├── LICENSE ├── README.md ├── config ├── fold.json ├── id.json ├── ip.json └── setting.json ├── main.py ├── requirements.txt ├── ui ├── CustomMessageBox.py ├── UIFunctions.py ├── __pycache__ │ ├── CustomMessageBox.cpython-39.pyc │ ├── UIFunctions.cpython-39.pyc │ ├── cmp_res.cpython-39.pyc │ ├── custom_grips.cpython-39.pyc │ ├── home.cpython-39.pyc │ ├── mainwindow.cpython-39.pyc │ └── resources_rc.cpython-39.pyc ├── cmp_res.py ├── custom_grips.py ├── mainwindow.py └── rtsp_dialog.ui ├── ultralytics ├── __init__.py ├── assets │ ├── bus.jpg │ └── zidane.jpg ├── datasets │ ├── Argoverse.yaml │ ├── GlobalWheat2020.yaml │ ├── ImageNet.yaml │ ├── Objects365.yaml │ ├── SKU-110K.yaml │ ├── VOC.yaml │ ├── VisDrone.yaml │ ├── coco-pose.yaml │ ├── coco.yaml │ ├── coco128-seg.yaml │ ├── coco128.yaml │ ├── coco8-pose.yaml │ ├── coco8-seg.yaml │ ├── coco8.yaml │ └── xView.yaml ├── hub │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-39.pyc │ │ ├── auth.cpython-39.pyc │ │ ├── session.cpython-39.pyc │ │ └── utils.cpython-39.pyc │ ├── auth.py │ ├── session.py │ └── utils.py ├── models │ ├── v3 │ │ ├── yolov3-spp.yaml │ │ ├── yolov3-tiny.yaml │ │ └── yolov3.yaml │ ├── v5 │ │ ├── yolov5-p6.yaml │ │ └── yolov5.yaml │ └── v8 │ │ ├── yolov8-cls.yaml │ │ ├── yolov8-p2.yaml │ │ ├── yolov8-p6.yaml │ │ ├── yolov8-pose-p6.yaml │ │ ├── yolov8-pose.yaml │ │ ├── yolov8-seg.yaml │ │ └── yolov8.yaml ├── nn │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-39.pyc │ │ ├── autobackend.cpython-39.pyc │ │ ├── autoshape.cpython-39.pyc │ │ ├── modules.cpython-39.pyc │ │ └── tasks.cpython-39.pyc │ ├── autobackend.py │ ├── autoshape.py │ ├── modules.py │ └── tasks.py ├── tracker │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-39.pyc │ │ └── track.cpython-39.pyc │ ├── cfg │ │ ├── botsort.yaml │ │ └── bytetrack.yaml │ ├── track.py │ ├── trackers │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-39.pyc │ │ │ ├── basetrack.cpython-39.pyc │ │ │ ├── bot_sort.cpython-39.pyc │ │ │ └── byte_tracker.cpython-39.pyc │ │ ├── basetrack.py │ │ ├── bot_sort.py │ │ └── byte_tracker.py │ └── utils │ │ ├── __init__.py │ │ ├── __pycache__ │ │ ├── __init__.cpython-39.pyc │ │ ├── gmc.cpython-39.pyc │ │ ├── kalman_filter.cpython-39.pyc │ │ └── matching.cpython-39.pyc │ │ ├── gmc.py │ │ ├── kalman_filter.py │ │ └── matching.py └── yolo │ ├── __init__.py │ ├── cfg │ ├── __init__.py │ ├── __pycache__ │ │ └── __init__.cpython-39.pyc │ └── default.yaml │ ├── data │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-39.pyc │ │ ├── augment.cpython-39.pyc │ │ ├── base.cpython-39.pyc │ │ ├── build.cpython-39.pyc │ │ ├── dataset.cpython-39.pyc │ │ ├── dataset_wrappers.cpython-39.pyc │ │ └── utils.cpython-39.pyc │ ├── augment.py │ ├── base.py │ ├── build.py │ ├── dataloaders │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-39.pyc │ │ │ ├── stream_loaders.cpython-39.pyc │ │ │ ├── v5augmentations.cpython-39.pyc │ │ │ └── v5loader.cpython-39.pyc │ │ ├── stream_loaders.py │ │ ├── v5augmentations.py │ │ └── v5loader.py │ ├── dataset.py │ ├── dataset_wrappers.py │ └── utils.py │ ├── engine │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-39.pyc │ │ ├── exporter.cpython-39.pyc │ │ ├── model.cpython-39.pyc │ │ ├── predictor.cpython-39.pyc │ │ ├── results.cpython-39.pyc │ │ ├── trainer.cpython-39.pyc │ │ └── validator.cpython-39.pyc │ ├── exporter.py │ ├── model.py │ ├── predictor.py │ ├── results.py │ ├── trainer.py │ └── validator.py │ ├── utils │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-39.pyc │ │ ├── autobatch.cpython-39.pyc │ │ ├── benchmarks.cpython-39.pyc │ │ ├── checks.cpython-39.pyc │ │ ├── dist.cpython-39.pyc │ │ ├── downloads.cpython-39.pyc │ │ ├── files.cpython-39.pyc │ │ ├── instance.cpython-39.pyc │ │ ├── loss.cpython-39.pyc │ │ ├── metrics.cpython-39.pyc │ │ ├── ops.cpython-39.pyc │ │ ├── plotting.cpython-39.pyc │ │ ├── tal.cpython-39.pyc │ │ └── torch_utils.cpython-39.pyc │ ├── autobatch.py │ ├── benchmarks.py │ ├── callbacks │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-39.pyc │ │ │ ├── base.cpython-39.pyc │ │ │ ├── clearml.cpython-39.pyc │ │ │ ├── comet.cpython-39.pyc │ │ │ ├── hub.cpython-39.pyc │ │ │ ├── mlflow.cpython-39.pyc │ │ │ └── tensorboard.cpython-39.pyc │ │ ├── base.py │ │ ├── clearml.py │ │ ├── comet.py │ │ ├── hub.py │ │ ├── mlflow.py │ │ └── tensorboard.py │ ├── checks.py │ ├── dist.py │ ├── downloads.py │ ├── files.py │ ├── instance.py │ ├── loss.py │ ├── metrics.py │ ├── ops.py │ ├── plotting.py │ ├── tal.py │ └── torch_utils.py │ └── v8 │ ├── __init__.py │ ├── __pycache__ │ └── __init__.cpython-39.pyc │ ├── classify │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-39.pyc │ │ ├── predict.cpython-39.pyc │ │ ├── train.cpython-39.pyc │ │ └── val.cpython-39.pyc │ ├── predict.py │ ├── train.py │ └── val.py │ ├── detect │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-39.pyc │ │ ├── predict.cpython-39.pyc │ │ ├── train.cpython-39.pyc │ │ └── val.cpython-39.pyc │ ├── predict.py │ ├── train.py │ └── val.py │ ├── pose │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-39.pyc │ │ ├── predict.cpython-39.pyc │ │ ├── train.cpython-39.pyc │ │ └── val.cpython-39.pyc │ ├── predict.py │ ├── train.py │ └── val.py │ └── segment │ ├── __init__.py │ ├── __pycache__ │ ├── __init__.cpython-39.pyc │ ├── predict.cpython-39.pyc │ ├── train.cpython-39.pyc │ └── val.cpython-39.pyc │ ├── predict.py │ ├── train.py │ └── val.py ├── utils ├── __pycache__ │ ├── capnums.cpython-39.pyc │ ├── id_dialog.cpython-39.pyc │ ├── id_win.cpython-39.pyc │ ├── rtsp_dialog.cpython-39.pyc │ └── rtsp_win.cpython-39.pyc ├── capnums.py ├── id_dialog.py ├── id_win.py ├── rtsp_dialog.py ├── rtsp_win.py └── video_transform.py └── weights └── 轻量级模型.pt /README.md: -------------------------------------------------------------------------------- 1 | ## 基于YOLOv8与Qt的多目标跟踪智能交通路况监控系统 2 | # 1.演示视频 3 | https://www.bilibili.com/video/BV1yX4y1m7Fe/?spm_id_from=333.999.0.0
4 | https://youtu.be/_77LrsXaYzM 5 | # 2.安装（INSTALL) 6 | ## 第一步（FIRST STEP) 安装ANACONDA
7 | 1）访问Anaconda官网：https://www.anaconda.com/products/individual
8 | 2）选择相应的操作系统版本并下载对应的安装包（推荐下载64位版本）
9 | 3）打开下载的安装包，按照提示进行安装即可
10 | 4）创建一个虚拟环境：
11 | conda create --name 自命名 python=3.9.16
12 |
13 | ## 第二步（SECOND STEP) pip install -r requirements.txt
14 | 激活环境并安装相应的库： activate 自命名-> pip install -r requirements.txt
15 | 这一步会安装cpu版本的torch与torchvision，如果想要更好的帧数体验请安装cuda版本哦，安装cuda版本很简单，首先要有英伟达显卡，其次nvdia-smi查看cuda driver驱动版本号，上英伟达官网选择对应cuda版本号的cuda套件安装，最后去torch官网选择自己安装的cuda套件版本使用conda或者pip安装即可。
16 | # 3.运行 17 | 配置好环境后在含有main.py的工作目录下运行main.py即可，也可以下载以下链接里的压缩包使用exe文件运行：
18 | https://pan.baidu.com/s/1U9dskWzOouF4y1_s7KnPfg?pwd=Zlad 提取码: Zlad 19 | 20 | ## Multi-Object Tracking Intelligent Traffic Monitoring System based on YOLOv8 and Qt 21 | 22 | # 1. Demo Video 23 | https://www.bilibili.com/video/BV1yX4y1m7Fe/?spm_id_from=333.999.0.0
24 | https://youtu.be/_77LrsXaYzM 25 | 26 | # 2. Installation 27 | ## First Step: Install Anaconda 28 | 1) Visit the Anaconda official website: https://www.anaconda.com/products/individual
29 | 2) Select the appropriate operating system version and download the corresponding installation package (it is recommended to download the 64-bit version)
30 | 3) Open the downloaded installation package and follow the prompts to install it
31 | 4) Create a virtual environment:
32 | conda create --name your_env_name python=3.19.16
33 | 34 | ## Second Step: pip install -r requirements.txt 35 | Activate the environment and install the required libraries:
36 | activate your_env_name -> pip install -r requirements.txt
37 | 38 | This step will install the CPU version of torch and torchvision. If you want a better frame rate experience, please install the CUDA version. Installing the CUDA version is very simple. First, you need an NVIDIA graphics card. Next, use nvidia-smi to check the version number of the CUDA driver. Then, select the corresponding CUDA package version according to the CUDA driver version number on the NVIDIA official website, and finally, choose the CUDA package version you installed and use conda or pip to install it on the torch official website. 39 | 40 | # 3. Running 41 | After configuring the environment, run main.py in the working directory that contains the file. You can also download the compressed package from the following link and use the exe file to run it:
42 | https://pan.baidu.com/s/1U9dskWzOouF4y1_s7KnPfg?pwd=Zlad Password: Zlad 43 | 44 | ## 参考(REFERENCE) 45 | https://github.com/Jai-wei/YOLOv8-PySide6-GUI
46 | https://github.com/ultralytics/ultralytics
47 | https://doc.qt.io/qtforpython-6/ 48 | 49 | 50 | 51 | 52 | 53 | 54 | -------------------------------------------------------------------------------- /config/fold.json: -------------------------------------------------------------------------------- 1 | { 2 | "open_fold": "D:/" 3 | } 4 | -------------------------------------------------------------------------------- /config/id.json: -------------------------------------------------------------------------------- 1 | { 2 | "id": "2" 3 | } -------------------------------------------------------------------------------- /config/ip.json: -------------------------------------------------------------------------------- 1 | { 2 | "ip": "rtsp://admin:admin@192.168.0.103:8554/live" 3 | } -------------------------------------------------------------------------------- /config/setting.json: -------------------------------------------------------------------------------- 1 | { 2 | "iou": 0.45, 3 | "conf": 0.25, 4 | "rate": 10, 5 | "save_res": 2, 6 | "save_txt": 2 7 | } -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | #win+r ->cmd->cd-> pip install -r requirements.txt 2 | matplotlib>=3.2.2 3 | opencv-python>=4.6.0 4 | numpy>=1.24.3 5 | Pillow>=7.1.2 6 | PyYAML>=5.3.1 7 | requests>=2.23.0 8 | scipy>=1.4.1 9 | torch>=1.7.0 # install cuda version for better fps performance 10 | torchvision>=0.8.1 # install cuda version for better fps performance 11 | tqdm>=4.64.0 12 | supervision>=0.6.0 13 | psutil>=5.9.5 14 | thop>=0.1.1 15 | PySide6>=6.4.2 16 | pandas>=2.0.1 17 | lap>=0.4 -------------------------------------------------------------------------------- /ui/CustomMessageBox.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | # @Author : CatfishW🚀 3 | # @Time : 2023/5/1 4 | from PySide6.QtCore import QTimer, Qt 5 | from PySide6.QtWidgets import QMessageBox 6 | from PySide6.QtGui import QPixmap, QIcon 7 | 8 | 9 | # Single-button dialog box, which disappears automatically after appearing for a specified period of time 10 | class MessageBox(QMessageBox): 11 | def __init__(self, *args, title='提示', count=1, time=1000, auto=False, **kwargs): 12 | super(MessageBox, self).