行训练并修改detect.py
1.1 yolov5训练
1.2 修改detect.py
（1）'–weights’为训练好的模型权重，default=ROOT / ‘best.pt’为模型权重路径；
（2）’–source’为未打标签的图片数据, default='G:/RGBD_data/0001112220601/3/rgb/'为图片路径；
（3）测试结果保存在’runs/detect/labels’路径中。
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
import argparse
import os
import sys
from pathlib import Path
import torch
import torch.backends.cudnn as cudnn
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.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams
from utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2,
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
@torch.no_grad()
def run(
weights=ROOT / 'yolov5s.pt', # model.pt path(s)
source=ROOT / 'data/images', # file/dir/URL/glob, 0 for webcam
data=ROOT / 'data/VOC.yaml', # dataset.yaml path
imgsz=(640, 640), # inference size (height, width)
conf_thres=0.1, # confidence threshold
iou_thres=0.1, # NMS IOU threshold
max_det=1000, # maximum detections per image
device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu
view_img=True, # show results
save_txt=True, # save results to *.txt
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)
save_img = not nosave and not source.endswith('.txt') # save inference images
is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
if is_url and is_file:
source = check_file(source) # download
# Directories
save_dir = increment_path(Path(project) / name, exist_ok=exist_ok) # increment run
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir
# Load model
device = select_device(device)
model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
stride, names, pt = model.stride, model.names, model.pt
imgsz = check_img_size(imgsz, s=stride) # check image size
# Dataloader
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)
bs = len(dataset) # batch_size
else:
dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)
bs = 1 # batch_size
vid_path, vid_writer = [None] * bs, [None] * bs
# Run inference
model.warmup(imgsz=(1 if pt else bs, 3, *imgsz)) # warmup
dt, seen = [0.0, 0.0, 0.0], 0
for path, im, im0s, vid_cap, s in dataset:
t1 = time_sync()
im = torch.from_numpy(im).to(device)
im = im.half() if model.fp16 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
p, im0, frame = path[i], im0s[i].copy(), dataset.count
s += f'{i}: '
else:
p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)
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
# print(xywh)
line = (cls, *xywh, conf) if save_conf else (cls, *xywh) # label format
# print(line)
with open(f'{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))
if save_crop:
save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
# 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:
if dataset.mode == 'image':
continue
# cv2.imwrite(save_path, im0)
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 = str(Path(save_path).with_suffix('.mp4')) # force *.mp4 suffix on results videos
vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
vid_writer[i].write(im0)
# Print time (inference-only)
LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)')
# 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 / 'best.pt', help='model path(s)')
# parser.add_argument('--source', type=str, default=ROOT / 'VOCData_test/222/rgb/', help='file/dir/URL/glob, 0 for webcam')
parser.add_argument('--source', type=str, default='G:/RGBD_data/0001112220601/3/rgb/', help='file/dir/URL/glob, 0 for webcam')
parser.add_argument('--data', type=str, default=ROOT / 'data/VOC.yaml', help='(optional) dataset.yaml path')
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=0.4, help='confidence threshold')
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='0', 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', default=True, action='store_true', help='save results to *.txt')
parser.add_argument('--save-conf', default=False, 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=3, 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(vars(opt))
return opt
def main(opt):
check_requirements(exclude=('tensorboard', 'thop'))
run(**vars(opt))
if __name__ == "__main__":
opt = parse_opt()
main(opt)
2.txt转换成xml格式
新建txt2xml.py，代码内dict为标签名，代码如下（示例）：
from xml.dom.minidom import Document
import os
import cv2
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 = {'0': "head",#字典对类型进行转换
'1': "bag",
'2': "suitcase",
'3': "child",
'4': "babycarriage",
'5': "umbrella",
'6': "flatcar",
'7': "sack",
}
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]+".png")
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("G:/yolov5/yolov5-master/runs/detect/exp2/labels/", "G:/RGBD_data/0001112220601/3/xml/", "G:/RGBD_data/0001112220601/3/rgb/")
总结
本方法可以节省标注时间，但还是要对输出的标签进行手动微调。
扫一扫
2236
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
