<annotation>
	<folder></folder>
	<filename>CDD84EAA8288FE4CFA365CC4F2A2DCD0_jpg.rf.95314b0bd1f49391d6a000afdbd2fa6f.jpg</filename>
	<path>CDD84EAA8288FE4CFA365CC4F2A2DCD0_jpg.rf.95314b0bd1f49391d6a000afdbd2fa6f.jpg</path>
	<source>
		<database>roboflow.com</database>
	</source>
	<size>
		<width>640</width>
		<height>640</height>
		<depth>3</depth>
	</size>
	<segmented>0</segmented>
	<object>
		<name>electric-vehicle</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<occluded>0</occluded>
		<bndbox>
			<xmin>365</xmin>
			<xmax>442</xmax>
			<ymin>66</ymin>
			<ymax>245</ymax>
		</bndbox>
	</object>
	<object>
		<name>electric-vehicle</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<occluded>0</occluded>
		<bndbox>
			<xmin>41</xmin>
			<xmax>275</xmax>
			<ymin>92</ymin>
			<ymax>478</ymax>
		</bndbox>
	</object>
	<object>
		<name>electric-vehicle</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<occluded>0</occluded>
		<bndbox>
			<xmin>226</xmin>
			<xmax>394</xmax>
			<ymin>107</ymin>
			<ymax>524</ymax>
		</bndbox>
	</object>
	<object>
		<name>electric-vehicle</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<occluded>0</occluded>
		<bndbox>
			<xmin>579</xmin>
			<xmax>640</xmax>
			<ymin>192</ymin>
			<ymax>546</ymax>
		</bndbox>
	</object>
</annotation>

2 0.70703125 0.38515625 0.38046875 0.765625
1 0.18359375 0.1796875 0.3671875 0.359375

import os
import random

trainval_percent = 0.9
train_percent = 0.9
xmlfilepath = 'data/Annotations'
txtsavepath = 'data/ImageSets'
total_xml = os.listdir(xmlfilepath)

num = len(total_xml)
list = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list, tv)
train = random.sample(trainval, tr)

ftrainval = open('data/ImageSets/trainval.txt', 'w')
ftest = open('data/ImageSets/test.txt', 'w')
ftrain = open('data/ImageSets/train.txt', 'w')
fval = open('data/ImageSets/val.txt', 'w')

for i in list:
    name = total_xml[i][:-4] + '\n'
    if i in trainval:
        ftrainval.write(name)
        if i in train:
            ftrain.write(name)
        else:
            fval.write(name)
    else:
        ftest.write(name)

ftrainval.close()
ftrain.close()
fval.close()
ftest.close()

import xml.etree.ElementTree as ET
import os
from os import getcwd

sets = ['train', 'val', 'test']
classes = ['advertising', 'bike', 'electric-vehicle', 'person'] # 根据标签名称填写类别
abs_path = os.getcwd()
print(abs_path)


def convert(size, box):
    dw = 1. / (size[0])
    dh = 1. / (size[1])
    x = (box[0] + box[1]) / 2.0 - 1
    y = (box[2] + box[3]) / 2.0 - 1
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x * dw
    w = w * dw
    y = y * dh
    h = h * dh
    return x, y, w, h


def convert_annotation(image_id):
    in_file = open('data/Annotations/%s.xml' % (image_id), encoding='UTF-8')
    out_file = open('data/labels/%s.txt' % (image_id), 'w')
    tree = ET.parse(in_file)
    root = tree.getroot()
    size = root.find('size')
    w = int(size.find('width').text)
    h = int(size.find('height').text)
    for obj in root.iter('object'):
        difficult = obj.find('difficult').text
        cls = obj.find('name').text
        if cls not in classes or int(difficult) == 1:
            continue
        cls_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))
        b1, b2, b3, b4 = b
        # 标注越界修正
        if b2 > w:
            b2 = w
        if b4 > h:
            b4 = h
        b = (b1, b2, b3, b4)
        bb = convert((w, h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')


wd = getcwd()
for image_set in sets:
    if not os.path.exists('data/labels/'):
        os.makedirs('data/labels/')
    image_ids = open('data/ImageSets/%s.txt' % (image_set)).read().strip().split()
    list_file = open('data/%s.txt' % (image_set), 'w')
    for image_id in image_ids:
        list_file.write(abs_path + '/data/images/%s.jpg\n' % (image_id))
        convert_annotation(image_id)
    list_file.close()

train: data/train.txt
val: data/val.txt
test: data/test.txt

nc: 4
names: ['advertising', 'bike', 'electric-vehicle', 'person']

model = YOLO('yolov8s.pt')
results = model.train(data='data.yaml', epochs=200, imgsz=640, batch=16, workers=0)

yolo train data=data.yaml model=yolov8s.pt epochs=200 imgsz=640 batch=16 workers=0 device=0

import cv2
from ultralytics import YOLO

# Load the YOLOv8 model
model = YOLO("./best.pt") # 自定义预测模型加载路径

# Open the video file
video_path = "./demo.mp4" # 自定义预测视频路径
cap = cv2.VideoCapture(video_path) 

# Get the video properties
frame_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
frame_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
fps = cap.get(cv2.CAP_PROP_FPS)