__init__(*args, **kwargs) 13 | self._count = count 14 | self._time = time 15 | self._auto = auto # Whether to close automatically 16 | assert count > 0 # must be greater than 0 17 | assert time >= 500 # Must be >=500 milliseconds 18 | self.setStyleSheet(''' 19 | QWidget{color:black; 20 | background-color: qlineargradient(x0:0, y0:1, x1:1, y1:1,stop:0.4 rgb(0,205,102),stop:1 rgb(0 205 102)); 21 | font: 13pt "Microsoft YaHei UI"; 22 | padding-right: 5px; 23 | padding-top: 14px; 24 | font-weight: light;} 25 | QLabel{ 26 | color:white; 27 | background-color: rgba(107, 128, 210, 0);}''') 28 | 29 | self.setWindowTitle(title) 30 | 31 | self.setStandardButtons(QMessageBox.StandardButton.Close) # close button 32 | self.closeBtn = self.button(QMessageBox.StandardButton.Close) # get close button 33 | self.closeBtn.setText('Close') 34 | self.closeBtn.setVisible(False) 35 | self._timer = QTimer(self, timeout=self.doCountDown) 36 | self._timer.start(self._time) 37 | 38 | def doCountDown(self): 39 | self._count -= 1 40 | if self._count <= 0: 41 | self._timer.stop() 42 | if self._auto: # auto close 43 | self.accept() 44 | self.close() 45 | 46 | if __name__ == '__main__': 47 | MessageBox(QWidget=None, text='123', auto=True).exec() 48 | -------------------------------------------------------------------------------- /ui/UIFunctions.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | # @Author : CatfishW🚀 3 | # @Time : 2023/5/1 4 | from main import * 5 | from ui.custom_grips import CustomGrip 6 | from PySide6.QtCore import QPropertyAnimation, QEasingCurve, QEvent, QTimer 7 | from PySide6.QtCore import * 8 | from PySide6.QtGui import * 9 | from PySide6.QtWidgets import * 10 | import time 11 | 12 | GLOBAL_STATE = False # max min flag 13 | GLOBAL_TITLE_BAR = True 14 | 15 | 16 | class UIFuncitons(MainWindow): 17 | #展开左菜单 18 | def toggleMenu(self, enable): 19 | if enable: 20 | standard = 68 21 | maxExtend = 180 22 | width = self.LeftMenuBg.width() 23 | 24 | if width == 68: 25 | widthExtended = maxExtend 26 | else: 27 | widthExtended = standard 28 | 29 | #Qt动画 30 | self.animation = QPropertyAnimation(self.LeftMenuBg, b"minimumWidth") 31 | self.animation.setDuration(500) # ms 32 | self.animation.setStartValue(width) 33 | self.animation.setEndValue(widthExtended) 34 | self.animation.setEasingCurve(QEasingCurve.InOutQuint) 35 | self.animation.start() 36 | 37 | #展开右菜单 38 | def settingBox(self, enable): 39 | if enable: 40 | #获取宽度 41 | widthRightBox = self.prm_page.width() # right set column width 42 | widthLeftBox = self.LeftMenuBg.width() # left column length 43 | maxExtend = 220 44 | standard = 0 45 | 46 | #设置最大宽度 47 | if widthRightBox == 0: 48 | widthExtended = maxExtend 49 | else: 50 | widthExtended = standard 51 | 52 | #左菜单的动画 53 | self.left_box = QPropertyAnimation(self.LeftMenuBg, b"minimumWidth") 54 | self.left_box.setDuration(500) 55 | self.left_box.setStartValue(widthLeftBox) 56 | self.left_box.setEndValue(68) 57 | self.left_box.setEasingCurve(QEasingCurve.InOutQuart) 58 | 59 | #设置界面的动画 60 | self.right_box = QPropertyAnimation(self.prm_page, b"minimumWidth") 61 | self.right_box.setDuration(500) 62 | self.right_box.setStartValue(widthRightBox) 63 | self.right_box.setEndValue(widthExtended) 64 | self.right_box.setEasingCurve(QEasingCurve.InOutQuart) 65 | 66 | #并行动画 67 | self.group = QParallelAnimationGroup() 68 | self.group.addAnimation(self.left_box) 69 | self.group.addAnimation(self.right_box) 70 | self.group.start() 71 | 72 | #最大化窗口 73 | def maximize_restore(self): 74 | global GLOBAL_STATE 75 | status = GLOBAL_STATE 76 | if status == False: 77 | GLOBAL_STATE = True 78 | self.showMaximized() #最大化 79 | self.max_sf.setToolTip("Restore") 80 | self.frame_size_grip.hide() 81 | self.left_grip.hide() 82 | self.right_grip.hide() 83 | self.top_grip.hide() 84 | self.bottom_grip.hide() 85 | else: 86 | GLOBAL_STATE = False 87 | self.showNormal() #最小化 88 | self.resize(self.width()+1, self.height()+1) 89 | self.max_sf.setToolTip("Maximize") 90 | self.frame_size_grip.show() 91 | self.left_grip.show() 92 | self.right_grip.show() 93 | self.top_grip.show() 94 | self.bottom_grip.show() 95 | 96 | # window control 97 | def uiDefinitions(self): 98 | # Double-click the title bar to maximize 99 | def dobleClickMaximizeRestore(event): 100 | if event.type() == QEvent.MouseButtonDblClick: 101 | QTimer.singleShot(250, lambda: UIFuncitons.maximize_restore(self)) 102 | self.top.mouseDoubleClickEvent = dobleClickMaximizeRestore 103 | 104 | # MOVE WINDOW / MAXIMIZE / RESTORE 105 | def moveWindow(event): 106 | if GLOBAL_STATE: # IF MAXIMIZED CHANGE TO NORMAL 107 | UIFuncitons.maximize_restore(self) 108 | if event.buttons() == Qt.LeftButton: # MOVE 109 | self.move(self.pos() + event.globalPos() - self.dragPos) 110 | self.dragPos = event.globalPos() 111 | self.top.mouseMoveEvent = moveWindow 112 | # CUSTOM GRIPS 113 | self.left_grip = CustomGrip(self, Qt.LeftEdge, True) 114 | self.right_grip = CustomGrip(self, Qt.RightEdge, True) 115 | self.top_grip = CustomGrip(self, Qt.TopEdge, True) 116 | self.bottom_grip = CustomGrip(self, Qt.BottomEdge, True) 117 | 118 | # MINIMIZE 119 | self.min_sf.clicked.connect(lambda: self.showMinimized()) 120 | # MAXIMIZE/RESTORE 121 | self.max_sf.clicked.connect(lambda: UIFuncitons.maximize_restore(self)) 122 | # CLOSE APPLICATION 123 | self.close_button.clicked.connect(self.close) 124 | 125 | # Control the stretching of the four sides of the window 126 | def resize_grips(self): 127 | self.left_grip.setGeometry(0, 10, 10, self.height()) 128 | self.right_grip.setGeometry(self.width() - 10, 10, 10, self.height()) 129 | self.top_grip.setGeometry(0, 0, self.width(), 10) 130 | self.bottom_grip.setGeometry(0, self.height() - 10, self.width(), 10) 131 | 132 | # Show module to add shadow 133 | def shadow_style(self, widget, Color): 134 | shadow = QGraphicsDropShadowEffect(self) 135 | shadow.setOffset(8, 8) # offset 136 | shadow.setBlurRadius(38) # shadow radius 137 | shadow.setColor(Color) # shadow color 138 | widget.setGraphicsEffect(shadow) -------------------------------------------------------------------------------- /ui/__pycache__/CustomMessageBox.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ui/__pycache__/CustomMessageBox.cpython-39.pyc -------------------------------------------------------------------------------- /ui/__pycache__/UIFunctions.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ui/__pycache__/UIFunctions.cpython-39.pyc -------------------------------------------------------------------------------- /ui/__pycache__/cmp_res.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ui/__pycache__/cmp_res.cpython-39.pyc -------------------------------------------------------------------------------- /ui/__pycache__/custom_grips.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ui/__pycache__/custom_grips.cpython-39.pyc -------------------------------------------------------------------------------- /ui/__pycache__/home.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ui/__pycache__/home.cpython-39.pyc -------------------------------------------------------------------------------- /ui/__pycache__/mainwindow.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ui/__pycache__/mainwindow.cpython-39.pyc -------------------------------------------------------------------------------- /ui/__pycache__/resources_rc.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ui/__pycache__/resources_rc.cpython-39.pyc -------------------------------------------------------------------------------- /ui/rtsp_dialog.ui: -------------------------------------------------------------------------------- 1 | 2 | 3 | Form 4 | 5 | 6 | 7 | 0 8 | 0 9 | 783 10 | 40 11 | 12 | 13 | 14 | 15 | 0 16 | 40 17 | 18 | 19 | 20 | 21 | 16777215 22 | 41 23 | 24 | 25 | 26 | Form 27 | 28 | 29 | 30 | :/img/icon/实时视频流解析.png:/img/icon/实时视频流解析.png 31 | 32 | 33 | #Form{background:rgba(120,120,120,255)} 34 | 35 | 36 | 37 | 5 38 | 39 | 40 | 5 41 | 42 | 43 | 44 | 45 | 46 | 0 47 | 30 48 | 49 | 50 | 51 | 52 | 16777215 53 | 30 54 | 55 | 56 | 57 | QLabel{font-family: "Microsoft YaHei"; 58 | font-size: 18px; 59 | font-weight: bold; 60 | color:white;} 61 | 62 | 63 | rtsp address: 64 | 65 | 66 | 67 | 68 | 69 | 70 | 71 | 0 72 | 31 73 | 74 | 75 | 76 | background-color: rgb(207, 207, 207); 77 | 78 | 79 | 80 | 81 | 82 | 83 | QPushButton{font-family: "Microsoft YaHei"; 84 | font-size: 18px; 85 | font-weight: bold; 86 | color:white; 87 | text-align: center center; 88 | padding-left: 5px; 89 | padding-right: 5px; 90 | padding-top: 4px; 91 | padding-bottom: 4px; 92 | border-style: solid; 93 | border-width: 0px; 94 | border-color: rgba(255, 255, 255, 255); 95 | border-radius: 3px; 96 | background-color: rgba(255,255,255,30);} 97 | 98 | QPushButton:focus{outline: none;} 99 | 100 | QPushButton::pressed{font-family: "Microsoft YaHei"; 101 | font-size: 16px; 102 | font-weight: bold; 103 | color:rgb(200,200,200); 104 | text-align: center center; 105 | padding-left: 5px; 106 | padding-right: 5px; 107 | padding-top: 4px; 108 | padding-bottom: 4px; 109 | border-style: solid; 110 | border-width: 0px; 111 | border-color: rgba(255, 255, 255, 255); 112 | border-radius: 3px; 113 | background-color: rgba(255,255,255,150);} 114 | 115 | QPushButton::hover { 116 | border-style: solid; 117 | border-width: 0px; 118 | border-radius: 0px; 119 | background-color: rgba(255,255,255,50);} 120 | 121 | 122 | confirm 123 | 124 | 125 | 126 | 127 | 128 | 129 | 130 | 131 | 132 | 133 | -------------------------------------------------------------------------------- /ultralytics/__init__.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | __version__ = '8.0.75' 4 | 5 | from ultralytics.hub import start 6 | from ultralytics.yolo.engine.model import YOLO 7 | from ultralytics.yolo.utils.checks import check_yolo as checks 8 | 9 | __all__ = '__version__', 'YOLO', 'checks', 'start' # allow simpler import 10 | -------------------------------------------------------------------------------- /ultralytics/assets/bus.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/assets/bus.jpg -------------------------------------------------------------------------------- /ultralytics/assets/zidane.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/assets/zidane.jpg -------------------------------------------------------------------------------- /ultralytics/datasets/Argoverse.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | # Argoverse-HD dataset (ring-front-center camera) http://www.cs.cmu.edu/~mengtial/proj/streaming/ by Argo AI 3 | # Example usage: yolo train data=Argoverse.yaml 4 | # parent 5 | # ├── ultralytics 6 | # └── datasets 7 | # └── Argoverse ← downloads here (31.3 GB) 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/Argoverse # dataset root dir 12 | train: Argoverse-1.1/images/train/ # train images (relative to 'path') 39384 images 13 | val: Argoverse-1.1/images/val/ # val images (relative to 'path') 15062 images 14 | test: Argoverse-1.1/images/test/ # test images (optional) https://eval.ai/web/challenges/challenge-page/800/overview 15 | 16 | # Classes 17 | names: 18 | 0: person 19 | 1: bicycle 20 | 2: car 21 | 3: motorcycle 22 | 4: bus 23 | 5: truck 24 | 6: traffic_light 25 | 7: stop_sign 26 | 27 | 28 | # Download script/URL (optional) --------------------------------------------------------------------------------------- 29 | download: | 30 | import json 31 | from tqdm import tqdm 32 | from ultralytics.yolo.utils.downloads import download 33 | from pathlib import Path 34 | 35 | def argoverse2yolo(set): 36 | labels = {} 37 | a = json.load(open(set, "rb")) 38 | for annot in tqdm(a['annotations'], desc=f"Converting {set} to YOLOv5 format..."): 39 | img_id = annot['image_id'] 40 | img_name = a['images'][img_id]['name'] 41 | img_label_name = f'{img_name[:-3]}txt' 42 | 43 | cls = annot['category_id'] # instance class id 44 | x_center, y_center, width, height = annot['bbox'] 45 | x_center = (x_center + width / 2) / 1920.0 # offset and scale 46 | y_center = (y_center + height / 2) / 1200.0 # offset and scale 47 | width /= 1920.0 # scale 48 | height /= 1200.0 # scale 49 | 50 | img_dir = set.parents[2] / 'Argoverse-1.1' / 'labels' / a['seq_dirs'][a['images'][annot['image_id']]['sid']] 51 | if not img_dir.exists(): 52 | img_dir.mkdir(parents=True, exist_ok=True) 53 | 54 | k = str(img_dir / img_label_name) 55 | if k not in labels: 56 | labels[k] = [] 57 | labels[k].append(f"{cls} {x_center} {y_center} {width} {height}\n") 58 | 59 | for k in labels: 60 | with open(k, "w") as f: 61 | f.writelines(labels[k]) 62 | 63 | 64 | # Download 65 | dir = Path(yaml['path']) # dataset root dir 66 | urls = ['https://argoverse-hd.s3.us-east-2.amazonaws.com/Argoverse-HD-Full.zip'] 67 | download(urls, dir=dir) 68 | 69 | # Convert 70 | annotations_dir = 'Argoverse-HD/annotations/' 71 | (dir / 'Argoverse-1.1' / 'tracking').rename(dir / 'Argoverse-1.1' / 'images') # rename 'tracking' to 'images' 72 | for d in "train.json", "val.json": 73 | argoverse2yolo(dir / annotations_dir / d) # convert VisDrone annotations to YOLO labels 74 | -------------------------------------------------------------------------------- /ultralytics/datasets/GlobalWheat2020.