修改detect.py如下：
"""Run inference with a YOLOv5 model on images, videos, directories, streams
Usage:
$ python path/to/detect.py --source path/to/img.jpg --weights yolov5s.pt --img 640
"""
import argparse
import sys
import time
from pathlib import Path
import cv2
import torch
import torch.backends.cudnn as cudnn
FILE = Path(__file__).absolute()
sys.path.append(FILE.parents[0].as_posix()) # add yolov5/ to path
from models.experimental import attempt_load
from utils.datasets import LoadStreams, LoadImages
from utils.general import check_img_size, check_requirements, check_imshow, colorstr, non_max_suppression, \
apply_classifier, scale_coords, xyxy2xywh, strip_optimizer, set_logging, increment_path, save_one_box
from utils.plots import colors, plot_one_box
from utils.torch_utils import select_device, load_classifier, time_sync
import numpy as np
from xml.etree import ElementTree as ET
import warnings
warnings.filterwarnings('ignore')
labelsPath = "./data/auto.names"
LABELS = open(labelsPath).read().strip().split("\n")
print(LABELS)
# 定义一个创建一级分支object的函数
def create_object(root, xi, yi, xa, ya, obj_name): # 参数依次，树根，xmin，ymin，xmax，ymax
# 创建一级分支object
_object = ET.SubElement(root, 'object')
# 创建二级分支
name = ET.SubElement(_object, 'name')
# print(obj_name)
name.text = str(obj_name)
pose = ET.SubElement(_object, 'pose')
pose.text = 'Unspecified'
truncated = ET.SubElement(_object, 'truncated')
truncated.text = '0'
difficult = ET.SubElement(_object, 'difficult')
difficult.text = '0'
# 创建bndbox
bndbox = ET.SubElement(_object, 'bndbox')
xmin = ET.SubElement(bndbox, 'xmin')
xmin.text = '%s' % xi
ymin = ET.SubElement(bndbox, 'ymin')
ymin.text = '%s' % yi
xmax = ET.SubElement(bndbox, 'xmax')
xmax.text = '%s' % xa
ymax = ET.SubElement(bndbox, 'ymax')
ymax.text = '%s' % ya
# 创建xml文件的函数
def create_tree(sources, image_name, h, w):
imgdir = sources.split('/')[-1]
# 创建树根annotation
annotation = ET.Element('annotation')
# 创建一级分支folder
folder = ET.SubElement(annotation, 'folder')
# 添加folder标签内容
folder.text = (imgdir)
# 创建一级分支filename
filename = ET.SubElement(annotation, 'filename')
filename.text = image_name
# 创建一级分支path
path = ET.SubElement(annotation, 'path')
path.text = image_name # 用于返回当前工作目录
# 创建一级分支source
source = ET.SubElement(annotation, 'source')
# 创建source下的二级分支database
database = ET.SubElement(source, 'database')
database.text = 'Unknown'
# 创建一级分支size
size = ET.SubElement(annotation, 'size')
# 创建size下的二级分支图像的宽、高及depth
width = ET.SubElement(size, 'width')
width.text = str(w)
height = ET.SubElement(size, 'height')
height.text = str(h)
depth = ET.SubElement(size, 'depth')
depth.text = '3'
# 创建一级分支segmented
segmented = ET.SubElement(annotation, 'segmented')
segmented.text = '0'
return annotation
@torch.no_grad()
def run(weights='weights/yolov5x.pt', # model.pt path(s)
source='', # 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='', # cuda device, i.e. 0 or 0,1,2,3 or cpu
view_img=False, # show results
save_txt=False, # 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='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
):
save_img = not nosave and not source.endswith('.txt') # save inference images
webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(
('rtsp://', 'rtmp://', 'http://', 'https://'))
# 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
print(save_dir)
# Initialize
set_logging()
device = select_device(device)
half &= device.type != 'cpu' # half precision only supported on CUDA
# Load model
w = weights[0] if isinstance(weights, list) else weights
classify, pt, onnx = False, w.endswith('.pt'), w.endswith('.onnx') # inference type
stride, names = 64, [f'class{i}' for i in range(1000)] # assign defaults
if pt:
model = attempt_load(weights, map_location=device) # load FP32 model
stride = int(model.stride.max()) # model stride
names = model.module.names if hasattr(model, 'module') else model.names # get class names
# print(names)
if half:
model.half() # to FP16
if classify: # second-stage classifier
modelc = load_classifier(name='resnet50', n=2) # initialize
modelc.load_state_dict(torch.load('resnet50.pt', map_location=device)['model']).to(device).eval()
elif onnx:
check_requirements(('onnx', 'onnxruntime'))
import onnxruntime
session = onnxruntime.InferenceSession(w, None)
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)
bs = len(dataset) # batch_size
else:
dataset = LoadImages(source, img_size=imgsz, stride=stride)
bs = 1 # batch_size
vid_path, vid_writer = [None] * bs, [None] * bs
# Run inference
if pt and device.type != 'cpu': #进行一次前向推理,测试程序是否正常
model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters()))) # run once
t0 = time.time()
"""
path 图片/视频路径 /media/ai/D/Teamwork/wushuli/yolov5-master/test_images/5.jpg
img 进行resize+pad之后的图片 img.shape: (3, 384, 640) (3,h,w)
im0s 原size图片 im0s.shape: (1080, 1920, 3)
cap 当读取图片时为None，读取视频时为视频源
"""
for path, img, im0s, vid_cap in dataset:
if pt:
img = torch.from_numpy(img).to(device)