# Define the codec and create VideoWriter object
fourcc = cv2.VideoWriter_fourcc(*'mp4v')  # Be sure to use lower case
out = cv2.VideoWriter('./outputs.mp4', fourcc, fps, (frame_width, frame_height)) # 自定义输出视频路径

# Loop through the video frames
while cap.isOpened():
    # Read a frame from the video
    success, frame = cap.read()

    if success:
        # Run YOLOv8 inference on the frame
        # results = model(frame)
        results = model.predict(source=frame, save=True, imgsz=640, conf=0.5)

        results[0].names[0] = "道路积水"
        # Visualize the results on the frame
        annotated_frame = results[0].plot()

        # Write the annotated frame to the output file
        out.write(annotated_frame)

        # Display the annotated frame (optional)
        cv2.imshow("YOLOv8 Inference", annotated_frame)

        # Break the loop if 'q' is pressed
        if cv2.waitKey(1) & 0xFF == ord("q"):
            break
    else:
        # Break the loop if the end of the video is reached
        break

# Release the video capture and writer objects
cap.release()
out.release()
cv2.destroyAllWindows()

yolo predict model="best.pt" source='demo.jpg'

# 安装torch环境
pip install torch -i https://pypi.tuna.tsinghua.edu.cn/simple
# 安装PySide6依赖项
pip install PySide6 -i https://pypi.tuna.tsinghua.edu.cn/simple
# 安装opencv-python依赖项
pip install opencv-python -i https://pypi.tuna.tsinghua.edu.cn/simple

class MyWindow(QtWidgets.QMainWindow):
    def __init__(self):
        super().__init__()

        self.init_gui()
        self.model = None
        self.timer = QtCore.QTimer()
        self.timer1 = QtCore.QTimer()
        self.cap = None
        self.video = None
        self.file_path = None
        self.base_name = None
        self.timer1.timeout.connect(self.video_show)

    def init_gui(self):
        self.folder_path = "model_file"  # 自定义修改：设置文件夹路径
        self.setFixedSize(1300, 650)
        self.setWindowTitle('目标检测')  # 自定义修改：设置窗口名称
        self.setWindowIcon(QIcon("111.jpg"))  # 自定义修改：设置窗口图标
        central_widget = QtWidgets.QWidget(self)
        self.setCentralWidget(central_widget)
        main_layout = QtWidgets.QVBoxLayout(central_widget)

        # 界面上半部分： 视频框
        topLayout = QtWidgets.QHBoxLayout()
        self.oriVideoLabel = QtWidgets.QLabel(self)
        
        # 界面下半部分： 输出框 和 按钮
        groupBox = QtWidgets.QGroupBox(self)
        groupBox.setStyleSheet('QGroupBox {border: 0px solid #D7E2F9;}')
        bottomLayout = QtWidgets.QHBoxLayout(groupBox)
        main_layout.addWidget(groupBox)
        btnLayout = QtWidgets.QHBoxLayout()
        btn1Layout = QtWidgets.QVBoxLayout()
        btn2Layout = QtWidgets.QVBoxLayout()
        btn3Layout = QtWidgets.QVBoxLayout()

        # 创建日志打印文本框
        self.outputField = QtWidgets.QTextBrowser()
        self.outputField.setFixedSize(530, 180)
        self.outputField.setStyleSheet('font-size: 13px; font-family: "Microsoft YaHei"; background-color: #f0f0f0; border: 2px solid #ccc; border-radius: 10px;')
        self.detectlabel = QtWidgets.QLabel(self)
        self.oriVideoLabel.setFixedSize(530, 400)
        self.detectlabel.setFixedSize(530, 400)
        self.oriVideoLabel.setStyleSheet('border: 2px solid #ccc; border-radius: 10px; margin-top:75px;')
        self.detectlabel.setStyleSheet('border: 2px solid #ccc; border-radius: 10px; margin-top: 75px;')
        topLayout.addWidget(self.oriVideoLabel)
        topLayout.addWidget(self.detectlabel)
        main_layout.addLayout(topLayout)