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | # Global Wheat 2020 dataset http://www.global-wheat.com/ by University of Saskatchewan 3 | # Example usage: yolo train data=GlobalWheat2020.yaml 4 | # parent 5 | # ├── ultralytics 6 | # └── datasets 7 | # └── GlobalWheat2020 ← downloads here (7.0 GB) 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/GlobalWheat2020 # dataset root dir 12 | train: # train images (relative to 'path') 3422 images 13 | - images/arvalis_1 14 | - images/arvalis_2 15 | - images/arvalis_3 16 | - images/ethz_1 17 | - images/rres_1 18 | - images/inrae_1 19 | - images/usask_1 20 | val: # val images (relative to 'path') 748 images (WARNING: train set contains ethz_1) 21 | - images/ethz_1 22 | test: # test images (optional) 1276 images 23 | - images/utokyo_1 24 | - images/utokyo_2 25 | - images/nau_1 26 | - images/uq_1 27 | 28 | # Classes 29 | names: 30 | 0: wheat_head 31 | 32 | 33 | # Download script/URL (optional) --------------------------------------------------------------------------------------- 34 | download: | 35 | from ultralytics.yolo.utils.downloads import download 36 | from pathlib import Path 37 | 38 | # Download 39 | dir = Path(yaml['path']) # dataset root dir 40 | urls = ['https://zenodo.org/record/4298502/files/global-wheat-codalab-official.zip', 41 | 'https://github.com/ultralytics/yolov5/releases/download/v1.0/GlobalWheat2020_labels.zip'] 42 | download(urls, dir=dir) 43 | 44 | # Make Directories 45 | for p in 'annotations', 'images', 'labels': 46 | (dir / p).mkdir(parents=True, exist_ok=True) 47 | 48 | # Move 49 | for p in 'arvalis_1', 'arvalis_2', 'arvalis_3', 'ethz_1', 'rres_1', 'inrae_1', 'usask_1', \ 50 | 'utokyo_1', 'utokyo_2', 'nau_1', 'uq_1': 51 | (dir / p).rename(dir / 'images' / p) # move to /images 52 | f = (dir / p).with_suffix('.json') # json file 53 | if f.exists(): 54 | f.rename((dir / 'annotations' / p).with_suffix('.json')) # move to /annotations 55 | -------------------------------------------------------------------------------- /ultralytics/datasets/SKU-110K.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | # SKU-110K retail items dataset https://github.com/eg4000/SKU110K_CVPR19 by Trax Retail 3 | # Example usage: yolo train data=SKU-110K.yaml 4 | # parent 5 | # ├── ultralytics 6 | # └── datasets 7 | # └── SKU-110K ← downloads here (13.6 GB) 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/SKU-110K # dataset root dir 12 | train: train.txt # train images (relative to 'path') 8219 images 13 | val: val.txt # val images (relative to 'path') 588 images 14 | test: test.txt # test images (optional) 2936 images 15 | 16 | # Classes 17 | names: 18 | 0: object 19 | 20 | 21 | # Download script/URL (optional) --------------------------------------------------------------------------------------- 22 | download: | 23 | import shutil 24 | from pathlib import Path 25 | 26 | import numpy as np 27 | import pandas as pd 28 | from tqdm import tqdm 29 | 30 | from ultralytics.yolo.utils.downloads import download 31 | from ultralytics.yolo.utils.ops import xyxy2xywh 32 | 33 | # Download 34 | dir = Path(yaml['path']) # dataset root dir 35 | parent = Path(dir.parent) # download dir 36 | urls = ['http://trax-geometry.s3.amazonaws.com/cvpr_challenge/SKU110K_fixed.tar.gz'] 37 | download(urls, dir=parent) 38 | 39 | # Rename directories 40 | if dir.exists(): 41 | shutil.rmtree(dir) 42 | (parent / 'SKU110K_fixed').rename(dir) # rename dir 43 | (dir / 'labels').mkdir(parents=True, exist_ok=True) # create labels dir 44 | 45 | # Convert labels 46 | names = 'image', 'x1', 'y1', 'x2', 'y2', 'class', 'image_width', 'image_height' # column names 47 | for d in 'annotations_train.csv', 'annotations_val.csv', 'annotations_test.csv': 48 | x = pd.read_csv(dir / 'annotations' / d, names=names).values # annotations 49 | images, unique_images = x[:, 0], np.unique(x[:, 0]) 50 | with open((dir / d).with_suffix('.txt').__str__().replace('annotations_', ''), 'w') as f: 51 | f.writelines(f'./images/{s}\n' for s in unique_images) 52 | for im in tqdm(unique_images, desc=f'Converting {dir / d}'): 53 | cls = 0 # single-class dataset 54 | with open((dir / 'labels' / im).with_suffix('.txt'), 'a') as f: 55 | for r in x[images == im]: 56 | w, h = r[6], r[7] # image width, height 57 | xywh = xyxy2xywh(np.array([[r[1] / w, r[2] / h, r[3] / w, r[4] / h]]))[0] # instance 58 | f.write(f"{cls} {xywh[0]:.5f} {xywh[1]:.5f} {xywh[2]:.5f} {xywh[3]:.5f}\n") # write label 59 | -------------------------------------------------------------------------------- /ultralytics/datasets/VOC.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | # PASCAL VOC dataset http://host.robots.ox.ac.uk/pascal/VOC by University of Oxford 3 | # Example usage: yolo train data=VOC.yaml 4 | # parent 5 | # ├── ultralytics 6 | # └── datasets 7 | # └── VOC ← downloads here (2.8 GB) 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/VOC 12 | train: # train images (relative to 'path') 16551 images 13 | - images/train2012 14 | - images/train2007 15 | - images/val2012 16 | - images/val2007 17 | val: # val images (relative to 'path') 4952 images 18 | - images/test2007 19 | test: # test images (optional) 20 | - images/test2007 21 | 22 | # Classes 23 | names: 24 | 0: aeroplane 25 | 1: bicycle 26 | 2: bird 27 | 3: boat 28 | 4: bottle 29 | 5: bus 30 | 6: car 31 | 7: cat 32 | 8: chair 33 | 9: cow 34 | 10: diningtable 35 | 11: dog 36 | 12: horse 37 | 13: motorbike 38 | 14: person 39 | 15: pottedplant 40 | 16: sheep 41 | 17: sofa 42 | 18: train 43 | 19: tvmonitor 44 | 45 | 46 | # Download script/URL (optional) --------------------------------------------------------------------------------------- 47 | download: | 48 | import xml.etree.ElementTree as ET 49 | 50 | from tqdm import tqdm 51 | from ultralytics.yolo.utils.downloads import download 52 | from pathlib import Path 53 | 54 | def convert_label(path, lb_path, year, image_id): 55 | def convert_box(size, box): 56 | dw, dh = 1. / size[0], 1. / size[1] 57 | x, y, w, h = (box[0] + box[1]) / 2.0 - 1, (box[2] + box[3]) / 2.0 - 1, box[1] - box[0], box[3] - box[2] 58 | return x * dw, y * dh, w * dw, h * dh 59 | 60 | in_file = open(path / f'VOC{year}/Annotations/{image_id}.xml') 61 | out_file = open(lb_path, 'w') 62 | tree = ET.parse(in_file) 63 | root = tree.getroot() 64 | size = root.find('size') 65 | w = int(size.find('width').text) 66 | h = int(size.find('height').text) 67 | 68 | names = list(yaml['names'].values()) # names list 69 | for obj in root.iter('object'): 70 | cls = obj.find('name').text 71 | if cls in names and int(obj.find('difficult').text) != 1: 72 | xmlbox = obj.find('bndbox') 73 | bb = convert_box((w, h), [float(xmlbox.find(x).text) for x in ('xmin', 'xmax', 'ymin', 'ymax')]) 74 | cls_id = names.index(cls) # class id 75 | out_file.write(" ".join([str(a) for a in (cls_id, *bb)]) + '\n') 76 | 77 | 78 | # Download 79 | dir = Path(yaml['path']) # dataset root dir 80 | url = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/' 81 | urls = [f'{url}VOCtrainval_06-Nov-2007.zip', # 446MB, 5012 images 82 | f'{url}VOCtest_06-Nov-2007.zip', # 438MB, 4953 images 83 | f'{url}VOCtrainval_11-May-2012.zip'] # 1.95GB, 17126 images 84 | download(urls, dir=dir / 'images', curl=True, threads=3) 85 | 86 | # Convert 87 | path = dir / 'images/VOCdevkit' 88 | for year, image_set in ('2012', 'train'), ('2012', 'val'), ('2007', 'train'), ('2007', 'val'), ('2007', 'test'): 89 | imgs_path = dir / 'images' / f'{image_set}{year}' 90 | lbs_path = dir / 'labels' / f'{image_set}{year}' 91 | imgs_path.mkdir(exist_ok=True, parents=True) 92 | lbs_path.mkdir(exist_ok=True, parents=True) 93 | 94 | with open(path / f'VOC{year}/ImageSets/Main/{image_set}.txt') as f: 95 | image_ids = f.read().strip().split() 96 | for id in tqdm(image_ids, desc=f'{image_set}{year}'): 97 | f = path / f'VOC{year}/JPEGImages/{id}.jpg' # old img path 98 | lb_path = (lbs_path / f.name).with_suffix('.txt') # new label path 99 | f.rename(imgs_path / f.name) # move image 100 | convert_label(path, lb_path, year, id) # convert labels to YOLO format 101 | -------------------------------------------------------------------------------- /ultralytics/datasets/VisDrone.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | # VisDrone2019-DET dataset https://github.com/VisDrone/VisDrone-Dataset by Tianjin University 3 | # Example usage: yolo train data=VisDrone.yaml 4 | # parent 5 | # ├── ultralytics 6 | # └── datasets 7 | # └── VisDrone ← downloads here (2.3 GB) 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/VisDrone # dataset root dir 12 | train: VisDrone2019-DET-train/images # train images (relative to 'path') 6471 images 13 | val: VisDrone2019-DET-val/images # val images (relative to 'path') 548 images 14 | test: VisDrone2019-DET-test-dev/images # test images (optional) 1610 images 15 | 16 | # Classes 17 | names: 18 | 0: pedestrian 19 | 1: people 20 | 2: bicycle 21 | 3: car 22 | 4: van 23 | 5: truck 24 | 6: tricycle 25 | 7: awning-tricycle 26 | 8: bus 27 | 9: motor 28 | 29 | 30 | # Download script/URL (optional) --------------------------------------------------------------------------------------- 31 | download: | 32 | import os 33 | from pathlib import Path 34 | 35 | from ultralytics.yolo.utils.downloads import download 36 | 37 | def visdrone2yolo(dir): 38 | from PIL import Image 39 | from tqdm import tqdm 40 | 41 | def convert_box(size, box): 42 | # Convert VisDrone box to YOLO xywh box 43 | dw = 1. / size[0] 44 | dh = 1. / size[1] 45 | return (box[0] + box[2] / 2) * dw, (box[1] + box[3] / 2) * dh, box[2] * dw, box[3] * dh 46 | 47 | (dir / 'labels').mkdir(parents=True, exist_ok=True) # make labels directory 48 | pbar = tqdm((dir / 'annotations').glob('*.txt'), desc=f'Converting {dir}') 49 | for f in pbar: 50 | img_size = Image.open((dir / 'images' / f.name).with_suffix('.jpg')).size 51 | lines = [] 52 | with open(f, 'r') as file: # read annotation.txt 53 | for row in [x.split(',') for x in file.read().strip().splitlines()]: 54 | if row[4] == '0': # VisDrone 'ignored regions' class 0 55 | continue 56 | cls = int(row[5]) - 1 57 | box = convert_box(img_size, tuple(map(int, row[:4]))) 58 | lines.append(f"{cls} {' '.join(f'{x:.6f}' for x in box)}\n") 59 | with open(str(f).replace(f'{os.sep}annotations{os.sep}', f'{os.sep}labels{os.sep}'), 'w') as fl: 60 | fl.writelines(lines) # write label.txt 61 | 62 | 63 | # Download 64 | dir = Path(yaml['path']) # dataset root dir 65 | urls = ['https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-train.zip', 66 | 'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-val.zip', 67 | 'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-test-dev.zip', 68 | 'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-test-challenge.zip'] 69 | download(urls, dir=dir, curl=True, threads=4) 70 | 71 | # Convert 72 | for d in 'VisDrone2019-DET-train', 'VisDrone2019-DET-val', 'VisDrone2019-DET-test-dev': 73 | visdrone2yolo(dir / d) # convert VisDrone annotations to YOLO labels 74 | -------------------------------------------------------------------------------- /ultralytics/datasets/coco-pose.