img = img.half() if half else img.float() # uint8 to fp16/32
elif onnx:
img = img.astype('float32')
img /= 255.0 # 0 - 255 to 0.0 - 1.0
if len(img.shape) == 3:
img = img[None] # expand for batch dim
# Inference
t1 = time_sync()
if pt:
visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
pred = model(img, augment=augment, visualize=visualize)[0]
# print(pred.shape) #[1, 15120, 6] 6分为（cx,cy,w,h,置信度，分类结果）
elif onnx:
pred = torch.tensor(session.run([session.get_outputs()[0].name], {session.get_inputs()[0].name: img}))
# NMS
#pred是一个列表list[torch.tensor]，长度为batch_size
# 每一个torch.tensor的shape为(num_boxes, 6),内容为box(xmin,ymin,xmax,ymax)+conf+cls
pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
# print("**********2**********", pred)
t2 = time_sync()
# Second-stage classifier (optional)
if classify:
pred = apply_classifier(pred, modelc, img, im0s)
(h, w) = im0s.shape[:2]
annotation = create_tree(source, path, h, w)
# Process predictions
for i, det in enumerate(pred): # detections per image
# print(i) #0
if webcam: # batch_size >= 1
p, s, im0, frame = path[i], f'{i}: ', im0s[i].copy(), dataset.count
else:
p, s, im0, frame = path, '', im0s.copy(), getattr(dataset, 'frame', 0)
p = Path(p) # to Path /media/ai/D/Teamwork/wushuli/yolov5-master/test_images/1.jpg
# print(p.name) #1.jpg
save_path = str(save_dir / p.name) # img.jpg
# print(save_path) #runs/detect/exp740/1.jpg
txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # img.txt
s += '%gx%g ' % img.shape[2:] # print string
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh ##tensor([1920, 1080, 1920, 1080])
imc = im0.copy() if save_crop else im0 # for save_crop
if len(det):
# Rescale boxes from img_size to im0 size
# print(img.shape[2:]) #torch.Size([384, 640])
# print(im0.shape) #(1080, 1920, 3)
## 调整预测框的坐标：基于resize+pad的图片的坐标-->基于原size图片的坐标
det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()
# print(det[:, :4])
# 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 xyxy: xml里需要的文件格式
for *xyxy, conf, cls in reversed(det):
print()
box_ = torch.tensor(xyxy).numpy()
x1, y1, x2, y2 = int(box_[0]), int(box_[1]), int(box_[2]), int(box_[3])
label = LABELS[int(cls)]
print("x1, y1, x2, y2, label: ", x1, y1, x2, y2, label)
create_object(annotation, x1, y1, x2, y2, label)
if save_txt: # Write to file
## 将xyxy(左上角+右下角)格式转为xywh(中心点+宽长)格式，并除上w，h做归一化，转化为列表再保存
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
print("xywh: ", 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')
tree = ET.ElementTree(annotation)
annotation_path_root = source.replace(source.split('/')[-1], 'output_xml')
print(annotation_path_root) #output_xml
print(path) #D:\yolov5-master\test_images\192.168.1.64_01_20200930100010174.jpg
tree.write('{}/{}.xml'.format(annotation_path_root, path.split('\\')[-1].strip('.jpg')))
# p.name.strip('.jpg')
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}')
plot_one_box(xyxy, im0, label=label, color=colors(c, True), line_thickness=line_thickness)
if save_crop:
save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
t3 = time.time()
# Print time (inference + NMS)
print(f'{s} inference + NMS Done. ({t2 - t1:.3f}s)')
print(f'{s} inference + NMS + XML_SAVE Done. ({t3 - t1:.3f}s)')
# Stream results
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':
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 += '.mp4'
vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
vid_writer[i].write(im0)
t4 = time.time()
print(f'{s} Per image process time: ({t4 - t1:.3f}s)')
print()
print("*********************************************************************")
print("Xml saved to ", '{}'.format(annotation_path_root)) #output_xml/5.xml
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 ''
print(f"Results saved to {save_dir}{s}")
if update:
strip_optimizer(weights) # update model (to fix SourceChangeWarning)
print(f'All Done. ({time.time() - t0:.3f}s)')
def parse_opt():
parser = argparse.ArgumentParser()
parser.add_argument('--weights', nargs='+', type=str, default='runs/train/exp728/weights/best.pt', help='model.pt path(s)')
parser.add_argument('--source', type=str, default='test_images', help='file/dir/URL/glob, 0 for webcam')
parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='inference size (pixels)')
parser.add_argument('--conf-thres', type=float, default=0.25, 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='cpu', 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: --class 0, or --class 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='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')
opt = parser.parse_args()
return opt
def main(opt):
print(colorstr('detect: ') + ', '.join(f'{k}={v}' for k, v in vars(opt).items()))
check_requirements(exclude=('tensorboard', 'thop'))
run(**vars(opt))
if __name__ == "__main__":
opt = parse_opt()
main(opt)
代码中labelsPath里面储存自己的类别名字，xml保存的文件夹名字为output_xml，按需修改。
标注完成后使用labelImg查看标注结果，先打开Open Dir加载刚才预标注的图片，Change Save Dir选择刚才xml保存的路径，之后就可以进行微调。
参考链接：