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | # COCO 2017 dataset http://cocodataset.org by Microsoft 3 | # Example usage: yolo train data=coco-pose.yaml 4 | # parent 5 | # ├── ultralytics 6 | # └── datasets 7 | # └── coco-pose ← downloads here (20.1 GB) 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/coco-pose # dataset root dir 12 | train: train2017.txt # train images (relative to 'path') 118287 images 13 | val: val2017.txt # val images (relative to 'path') 5000 images 14 | test: test-dev2017.txt # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794 15 | 16 | # Keypoints 17 | kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible) 18 | flip_idx: [0, 2, 1, 4, 3, 6, 5, 8, 7, 10, 9, 12, 11, 14, 13, 16, 15] 19 | 20 | # Classes 21 | names: 22 | 0: person 23 | 24 | # Download script/URL (optional) 25 | download: | 26 | from ultralytics.yolo.utils.downloads import download 27 | from pathlib import Path 28 | 29 | # Download labels 30 | dir = Path(yaml['path']) # dataset root dir 31 | url = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/' 32 | urls = [url + 'coco2017labels-pose.zip'] # labels 33 | download(urls, dir=dir.parent) 34 | # Download data 35 | urls = ['http://images.cocodataset.org/zips/train2017.zip', # 19G, 118k images 36 | 'http://images.cocodataset.org/zips/val2017.zip', # 1G, 5k images 37 | 'http://images.cocodataset.org/zips/test2017.zip'] # 7G, 41k images (optional) 38 | download(urls, dir=dir / 'images', threads=3) 39 | -------------------------------------------------------------------------------- /ultralytics/datasets/coco.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | # COCO 2017 dataset http://cocodataset.org by Microsoft 3 | # Example usage: yolo train data=coco.yaml 4 | # parent 5 | # ├── ultralytics 6 | # └── datasets 7 | # └── coco ← downloads here (20.1 GB) 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/coco # dataset root dir 12 | train: train2017.txt # train images (relative to 'path') 118287 images 13 | val: val2017.txt # val images (relative to 'path') 5000 images 14 | test: test-dev2017.txt # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794 15 | 16 | # Classes 17 | names: 18 | 0: person 19 | 1: bicycle 20 | 2: car 21 | 3: motorcycle 22 | 4: airplane 23 | 5: bus 24 | 6: train 25 | 7: truck 26 | 8: boat 27 | 9: traffic light 28 | 10: fire hydrant 29 | 11: stop sign 30 | 12: parking meter 31 | 13: bench 32 | 14: bird 33 | 15: cat 34 | 16: dog 35 | 17: horse 36 | 18: sheep 37 | 19: cow 38 | 20: elephant 39 | 21: bear 40 | 22: zebra 41 | 23: giraffe 42 | 24: backpack 43 | 25: umbrella 44 | 26: handbag 45 | 27: tie 46 | 28: suitcase 47 | 29: frisbee 48 | 30: skis 49 | 31: snowboard 50 | 32: sports ball 51 | 33: kite 52 | 34: baseball bat 53 | 35: baseball glove 54 | 36: skateboard 55 | 37: surfboard 56 | 38: tennis racket 57 | 39: bottle 58 | 40: wine glass 59 | 41: cup 60 | 42: fork 61 | 43: knife 62 | 44: spoon 63 | 45: bowl 64 | 46: banana 65 | 47: apple 66 | 48: sandwich 67 | 49: orange 68 | 50: broccoli 69 | 51: carrot 70 | 52: hot dog 71 | 53: pizza 72 | 54: donut 73 | 55: cake 74 | 56: chair 75 | 57: couch 76 | 58: potted plant 77 | 59: bed 78 | 60: dining table 79 | 61: toilet 80 | 62: tv 81 | 63: laptop 82 | 64: mouse 83 | 65: remote 84 | 66: keyboard 85 | 67: cell phone 86 | 68: microwave 87 | 69: oven 88 | 70: toaster 89 | 71: sink 90 | 72: refrigerator 91 | 73: book 92 | 74: clock 93 | 75: vase 94 | 76: scissors 95 | 77: teddy bear 96 | 78: hair drier 97 | 79: toothbrush 98 | 99 | 100 | # Download script/URL (optional) 101 | download: | 102 | from ultralytics.yolo.utils.downloads import download 103 | from pathlib import Path 104 | 105 | # Download labels 106 | segments = True # segment or box labels 107 | dir = Path(yaml['path']) # dataset root dir 108 | url = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/' 109 | urls = [url + ('coco2017labels-segments.zip' if segments else 'coco2017labels.zip')] # labels 110 | download(urls, dir=dir.parent) 111 | # Download data 112 | urls = ['http://images.cocodataset.org/zips/train2017.zip', # 19G, 118k images 113 | 'http://images.cocodataset.org/zips/val2017.zip', # 1G, 5k images 114 | 'http://images.cocodataset.org/zips/test2017.zip'] # 7G, 41k images (optional) 115 | download(urls, dir=dir / 'images', threads=3) 116 | -------------------------------------------------------------------------------- /ultralytics/datasets/coco128-seg.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | # COCO128-seg dataset https://www.kaggle.com/ultralytics/coco128 (first 128 images from COCO train2017) by Ultralytics 3 | # Example usage: yolo train data=coco128.yaml 4 | # parent 5 | # ├── ultralytics 6 | # └── datasets 7 | # └── coco128-seg ← downloads here (7 MB) 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/coco128-seg # dataset root dir 12 | train: images/train2017 # train images (relative to 'path') 128 images 13 | val: images/train2017 # val images (relative to 'path') 128 images 14 | test: # test images (optional) 15 | 16 | # Classes 17 | names: 18 | 0: person 19 | 1: bicycle 20 | 2: car 21 | 3: motorcycle 22 | 4: airplane 23 | 5: bus 24 | 6: train 25 | 7: truck 26 | 8: boat 27 | 9: traffic light 28 | 10: fire hydrant 29 | 11: stop sign 30 | 12: parking meter 31 | 13: bench 32 | 14: bird 33 | 15: cat 34 | 16: dog 35 | 17: horse 36 | 18: sheep 37 | 19: cow 38 | 20: elephant 39 | 21: bear 40 | 22: zebra 41 | 23: giraffe 42 | 24: backpack 43 | 25: umbrella 44 | 26: handbag 45 | 27: tie 46 | 28: suitcase 47 | 29: frisbee 48 | 30: skis 49 | 31: snowboard 50 | 32: sports ball 51 | 33: kite 52 | 34: baseball bat 53 | 35: baseball glove 54 | 36: skateboard 55 | 37: surfboard 56 | 38: tennis racket 57 | 39: bottle 58 | 40: wine glass 59 | 41: cup 60 | 42: fork 61 | 43: knife 62 | 44: spoon 63 | 45: bowl 64 | 46: banana 65 | 47: apple 66 | 48: sandwich 67 | 49: orange 68 | 50: broccoli 69 | 51: carrot 70 | 52: hot dog 71 | 53: pizza 72 | 54: donut 73 | 55: cake 74 | 56: chair 75 | 57: couch 76 | 58: potted plant 77 | 59: bed 78 | 60: dining table 79 | 61: toilet 80 | 62: tv 81 | 63: laptop 82 | 64: mouse 83 | 65: remote 84 | 66: keyboard 85 | 67: cell phone 86 | 68: microwave 87 | 69: oven 88 | 70: toaster 89 | 71: sink 90 | 72: refrigerator 91 | 73: book 92 | 74: clock 93 | 75: vase 94 | 76: scissors 95 | 77: teddy bear 96 | 78: hair drier 97 | 79: toothbrush 98 | 99 | 100 | # Download script/URL (optional) 101 | download: https://ultralytics.com/assets/coco128-seg.zip 102 | -------------------------------------------------------------------------------- /ultralytics/datasets/coco128.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | # COCO128 dataset https://www.kaggle.com/ultralytics/coco128 (first 128 images from COCO train2017) by Ultralytics 3 | # Example usage: yolo train data=coco128.yaml 4 | # parent 5 | # ├── ultralytics 6 | # └── datasets 7 | # └── coco128 ← downloads here (7 MB) 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/coco128 # dataset root dir 12 | train: images/train2017 # train images (relative to 'path') 128 images 13 | val: images/train2017 # val images (relative to 'path') 128 images 14 | test: # test images (optional) 15 | 16 | # Classes 17 | names: 18 | 0: person 19 | 1: bicycle 20 | 2: car 21 | 3: motorcycle 22 | 4: airplane 23 | 5: bus 24 | 6: train 25 | 7: truck 26 | 8: boat 27 | 9: traffic light 28 | 10: fire hydrant 29 | 11: stop sign 30 | 12: parking meter 31 | 13: bench 32 | 14: bird 33 | 15: cat 34 | 16: dog 35 | 17: horse 36 | 18: sheep 37 | 19: cow 38 | 20: elephant 39 | 21: bear 40 | 22: zebra 41 | 23: giraffe 42 | 24: backpack 43 | 25: umbrella 44 | 26: handbag 45 | 27: tie 46 | 28: suitcase 47 | 29: frisbee 48 | 30: skis 49 | 31: snowboard 50 | 32: sports ball 51 | 33: kite 52 | 34: baseball bat 53 | 35: baseball glove 54 | 36: skateboard 55 | 37: surfboard 56 | 38: tennis racket 57 | 39: bottle 58 | 40: wine glass 59 | 41: cup 60 | 42: fork 61 | 43: knife 62 | 44: spoon 63 | 45: bowl 64 | 46: banana 65 | 47: apple 66 | 48: sandwich 67 | 49: orange 68 | 50: broccoli 69 | 51: carrot 70 | 52: hot dog 71 | 53: pizza 72 | 54: donut 73 | 55: cake 74 | 56: chair 75 | 57: couch 76 | 58: potted plant 77 | 59: bed 78 | 60: dining table 79 | 61: toilet 80 | 62: tv 81 | 63: laptop 82 | 64: mouse 83 | 65: remote 84 | 66: keyboard 85 | 67: cell phone 86 | 68: microwave 87 | 69: oven 88 | 70: toaster 89 | 71: sink 90 | 72: refrigerator 91 | 73: book 92 | 74: clock 93 | 75: vase 94 | 76: scissors 95 | 77: teddy bear 96 | 78: hair drier 97 | 79: toothbrush 98 | 99 | 100 | # Download script/URL (optional) 101 | download: https://ultralytics.com/assets/coco128.zip 102 | -------------------------------------------------------------------------------- /ultralytics/datasets/coco8-pose.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | # COCO8-pose dataset (first 8 images from COCO train2017) by Ultralytics 3 | # Example usage: yolo train data=coco8-pose.yaml 4 | # parent 5 | # ├── ultralytics 6 | # └── datasets 7 | # └── coco8-pose ← downloads here (1 MB) 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/coco8-pose # dataset root dir 12 | train: images/train # train images (relative to 'path') 4 images 13 | val: images/val # val images (relative to 'path') 4 images 14 | test: # test images (optional) 15 | 16 | # Keypoints 17 | kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible) 18 | flip_idx: [0, 2, 1, 4, 3, 6, 5, 8, 7, 10, 9, 12, 11, 14, 13, 16, 15] 19 | 20 | # Classes 21 | names: 22 | 0: person 23 | 24 | # Download script/URL (optional) 25 | download: https://ultralytics.com/assets/coco8-pose.zip 26 | -------------------------------------------------------------------------------- /ultralytics/datasets/coco8-seg.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | # COCO8-seg dataset (first 8 images from COCO train2017) by Ultralytics 3 | # Example usage: yolo train data=coco8-seg.yaml 4 | # parent 5 | # ├── ultralytics 6 | # └── datasets 7 | # └── coco8-seg ← downloads here (1 MB) 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/coco8-seg # dataset root dir 12 | train: images/train # train images (relative to 'path') 4 images 13 | val: images/val # val images (relative to 'path') 4 images 14 | test: # test images (optional) 15 | 16 | # Classes 17 | names: 18 | 0: person 19 | 1: bicycle 20 | 2: car 21 | 3: motorcycle 22 | 4: airplane 23 | 5: bus 24 | 6: train 25 | 7: truck 26 | 8: boat 27 | 9: traffic light 28 | 10: fire hydrant 29 | 11: stop sign 30 | 12: parking meter 31 | 13: bench 32 | 14: bird 33 | 15: cat 34 | 16: dog 35 | 17: horse 36 | 18: sheep 37 | 19: cow 38 | 20: elephant 39 | 21: bear 40 | 22: zebra 41 | 23: giraffe 42 | 24: backpack 43 | 25: umbrella 44 | 26: handbag 45 | 27: tie 46 | 28: suitcase 47 | 29: frisbee 48 | 30: skis 49 | 31: snowboard 50 | 32: sports ball 51 | 33: kite 52 | 34: baseball bat 53 | 35: baseball glove 54 | 36: skateboard 55 | 37: surfboard 56 | 38: tennis racket 57 | 39: bottle 58 | 40: wine glass 59 | 41: cup 60 | 42: fork 61 | 43: knife 62 | 44: spoon 63 | 45: bowl 64 | 46: banana 65 | 47: apple 66 | 48: sandwich 67 | 49: orange 68 | 50: broccoli 69 | 51: carrot 70 | 52: hot dog 71 | 53: pizza 72 | 54: donut 73 | 55: cake 74 | 56: chair 75 | 57: couch 76 | 58: potted plant 77 | 59: bed 78 | 60: dining table 79 | 61: toilet 80 | 62: tv 81 | 63: laptop 82 | 64: mouse 83 | 65: remote 84 | 66: keyboard 85 | 67: cell phone 86 | 68: microwave 87 | 69: oven 88 | 70: toaster 89 | 71: sink 90 | 72: refrigerator 91 | 73: book 92 | 74: clock 93 | 75: vase 94 | 76: scissors 95 | 77: teddy bear 96 | 78: hair drier 97 | 79: toothbrush 98 | 99 | 100 | # Download script/URL (optional) 101 | download: https://ultralytics.com/assets/coco8-seg.zip 102 | -------------------------------------------------------------------------------- /ultralytics/datasets/coco8.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | # COCO8 dataset (first 8 images from COCO train2017) by Ultralytics 3 | # Example usage: yolo train data=coco8.yaml 4 | # parent 5 | # ├── ultralytics 6 | # └── datasets 7 | # └── coco8 ← downloads here (1 MB) 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/coco8 # dataset root dir 12 | train: images/train # train images (relative to 'path') 4 images 13 | val: images/val # val images (relative to 'path') 4 images 14 | test: # test images (optional) 15 | 16 | # Classes 17 | names: 18 | 0: person 19 | 1: bicycle 20 | 2: car 21 | 3: motorcycle 22 | 4: airplane 23 | 5: bus 24 | 6: train 25 | 7: truck 26 | 8: boat 27 | 9: traffic light 28 | 10: fire hydrant 29 | 11: stop sign 30 | 12: parking meter 31 | 13: bench 32 | 14: bird 33 | 15: cat 34 | 16: dog 35 | 17: horse 36 | 18: sheep 37 | 19: cow 38 | 20: elephant 39 | 21: bear 40 | 22: zebra 41 | 23: giraffe 42 | 24: backpack 43 | 25: umbrella 44 | 26: handbag 45 | 27: tie 46 | 28: suitcase 47 | 29: frisbee 48 | 30: skis 49 | 31: snowboard 50 | 32: sports ball 51 | 33: kite 52 | 34: baseball bat 53 | 35: baseball glove 54 | 36: skateboard 55 | 37: surfboard 56 | 38: tennis racket 57 | 39: bottle 58 | 40: wine glass 59 | 41: cup 60 | 42: fork 61 | 43: knife 62 | 44: spoon 63 | 45: bowl 64 | 46: banana 65 | 47: apple 66 | 48: sandwich 67 | 49: orange 68 | 50: broccoli 69 | 51: carrot 70 | 52: hot dog 71 | 53: pizza 72 | 54: donut 73 | 55: cake 74 | 56: chair 75 | 57: couch 76 | 58: potted plant 77 | 59: bed 78 | 60: dining table 79 | 61: toilet 80 | 62: tv 81 | 63: laptop 82 | 64: mouse 83 | 65: remote 84 | 66: keyboard 85 | 67: cell phone 86 | 68: microwave 87 | 69: oven 88 | 70: toaster 89 | 71: sink 90 | 72: refrigerator 91 | 73: book 92 | 74: clock 93 | 75: vase 94 | 76: scissors 95 | 77: teddy bear 96 | 78: hair drier 97 | 79: toothbrush 98 | 99 | 100 | # Download script/URL (optional) 101 | download: https://ultralytics.com/assets/coco8.zip 102 | -------------------------------------------------------------------------------- /ultralytics/datasets/xView.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | # DIUx xView 2018 Challenge https://challenge.xviewdataset.org by U.S. National Geospatial-Intelligence Agency (NGA) 3 | # -------- DOWNLOAD DATA MANUALLY and jar xf val_images.zip to 'datasets/xView' before running train command! -------- 4 | # Example usage: yolo train data=xView.yaml 5 | # parent 6 | # ├── ultralytics 7 | # └── datasets 8 | # └── xView ← downloads here (20.7 GB) 9 | 10 | 11 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 12 | path: ../datasets/xView # dataset root dir 13 | train: images/autosplit_train.txt # train images (relative to 'path') 90% of 847 train images 14 | val: images/autosplit_val.txt # train images (relative to 'path') 10% of 847 train images 15 | 16 | # Classes 17 | names: 18 | 0: Fixed-wing Aircraft 19 | 1: Small Aircraft 20 | 2: Cargo Plane 21 | 3: Helicopter 22 | 4: Passenger Vehicle 23 | 5: Small Car 24 | 6: Bus 25 | 7: Pickup Truck 26 | 8: Utility Truck 27 | 9: Truck 28 | 10: Cargo Truck 29 | 11: Truck w/Box 30 | 12: Truck Tractor 31 | 13: Trailer 32 | 14: Truck w/Flatbed 33 | 15: Truck w/Liquid 34 | 16: Crane Truck 35 | 17: Railway Vehicle 36 | 18: Passenger Car 37 | 19: Cargo Car 38 | 20: Flat Car 39 | 21: Tank car 40 | 22: Locomotive 41 | 23: Maritime Vessel 42 | 24: Motorboat 43 | 25: Sailboat 44 | 26: Tugboat 45 | 27: Barge 46 | 28: Fishing Vessel 47 | 29: Ferry 48 | 30: Yacht 49 | 31: Container Ship 50 | 32: Oil Tanker 51 | 33: Engineering Vehicle 52 | 34: Tower crane 53 | 35: Container Crane 54 | 36: Reach Stacker 55 | 37: Straddle Carrier 56 | 38: Mobile Crane 57 | 39: Dump Truck 58 | 40: Haul Truck 59 | 41: Scraper/Tractor 60 | 42: Front loader/Bulldozer 61 | 43: Excavator 62 | 44: Cement Mixer 63 | 45: Ground Grader 64 | 46: Hut/Tent 65 | 47: Shed 66 | 48: Building 67 | 49: Aircraft Hangar 68 | 50: Damaged Building 69 | 51: Facility 70 | 52: Construction Site 71 | 53: Vehicle Lot 72 | 54: Helipad 73 | 55: Storage Tank 74 | 56: Shipping container lot 75 | 57: Shipping Container 76 | 58: Pylon 77 | 59: Tower 78 | 79 | 80 | # Download script/URL (optional) --------------------------------------------------------------------------------------- 81 | download: | 82 | import json 83 | import os 84 | from pathlib import Path 85 | 86 | import numpy as np 87 | from PIL import Image 88 | from tqdm import tqdm 89 | 90 | from ultralytics.yolo.data.dataloaders.v5loader import autosplit 91 | from ultralytics.yolo.utils.ops import xyxy2xywhn 92 | 93 | 94 | def convert_labels(fname=Path('xView/xView_train.geojson')): 95 | # Convert xView geoJSON labels to YOLO format 96 | path = fname.parent 97 | with open(fname) as f: 98 | print(f'Loading {fname}...') 99 | data = json.load(f) 100 | 101 | # Make dirs 102 | labels = Path(path / 'labels' / 'train') 103 | os.system(f'rm -rf {labels}') 104 | labels.mkdir(parents=True, exist_ok=True) 105 | 106 | # xView classes 11-94 to 0-59 107 | xview_class2index = [-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 0, 1, 2, -1, 3, -1, 4, 5, 6, 7, 8, -1, 9, 10, 11, 108 | 12, 13, 14, 15, -1, -1, 16, 17, 18, 19, 20, 21, 22, -1, 23, 24, 25, -1, 26, 27, -1, 28, -1, 109 | 29, 30, 31, 32, 33, 34, 35, 36, 37, -1, 38, 39, 40, 41, 42, 43, 44, 45, -1, -1, -1, -1, 46, 110 | 47, 48, 49, -1, 50, 51, -1, 52, -1, -1, -1, 53, 54, -1, 55, -1, -1, 56, -1, 57, -1, 58, 59] 111 | 112 | shapes = {} 113 | for feature in tqdm(data['features'], desc=f'Converting {fname}'): 114 | p = feature['properties'] 115 | if p['bounds_imcoords']: 116 | id = p['image_id'] 117 | file = path / 'train_images' / id 118 | if file.exists(): # 1395.tif missing 119 | try: 120 | box = np.array([int(num) for num in p['bounds_imcoords'].split(",")]) 121 | assert box.shape[0] == 4, f'incorrect box shape {box.shape[0]}' 122 | cls = p['type_id'] 123 | cls = xview_class2index[int(cls)] # xView class to 0-60 124 | assert 59 >= cls >= 0, f'incorrect class index {cls}' 125 | 126 | # Write YOLO label 127 | if id not in shapes: 128 | shapes[id] = Image.open(file).size 129 | box = xyxy2xywhn(box[None].astype(np.float), w=shapes[id][0], h=shapes[id][1], clip=True) 130 | with open((labels / id).with_suffix('.txt'), 'a') as f: 131 | f.write(f"{cls} {' '.join(f'{x:.6f}' for x in box[0])}\n") # write label.txt 132 | except Exception as e: 133 | print(f'WARNING: skipping one label for {file}: {e}') 134 | 135 | 136 | # Download manually from https://challenge.xviewdataset.org 137 | dir = Path(yaml['path']) # dataset root dir 138 | # urls = ['https://d307kc0mrhucc3.cloudfront.net/train_labels.zip', # train labels 139 | # 'https://d307kc0mrhucc3.cloudfront.net/train_images.zip', # 15G, 847 train images 140 | # 'https://d307kc0mrhucc3.cloudfront.net/val_images.zip'] # 5G, 282 val images (no labels) 141 | # download(urls, dir=dir) 142 | 143 | # Convert labels 144 | convert_labels(dir / 'xView_train.geojson') 145 | 146 | # Move images 147 | images = Path(dir / 'images') 148 | images.mkdir(parents=True, exist_ok=True) 149 | Path(dir / 'train_images').rename(dir / 'images' / 'train') 150 | Path(dir / 'val_images').rename(dir / 'images' / 'val') 151 | 152 | # Split 153 | autosplit(dir / 'images' / 'train') 154 | -------------------------------------------------------------------------------- /ultralytics/hub/__init__.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | import requests 4 | 5 | from ultralytics.hub.auth import Auth 6 | from ultralytics.hub.utils import PREFIX 7 | from ultralytics.yolo.utils import LOGGER, SETTINGS, USER_CONFIG_DIR, yaml_save 8 | 9 | 10 | def login(api_key=''): 11 | """ 12 | Log in to the Ultralytics HUB API using the provided API key. 13 | 14 | Args: 15 | api_key (str, optional): May be an API key or a combination API key and model ID, i.e. key_id 16 | 17 | Example: 18 | from ultralytics import hub 19 | hub.login('API_KEY') 20 | """ 21 | Auth(api_key, verbose=True) 22 | 23 | 24 | def logout(): 25 | """ 26 | Log out of Ultralytics HUB by removing the API key from the settings file. To log in again, use 'yolo hub login'. 27 | 28 | Example: 29 | from ultralytics import hub 30 | hub.logout() 31 | """ 32 | SETTINGS['api_key'] = '' 33 | yaml_save(USER_CONFIG_DIR / 'settings.yaml', SETTINGS) 34 | LOGGER.info(f"{PREFIX}logged out ✅. To log in again, use 'yolo hub login'.") 35 | 36 | 37 | def start(key=''): 38 | """ 39 | Start training models with Ultralytics HUB (DEPRECATED). 40 | 41 | Args: 42 | key (str, optional): A string containing either the API key and model ID combination (apikey_modelid), 43 | or the full model URL (https://hub.ultralytics.com/models/apikey_modelid). 44 | """ 45 | api_key, model_id = key.split('_') 46 | LOGGER.warning(f""" 47 | WARNING ⚠️ ultralytics.start() is deprecated after 8.0.60. Updated usage to train Ultralytics HUB models is: 48 | 49 | from ultralytics import YOLO, hub 50 | 51 | hub.login('{api_key}') 52 | model = YOLO('https://hub.ultralytics.com/models/{model_id}') 53 | model.train()""") 54 | 55 | 56 | def reset_model(model_id=''): 57 | # Reset a trained model to an untrained state 58 | r = requests.post('https://api.ultralytics.com/model-reset', json={'apiKey': Auth().api_key, 'modelId': model_id}) 59 | if r.status_code == 200: 60 | LOGGER.info(f'{PREFIX}Model reset successfully') 61 | return 62 | LOGGER.warning(f'{PREFIX}Model reset failure {r.status_code} {r.reason}') 63 | 64 | 65 | def export_fmts_hub(): 66 | # Returns a list of HUB-supported export formats 67 | from ultralytics.yolo.engine.exporter import export_formats 68 | return list(export_formats()['Argument'][1:]) + ['ultralytics_tflite', 'ultralytics_coreml'] 69 | 70 | 71 | def export_model(model_id='', format='torchscript'): 72 | # Export a model to all formats 73 | assert format in export_fmts_hub(), f"Unsupported export format '{format}', valid formats are {export_fmts_hub()}" 74 | r = requests.post('https://api.ultralytics.com/export', 75 | json={ 76 | 'apiKey': Auth().api_key, 77 | 'modelId': model_id, 78 | 'format': format}) 79 | assert r.status_code == 200, f'{PREFIX}{format} export failure {r.status_code} {r.reason}' 80 | LOGGER.info(f'{PREFIX}{format} export started ✅') 81 | 82 | 83 | def get_export(model_id='', format='torchscript'): 84 | # Get an exported model dictionary with download URL 85 | assert format in export_fmts_hub(), f"Unsupported export format '{format}', valid formats are {export_fmts_hub()}" 86 | r = requests.post('https://api.ultralytics.com/get-export', 87 | json={ 88 | 'apiKey': Auth().api_key, 89 | 'modelId': model_id, 90 | 'format': format}) 91 | assert r.status_code == 200, f'{PREFIX}{format} get_export failure {r.status_code} {r.reason}' 92 | return r.json() 93 | 94 | 95 | if __name__ == '__main__': 96 | start() 97 | -------------------------------------------------------------------------------- /ultralytics/hub/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/hub/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/hub/__pycache__/auth.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/hub/__pycache__/auth.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/hub/__pycache__/session.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/hub/__pycache__/session.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/hub/__pycache__/utils.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/hub/__pycache__/utils.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/hub/auth.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | import requests 4 | 5 | from ultralytics.hub.utils import HUB_API_ROOT, PREFIX, request_with_credentials 6 | from ultralytics.yolo.utils import LOGGER, SETTINGS, emojis, is_colab, set_settings 7 | 8 | API_KEY_URL = 'https://hub.ultralytics.com/settings?tab=api+keys' 9 | 10 | 11 | class Auth: 12 | id_token = api_key = model_key = False 13 | 14 | def __init__(self, api_key='', verbose=False): 15 | """ 16 | Initialize the Auth class with an optional API key. 17 | 18 | Args: 19 | api_key (str, optional): May be an API key or a combination API key and model ID, i.e. key_id 20 | """ 21 | # Split the input API key in case it contains a combined key_model and keep only the API key part 22 | api_key = api_key.split('_')[0] 23 | 24 | # Set API key attribute as value passed or SETTINGS API key if none passed 25 | self.api_key = api_key or SETTINGS.get('api_key', '') 26 | 27 | # If an API key is provided 28 | if self.api_key: 29 | # If the provided API key matches the API key in the SETTINGS 30 | if self.api_key == SETTINGS.get('api_key'): 31 | # Log that the user is already logged in 32 | if verbose: 33 | LOGGER.info(f'{PREFIX}Authenticated ✅') 34 | return 35 | else: 36 | # Attempt to authenticate with the provided API key 37 | success = self.authenticate() 38 | # If the API key is not provided and the environment is a Google Colab notebook 39 | elif is_colab(): 40 | # Attempt to authenticate using browser cookies 41 | success = self.auth_with_cookies() 42 | else: 43 | # Request an API key 44 | success = self.request_api_key() 45 | 46 | # Update SETTINGS with the new API key after successful authentication 47 | if success: 48 | set_settings({'api_key': self.api_key}) 49 | # Log that the new login was successful 50 | if verbose: 51 | LOGGER.info(f'{PREFIX}New authentication successful ✅') 52 | elif verbose: 53 | LOGGER.info(f'{PREFIX}Retrieve API key from {API_KEY_URL}') 54 | 55 | def request_api_key(self, max_attempts=3): 56 | """ 57 | Prompt the user to input their API key. Returns the model ID. 58 | """ 59 | import getpass 60 | for attempts in range(max_attempts): 61 | LOGGER.info(f'{PREFIX}Login. Attempt {attempts + 1} of {max_attempts}') 62 | input_key = getpass.getpass(f'Enter API key from {API_KEY_URL} ') 63 | self.api_key = input_key.split('_')[0] # remove model id if present 64 | if self.authenticate(): 65 | return True 66 | raise ConnectionError(emojis(f'{PREFIX}Failed to authenticate ❌')) 67 | 68 | def authenticate(self) -> bool: 69 | """ 70 | Attempt to authenticate with the server using either id_token or API key. 71 | 72 | Returns: 73 | bool: True if authentication is successful, False otherwise. 74 | """ 75 | try: 76 | header = self.get_auth_header() 77 | if header: 78 | r = requests.post(f'{HUB_API_ROOT}/v1/auth', headers=header) 79 | if not r.json().get('success', False): 80 | raise ConnectionError('Unable to authenticate.') 81 | return True 82 | raise ConnectionError('User has not authenticated locally.') 83 | except ConnectionError: 84 | self.id_token = self.api_key = False # reset invalid 85 | LOGGER.warning(f'{PREFIX}Invalid API key ⚠️') 86 | return False 87 | 88 | def auth_with_cookies(self) -> bool: 89 | """ 90 | Attempt to fetch authentication via cookies and set id_token. 91 | User must be logged in to HUB and running in a supported browser. 92 | 93 | Returns: 94 | bool: True if authentication is successful, False otherwise. 95 | """ 96 | if not is_colab(): 97 | return False # Currently only works with Colab 98 | try: 99 | authn = request_with_credentials(f'{HUB_API_ROOT}/v1/auth/auto') 100 | if authn.get('success', False): 101 | self.id_token = authn.get('data', {}).get('idToken', None) 102 | self.authenticate() 103 | return True 104 | raise ConnectionError('Unable to fetch browser authentication details.') 105 | except ConnectionError: 106 | self.id_token = False # reset invalid 107 | return False 108 | 109 | def get_auth_header(self): 110 | """ 111 | Get the authentication header for making API requests. 112 | 113 | Returns: 114 | dict: The authentication header if id_token or API key is set, None otherwise. 115 | """ 116 | if self.id_token: 117 | return {'authorization': f'Bearer {self.id_token}'} 118 | elif self.api_key: 119 | return {'x-api-key': self.api_key} 120 | else: 121 | return None 122 | 123 | def get_state(self) -> bool: 124 | """ 125 | Get the authentication state. 126 | 127 | Returns: 128 | bool: True if either id_token or API key is set, False otherwise. 129 | """ 130 | return self.id_token or self.api_key 131 | 132 | def set_api_key(self, key: str): 133 | """ 134 | Set the API key for authentication. 135 | 136 | Args: 137 | key (str): The API key string. 138 | """ 139 | self.api_key = key 140 | -------------------------------------------------------------------------------- /ultralytics/models/v3/yolov3-spp.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.0 # model depth multiple 6 | width_multiple: 1.0 # layer channel multiple 7 | 8 | # darknet53 backbone 9 | backbone: 10 | # [from, number, module, args] 11 | [[-1, 1, Conv, [32, 3, 1]], # 0 12 | [-1, 1, Conv, [64, 3, 2]], # 1-P1/2 13 | [-1, 1, Bottleneck, [64]], 14 | [-1, 1, Conv, [128, 3, 2]], # 3-P2/4 15 | [-1, 2, Bottleneck, [128]], 16 | [-1, 1, Conv, [256, 3, 2]], # 5-P3/8 17 | [-1, 8, Bottleneck, [256]], 18 | [-1, 1, Conv, [512, 3, 2]], # 7-P4/16 19 | [-1, 8, Bottleneck, [512]], 20 | [-1, 1, Conv, [1024, 3, 2]], # 9-P5/32 21 | [-1, 4, Bottleneck, [1024]], # 10 22 | ] 23 | 24 | # YOLOv3-SPP head 25 | head: 26 | [[-1, 1, Bottleneck, [1024, False]], 27 | [-1, 1, SPP, [512, [5, 9, 13]]], 28 | [-1, 1, Conv, [1024, 3, 1]], 29 | [-1, 1, Conv, [512, 1, 1]], 30 | [-1, 1, Conv, [1024, 3, 1]], # 15 (P5/32-large) 31 | 32 | [-2, 1, Conv, [256, 1, 1]], 33 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 34 | [[-1, 8], 1, Concat, [1]], # cat backbone P4 35 | [-1, 1, Bottleneck, [512, False]], 36 | [-1, 1, Bottleneck, [512, False]], 37 | [-1, 1, Conv, [256, 1, 1]], 38 | [-1, 1, Conv, [512, 3, 1]], # 22 (P4/16-medium) 39 | 40 | [-2, 1, Conv, [128, 1, 1]], 41 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 42 | [[-1, 6], 1, Concat, [1]], # cat backbone P3 43 | [-1, 1, Bottleneck, [256, False]], 44 | [-1, 2, Bottleneck, [256, False]], # 27 (P3/8-small) 45 | 46 | [[27, 22, 15], 1, Detect, [nc]], # Detect(P3, P4, P5) 47 | ] 48 | -------------------------------------------------------------------------------- /ultralytics/models/v3/yolov3-tiny.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.0 # model depth multiple 6 | width_multiple: 1.0 # layer channel multiple 7 | 8 | # YOLOv3-tiny backbone 9 | backbone: 10 | # [from, number, module, args] 11 | [[-1, 1, Conv, [16, 3, 1]], # 0 12 | [-1, 1, nn.MaxPool2d, [2, 2, 0]], # 1-P1/2 13 | [-1, 1, Conv, [32, 3, 1]], 14 | [-1, 1, nn.MaxPool2d, [2, 2, 0]], # 3-P2/4 15 | [-1, 1, Conv, [64, 3, 1]], 16 | [-1, 1, nn.MaxPool2d, [2, 2, 0]], # 5-P3/8 17 | [-1, 1, Conv, [128, 3, 1]], 18 | [-1, 1, nn.MaxPool2d, [2, 2, 0]], # 7-P4/16 19 | [-1, 1, Conv, [256, 3, 1]], 20 | [-1, 1, nn.MaxPool2d, [2, 2, 0]], # 9-P5/32 21 | [-1, 1, Conv, [512, 3, 1]], 22 | [-1, 1, nn.ZeroPad2d, [[0, 1, 0, 1]]], # 11 23 | [-1, 1, nn.MaxPool2d, [2, 1, 0]], # 12 24 | ] 25 | 26 | # YOLOv3-tiny head 27 | head: 28 | [[-1, 1, Conv, [1024, 3, 1]], 29 | [-1, 1, Conv, [256, 1, 1]], 30 | [-1, 1, Conv, [512, 3, 1]], # 15 (P5/32-large) 31 | 32 | [-2, 1, Conv, [128, 1, 1]], 33 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 34 | [[-1, 8], 1, Concat, [1]], # cat backbone P4 35 | [-1, 1, Conv, [256, 3, 1]], # 19 (P4/16-medium) 36 | 37 | [[19, 15], 1, Detect, [nc]], # Detect(P4, P5) 38 | ] 39 | -------------------------------------------------------------------------------- /ultralytics/models/v3/yolov3.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.0 # model depth multiple 6 | width_multiple: 1.0 # layer channel multiple 7 | 8 | # darknet53 backbone 9 | backbone: 10 | # [from, number, module, args] 11 | [[-1, 1, Conv, [32, 3, 1]], # 0 12 | [-1, 1, Conv, [64, 3, 2]], # 1-P1/2 13 | [-1, 1, Bottleneck, [64]], 14 | [-1, 1, Conv, [128, 3, 2]], # 3-P2/4 15 | [-1, 2, Bottleneck, [128]], 16 | [-1, 1, Conv, [256, 3, 2]], # 5-P3/8 17 | [-1, 8, Bottleneck, [256]], 18 | [-1, 1, Conv, [512, 3, 2]], # 7-P4/16 19 | [-1, 8, Bottleneck, [512]], 20 | [-1, 1, Conv, [1024, 3, 2]], # 9-P5/32 21 | [-1, 4, Bottleneck, [1024]], # 10 22 | ] 23 | 24 | # YOLOv3 head 25 | head: 26 | [[-1, 1, Bottleneck, [1024, False]], 27 | [-1, 1, Conv, [512, 1, 1]], 28 | [-1, 1, Conv, [1024, 3, 1]], 29 | [-1, 1, Conv, [512, 1, 1]], 30 | [-1, 1, Conv, [1024, 3, 1]], # 15 (P5/32-large) 31 | 32 | [-2, 1, Conv, [256, 1, 1]], 33 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 34 | [[-1, 8], 1, Concat, [1]], # cat backbone P4 35 | [-1, 1, Bottleneck, [512, False]], 36 | [-1, 1, Bottleneck, [512, False]], 37 | [-1, 1, Conv, [256, 1, 1]], 38 | [-1, 1, Conv, [512, 3, 1]], # 22 (P4/16-medium) 39 | 40 | [-2, 1, Conv, [128, 1, 1]], 41 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 42 | [[-1, 6], 1, Concat, [1]], # cat backbone P3 43 | [-1, 1, Bottleneck, [256, False]], 44 | [-1, 2, Bottleneck, [256, False]], # 27 (P3/8-small) 45 | 46 | [[27, 22, 15], 1, Detect, [nc]], # Detect(P3, P4, P5) 47 | ] 48 | -------------------------------------------------------------------------------- /ultralytics/models/v5/yolov5-p6.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | scales: # model compound scaling constants, i.e. 'model=yolov5n-p6.yaml' will call yolov5-p6.yaml with scale 'n' 6 | # [depth, width, max_channels] 7 | n: [0.33, 0.25, 1024] 8 | s: [0.33, 0.50, 1024] 9 | m: [0.67, 0.75, 1024] 10 | l: [1.00, 1.00, 1024] 11 | x: [1.33, 1.25, 1024] 12 | 13 | # YOLOv5 v6.0 backbone 14 | backbone: 15 | # [from, number, module, args] 16 | [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 17 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 18 | [-1, 3, C3, [128]], 19 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 20 | [-1, 6, C3, [256]], 21 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 22 | [-1, 9, C3, [512]], 23 | [-1, 1, Conv, [768, 3, 2]], # 7-P5/32 24 | [-1, 3, C3, [768]], 25 | [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64 26 | [-1, 3, C3, [1024]], 27 | [-1, 1, SPPF, [1024, 5]], # 11 28 | ] 29 | 30 | # YOLOv5 v6.0 head 31 | head: 32 | [[-1, 1, Conv, [768, 1, 1]], 33 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 34 | [[-1, 8], 1, Concat, [1]], # cat backbone P5 35 | [-1, 3, C3, [768, False]], # 15 36 | 37 | [-1, 1, Conv, [512, 1, 1]], 38 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 39 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 40 | [-1, 3, C3, [512, False]], # 19 41 | 42 | [-1, 1, Conv, [256, 1, 1]], 43 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 44 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 45 | [-1, 3, C3, [256, False]], # 23 (P3/8-small) 46 | 47 | [-1, 1, Conv, [256, 3, 2]], 48 | [[-1, 20], 1, Concat, [1]], # cat head P4 49 | [-1, 3, C3, [512, False]], # 26 (P4/16-medium) 50 | 51 | [-1, 1, Conv, [512, 3, 2]], 52 | [[-1, 16], 1, Concat, [1]], # cat head P5 53 | [-1, 3, C3, [768, False]], # 29 (P5/32-large) 54 | 55 | [-1, 1, Conv, [768, 3, 2]], 56 | [[-1, 12], 1, Concat, [1]], # cat head P6 57 | [-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge) 58 | 59 | [[23, 26, 29, 32], 1, Detect, [nc]], # Detect(P3, P4, P5, P6) 60 | ] 61 | -------------------------------------------------------------------------------- /ultralytics/models/v5/yolov5.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | scales: # model compound scaling constants, i.e. 'model=yolov5n.yaml' will call yolov5.yaml with scale 'n' 6 | # [depth, width, max_channels] 7 | n: [0.33, 0.25, 1024] 8 | s: [0.33, 0.50, 1024] 9 | m: [0.67, 0.75, 1024] 10 | l: [1.00, 1.00, 1024] 11 | x: [1.33, 1.25, 1024] 12 | 13 | # YOLOv5 v6.0 backbone 14 | backbone: 15 | # [from, number, module, args] 16 | [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 17 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 18 | [-1, 3, C3, [128]], 19 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 20 | [-1, 6, C3, [256]], 21 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 22 | [-1, 9, C3, [512]], 23 | [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 24 | [-1, 3, C3, [1024]], 25 | [-1, 1, SPPF, [1024, 5]], # 9 26 | ] 27 | 28 | # YOLOv5 v6.0 head 29 | head: 30 | [[-1, 1, Conv, [512, 1, 1]], 31 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 32 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 33 | [-1, 3, C3, [512, False]], # 13 34 | 35 | [-1, 1, Conv, [256, 1, 1]], 36 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 37 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 38 | [-1, 3, C3, [256, False]], # 17 (P3/8-small) 39 | 40 | [-1, 1, Conv, [256, 3, 2]], 41 | [[-1, 14], 1, Concat, [1]], # cat head P4 42 | [-1, 3, C3, [512, False]], # 20 (P4/16-medium) 43 | 44 | [-1, 1, Conv, [512, 3, 2]], 45 | [[-1, 10], 1, Concat, [1]], # cat head P5 46 | [-1, 3, C3, [1024, False]], # 23 (P5/32-large) 47 | 48 | [[17, 20, 23], 1, Detect, [nc]], # Detect(P3, P4, P5) 49 | ] 50 | -------------------------------------------------------------------------------- /ultralytics/models/v8/yolov8-cls.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | # YOLOv8-cls image classification model. For Usage examples see https://docs.ultralytics.com/tasks/classify 3 | 4 | # Parameters 5 | nc: 1000 # number of classes 6 | scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n' 7 | # [depth, width, max_channels] 8 | n: [0.33, 0.25, 1024] 9 | s: [0.33, 0.50, 1024] 10 | m: [0.67, 0.75, 1024] 11 | l: [1.00, 1.00, 1024] 12 | x: [1.00, 1.25, 1024] 13 | 14 | # YOLOv8.0n backbone 15 | backbone: 16 | # [from, repeats, module, args] 17 | - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 18 | - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 19 | - [-1, 3, C2f, [128, True]] 20 | - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 21 | - [-1, 6, C2f, [256, True]] 22 | - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 23 | - [-1, 6, C2f, [512, True]] 24 | - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 25 | - [-1, 3, C2f, [1024, True]] 26 | 27 | # YOLOv8.0n head 28 | head: 29 | - [-1, 1, Classify, [nc]] # Classify 30 | -------------------------------------------------------------------------------- /ultralytics/models/v8/yolov8-p2.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | # YOLOv8 object detection model with P2-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect 3 | 4 | # Parameters 5 | nc: 80 # number of classes 6 | scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n' 7 | # [depth, width, max_channels] 8 | n: [0.33, 0.25, 1024] 9 | s: [0.33, 0.50, 1024] 10 | m: [0.67, 0.75, 768] 11 | l: [1.00, 1.00, 512] 12 | x: [1.00, 1.25, 512] 13 | 14 | # YOLOv8.0 backbone 15 | backbone: 16 | # [from, repeats, module, args] 17 | - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 18 | - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 19 | - [-1, 3, C2f, [128, True]] 20 | - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 21 | - [-1, 6, C2f, [256, True]] 22 | - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 23 | - [-1, 6, C2f, [512, True]] 24 | - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 25 | - [-1, 3, C2f, [1024, True]] 26 | - [-1, 1, SPPF, [1024, 5]] # 9 27 | 28 | # YOLOv8.0-p2 head 29 | head: 30 | - [-1, 1, nn.Upsample, [None, 2, 'nearest']] 31 | - [[-1, 6], 1, Concat, [1]] # cat backbone P4 32 | - [-1, 3, C2f, [512]] # 12 33 | 34 | - [-1, 1, nn.Upsample, [None, 2, 'nearest']] 35 | - [[-1, 4], 1, Concat, [1]] # cat backbone P3 36 | - [-1, 3, C2f, [256]] # 15 (P3/8-small) 37 | 38 | - [-1, 1, nn.Upsample, [None, 2, 'nearest']] 39 | - [[-1, 2], 1, Concat, [1]] # cat backbone P2 40 | - [-1, 3, C2f, [128]] # 18 (P2/4-xsmall) 41 | 42 | - [-1, 1, Conv, [128, 3, 2]] 43 | - [[-1, 15], 1, Concat, [1]] # cat head P3 44 | - [-1, 3, C2f, [256]] # 21 (P3/8-small) 45 | 46 | - [-1, 1, Conv, [256, 3, 2]] 47 | - [[-1, 12], 1, Concat, [1]] # cat head P4 48 | - [-1, 3, C2f, [512]] # 24 (P4/16-medium) 49 | 50 | - [-1, 1, Conv, [512, 3, 2]] 51 | - [[-1, 9], 1, Concat, [1]] # cat head P5 52 | - [-1, 3, C2f, [1024]] # 27 (P5/32-large) 53 | 54 | - [[18, 21, 24, 27], 1, Detect, [nc]] # Detect(P2, P3, P4, P5) 55 | -------------------------------------------------------------------------------- /ultralytics/models/v8/yolov8-p6.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | # YOLOv8 object detection model with P3-P6 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect 3 | 4 | # Parameters 5 | nc: 80 # number of classes 6 | scales: # model compound scaling constants, i.e. 'model=yolov8n-p6.yaml' will call yolov8-p6.yaml with scale 'n' 7 | # [depth, width, max_channels] 8 | n: [0.33, 0.25, 1024] 9 | s: [0.33, 0.50, 1024] 10 | m: [0.67, 0.75, 768] 11 | l: [1.00, 1.00, 512] 12 | x: [1.00, 1.25, 512] 13 | 14 | # YOLOv8.0x6 backbone 15 | backbone: 16 | # [from, repeats, module, args] 17 | - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 18 | - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 19 | - [-1, 3, C2f, [128, True]] 20 | - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 21 | - [-1, 6, C2f, [256, True]] 22 | - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 23 | - [-1, 6, C2f, [512, True]] 24 | - [-1, 1, Conv, [768, 3, 2]] # 7-P5/32 25 | - [-1, 3, C2f, [768, True]] 26 | - [-1, 1, Conv, [1024, 3, 2]] # 9-P6/64 27 | - [-1, 3, C2f, [1024, True]] 28 | - [-1, 1, SPPF, [1024, 5]] # 11 29 | 30 | # YOLOv8.0x6 head 31 | head: 32 | - [-1, 1, nn.Upsample, [None, 2, 'nearest']] 33 | - [[-1, 8], 1, Concat, [1]] # cat backbone P5 34 | - [-1, 3, C2, [768, False]] # 14 35 | 36 | - [-1, 1, nn.Upsample, [None, 2, 'nearest']] 37 | - [[-1, 6], 1, Concat, [1]] # cat backbone P4 38 | - [-1, 3, C2, [512, False]] # 17 39 | 40 | - [-1, 1, nn.Upsample, [None, 2, 'nearest']] 41 | - [[-1, 4], 1, Concat, [1]] # cat backbone P3 42 | - [-1, 3, C2, [256, False]] # 20 (P3/8-small) 43 | 44 | - [-1, 1, Conv, [256, 3, 2]] 45 | - [[-1, 17], 1, Concat, [1]] # cat head P4 46 | - [-1, 3, C2, [512, False]] # 23 (P4/16-medium) 47 | 48 | - [-1, 1, Conv, [512, 3, 2]] 49 | - [[-1, 14], 1, Concat, [1]] # cat head P5 50 | - [-1, 3, C2, [768, False]] # 26 (P5/32-large) 51 | 52 | - [-1, 1, Conv, [768, 3, 2]] 53 | - [[-1, 11], 1, Concat, [1]] # cat head P6 54 | - [-1, 3, C2, [1024, False]] # 29 (P6/64-xlarge) 55 | 56 | - [[20, 23, 26, 29], 1, Detect, [nc]] # Detect(P3, P4, P5, P6) 57 | -------------------------------------------------------------------------------- /ultralytics/models/v8/yolov8-pose-p6.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | # YOLOv8 object detection model with P3-P6 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect 3 | 4 | # Parameters 5 | nc: 1 # number of classes 6 | kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible) 7 | scales: # model compound scaling constants, i.e. 'model=yolov8n-p6.yaml' will call yolov8-p6.yaml with scale 'n' 8 | # [depth, width, max_channels] 9 | n: [0.33, 0.25, 1024] 10 | s: [0.33, 0.50, 1024] 11 | m: [0.67, 0.75, 768] 12 | l: [1.00, 1.00, 512] 13 | x: [1.00, 1.25, 512] 14 | 15 | # YOLOv8.0x6 backbone 16 | backbone: 17 | # [from, repeats, module, args] 18 | - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 19 | - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 20 | - [-1, 3, C2f, [128, True]] 21 | - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 22 | - [-1, 6, C2f, [256, True]] 23 | - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 24 | - [-1, 6, C2f, [512, True]] 25 | - [-1, 1, Conv, [768, 3, 2]] # 7-P5/32 26 | - [-1, 3, C2f, [768, True]] 27 | - [-1, 1, Conv, [1024, 3, 2]] # 9-P6/64 28 | - [-1, 3, C2f, [1024, True]] 29 | - [-1, 1, SPPF, [1024, 5]] # 11 30 | 31 | # YOLOv8.0x6 head 32 | head: 33 | - [-1, 1, nn.Upsample, [None, 2, 'nearest']] 34 | - [[-1, 8], 1, Concat, [1]] # cat backbone P5 35 | - [-1, 3, C2, [768, False]] # 14 36 | 37 | - [-1, 1, nn.Upsample, [None, 2, 'nearest']] 38 | - [[-1, 6], 1, Concat, [1]] # cat backbone P4 39 | - [-1, 3, C2, [512, False]] # 17 40 | 41 | - [-1, 1, nn.Upsample, [None, 2, 'nearest']] 42 | - [[-1, 4], 1, Concat, [1]] # cat backbone P3 43 | - [-1, 3, C2, [256, False]] # 20 (P3/8-small) 44 | 45 | - [-1, 1, Conv, [256, 3, 2]] 46 | - [[-1, 17], 1, Concat, [1]] # cat head P4 47 | - [-1, 3, C2, [512, False]] # 23 (P4/16-medium) 48 | 49 | - [-1, 1, Conv, [512, 3, 2]] 50 | - [[-1, 14], 1, Concat, [1]] # cat head P5 51 | - [-1, 3, C2, [768, False]] # 26 (P5/32-large) 52 | 53 | - [-1, 1, Conv, [768, 3, 2]] 54 | - [[-1, 11], 1, Concat, [1]] # cat head P6 55 | - [-1, 3, C2, [1024, False]] # 29 (P6/64-xlarge) 56 | 57 | - [[20, 23, 26, 29], 1, Pose, [nc, kpt_shape]] # Pose(P3, P4, P5, P6) 58 | -------------------------------------------------------------------------------- /ultralytics/models/v8/yolov8-pose.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | # YOLOv8-pose keypoints/pose estimation model. For Usage examples see https://docs.ultralytics.com/tasks/pose 3 | 4 | # Parameters 5 | nc: 1 # number of classes 6 | kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible) 7 | scales: # model compound scaling constants, i.e. 'model=yolov8n-pose.yaml' will call yolov8-pose.yaml with scale 'n' 8 | # [depth, width, max_channels] 9 | n: [0.33, 0.25, 1024] 10 | s: [0.33, 0.50, 1024] 11 | m: [0.67, 0.75, 768] 12 | l: [1.00, 1.00, 512] 13 | x: [1.00, 1.25, 512] 14 | 15 | # YOLOv8.0n backbone 16 | backbone: 17 | # [from, repeats, module, args] 18 | - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 19 | - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 20 | - [-1, 3, C2f, [128, True]] 21 | - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 22 | - [-1, 6, C2f, [256, True]] 23 | - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 24 | - [-1, 6, C2f, [512, True]] 25 | - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 26 | - [-1, 3, C2f, [1024, True]] 27 | - [-1, 1, SPPF, [1024, 5]] # 9 28 | 29 | # YOLOv8.0n head 30 | head: 31 | - [-1, 1, nn.Upsample, [None, 2, 'nearest']] 32 | - [[-1, 6], 1, Concat, [1]] # cat backbone P4 33 | - [-1, 3, C2f, [512]] # 12 34 | 35 | - [-1, 1, nn.Upsample, [None, 2, 'nearest']] 36 | - [[-1, 4], 1, Concat, [1]] # cat backbone P3 37 | - [-1, 3, C2f, [256]] # 15 (P3/8-small) 38 | 39 | - [-1, 1, Conv, [256, 3, 2]] 40 | - [[-1, 12], 1, Concat, [1]] # cat head P4 41 | - [-1, 3, C2f, [512]] # 18 (P4/16-medium) 42 | 43 | - [-1, 1, Conv, [512, 3, 2]] 44 | - [[-1, 9], 1, Concat, [1]] # cat head P5 45 | - [-1, 3, C2f, [1024]] # 21 (P5/32-large) 46 | 47 | - [[15, 18, 21], 1, Pose, [nc, kpt_shape]] # Pose(P3, P4, P5) 48 | -------------------------------------------------------------------------------- /ultralytics/models/v8/yolov8-seg.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | # YOLOv8-seg instance segmentation model. For Usage examples see https://docs.ultralytics.com/tasks/segment 3 | 4 | # Parameters 5 | nc: 80 # number of classes 6 | scales: # model compound scaling constants, i.e. 'model=yolov8n-seg.yaml' will call yolov8-seg.yaml with scale 'n' 7 | # [depth, width, max_channels] 8 | n: [0.33, 0.25, 1024] 9 | s: [0.33, 0.50, 1024] 10 | m: [0.67, 0.75, 768] 11 | l: [1.00, 1.00, 512] 12 | x: [1.00, 1.25, 512] 13 | 14 | # YOLOv8.0n backbone 15 | backbone: 16 | # [from, repeats, module, args] 17 | - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 18 | - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 19 | - [-1, 3, C2f, [128, True]] 20 | - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 21 | - [-1, 6, C2f, [256, True]] 22 | - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 23 | - [-1, 6, C2f, [512, True]] 24 | - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 25 | - [-1, 3, C2f, [1024, True]] 26 | - [-1, 1, SPPF, [1024, 5]] # 9 27 | 28 | # YOLOv8.0n head 29 | head: 30 | - [-1, 1, nn.Upsample, [None, 2, 'nearest']] 31 | - [[-1, 6], 1, Concat, [1]] # cat backbone P4 32 | - [-1, 3, C2f, [512]] # 12 33 | 34 | - [-1, 1, nn.Upsample, [None, 2, 'nearest']] 35 | - [[-1, 4], 1, Concat, [1]] # cat backbone P3 36 | - [-1, 3, C2f, [256]] # 15 (P3/8-small) 37 | 38 | - [-1, 1, Conv, [256, 3, 2]] 39 | - [[-1, 12], 1, Concat, [1]] # cat head P4 40 | - [-1, 3, C2f, [512]] # 18 (P4/16-medium) 41 | 42 | - [-1, 1, Conv, [512, 3, 2]] 43 | - [[-1, 9], 1, Concat, [1]] # cat head P5 44 | - [-1, 3, C2f, [1024]] # 21 (P5/32-large) 45 | 46 | - [[15, 18, 21], 1, Segment, [nc, 32, 256]] # Segment(P3, P4, P5) 47 | -------------------------------------------------------------------------------- /ultralytics/models/v8/yolov8.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | # YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect 3 | 4 | # Parameters 5 | nc: 80 # number of classes 6 | scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n' 7 | # [depth, width, max_channels] 8 | n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPs 9 | s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPs 10 | m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPs 11 | l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs 12 | x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs 13 | 14 | # YOLOv8.0n backbone 15 | backbone: 16 | # [from, repeats, module, args] 17 | - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 18 | - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 19 | - [-1, 3, C2f, [128, True]] 20 | - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 21 | - [-1, 6, C2f, [256, True]] 22 | - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 23 | - [-1, 6, C2f, [512, True]] 24 | - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 25 | - [-1, 3, C2f, [1024, True]] 26 | - [-1, 1, SPPF, [1024, 5]] # 9 27 | 28 | # YOLOv8.0n head 29 | head: 30 | - [-1, 1, nn.Upsample, [None, 2, 'nearest']] 31 | - [[-1, 6], 1, Concat, [1]] # cat backbone P4 32 | - [-1, 3, C2f, [512]] # 12 33 | 34 | - [-1, 1, nn.Upsample, [None, 2, 'nearest']] 35 | - [[-1, 4], 1, Concat, [1]] # cat backbone P3 36 | - [-1, 3, C2f, [256]] # 15 (P3/8-small) 37 | 38 | - [-1, 1, Conv, [256, 3, 2]] 39 | - [[-1, 12], 1, Concat, [1]] # cat head P4 40 | - [-1, 3, C2f, [512]] # 18 (P4/16-medium) 41 | 42 | - [-1, 1, Conv, [512, 3, 2]] 43 | - [[-1, 9], 1, Concat, [1]] # cat head P5 44 | - [-1, 3, C2f, [1024]] # 21 (P5/32-large) 45 | 46 | - [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5) 47 | -------------------------------------------------------------------------------- /ultralytics/nn/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/nn/__init__.py -------------------------------------------------------------------------------- /ultralytics/nn/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/nn/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/nn/__pycache__/autobackend.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/nn/__pycache__/autobackend.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/nn/__pycache__/autoshape.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/nn/__pycache__/autoshape.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/nn/__pycache__/modules.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/nn/__pycache__/modules.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/nn/__pycache__/tasks.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/nn/__pycache__/tasks.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/tracker/__init__.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | from .track import register_tracker 4 | from .trackers import BOTSORT, BYTETracker 5 | 6 | __all__ = 'register_tracker', 'BOTSORT', 'BYTETracker' # allow simpler import 7 | -------------------------------------------------------------------------------- /ultralytics/tracker/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/tracker/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/tracker/__pycache__/track.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/tracker/__pycache__/track.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/tracker/cfg/botsort.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | # Default YOLO tracker settings for BoT-SORT tracker https://github.com/NirAharon/BoT-SORT 3 | 4 | tracker_type: botsort # tracker type, ['botsort', 'bytetrack'] 5 | track_high_thresh: 0.5 # threshold for the first association 6 | track_low_thresh: 0.1 # threshold for the second association 7 | new_track_thresh: 0.6 # threshold for init new track if the detection does not match any tracks 8 | track_buffer: 30 # buffer to calculate the time when to remove tracks 9 | match_thresh: 0.8 # threshold for matching tracks 10 | # min_box_area: 10 # threshold for min box areas(for tracker evaluation, not used for now) 11 | # mot20: False # for tracker evaluation(not used for now) 12 | 13 | # BoT-SORT settings 14 | cmc_method: sparseOptFlow # method of global motion compensation 15 | # ReID model related thresh (not supported yet) 16 | proximity_thresh: 0.5 17 | appearance_thresh: 0.25 18 | with_reid: False 19 | -------------------------------------------------------------------------------- /ultralytics/tracker/cfg/bytetrack.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | # Default YOLO tracker settings for ByteTrack tracker https://github.com/ifzhang/ByteTrack 3 | 4 | tracker_type: bytetrack # tracker type, ['botsort', 'bytetrack'] 5 | track_high_thresh: 0.5 # threshold for the first association 6 | track_low_thresh: 0.1 # threshold for the second association 7 | new_track_thresh: 0.6 # threshold for init new track if the detection does not match any tracks 8 | track_buffer: 30 # buffer to calculate the time when to remove tracks 9 | match_thresh: 0.8 # threshold for matching tracks 10 | # min_box_area: 10 # threshold for min box areas(for tracker evaluation, not used for now) 11 | # mot20: False # for tracker evaluation(not used for now) 12 | -------------------------------------------------------------------------------- /ultralytics/tracker/track.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | from functools import partial 4 | 5 | import torch 6 | 7 | from ultralytics.yolo.utils import IterableSimpleNamespace, yaml_load 8 | from ultralytics.yolo.utils.checks import check_yaml 9 | 10 | from .trackers import BOTSORT, BYTETracker 11 | 12 | TRACKER_MAP = {'bytetrack': BYTETracker, 'botsort': BOTSORT} 13 | 14 | 15 | def on_predict_start(predictor, persist=False): 16 | """ 17 | Initialize trackers for object tracking during prediction. 18 | 19 | Args: 20 | predictor (object): The predictor object to initialize trackers for. 21 | persist (bool, optional): Whether to persist the trackers if they already exist. Defaults to False. 22 | 23 | Raises: 24 | AssertionError: If the tracker_type is not 'bytetrack' or 'botsort'. 25 | """ 26 | if hasattr(predictor, 'trackers') and persist: 27 | return 28 | tracker = check_yaml(predictor.args.tracker) 29 | cfg = IterableSimpleNamespace(**yaml_load(tracker)) 30 | assert cfg.tracker_type in ['bytetrack', 'botsort'], \ 31 | f"Only support 'bytetrack' and 'botsort' for now, but got '{cfg.tracker_type}'" 32 | trackers = [] 33 | for _ in range(predictor.dataset.bs): 34 | tracker = TRACKER_MAP[cfg.tracker_type](args=cfg, frame_rate=30) 35 | trackers.append(tracker) 36 | predictor.trackers = trackers 37 | 38 | 39 | def on_predict_postprocess_end(predictor): 40 | bs = predictor.dataset.bs 41 | im0s = predictor.batch[2] 42 | im0s = im0s if isinstance(im0s, list) else [im0s] 43 | for i in range(bs): 44 | det = predictor.results[i].boxes.cpu().numpy() 45 | if len(det) == 0: 46 | continue 47 | tracks = predictor.trackers[i].update(det, im0s[i]) 48 | if len(tracks) == 0: 49 | continue 50 | idx = tracks[:, -1].tolist() 51 | predictor.results[i] = predictor.results[i][idx] 52 | predictor.results[i].update(boxes=torch.as_tensor(tracks[:, :-1])) 53 | 54 | 55 | def register_tracker(model, persist): 56 | """ 57 | Register tracking callbacks to the model for object tracking during prediction. 58 | 59 | Args: 60 | model (object): The model object to register tracking callbacks for. 61 | persist (bool): Whether to persist the trackers if they already exist. 62 | 63 | """ 64 | model.add_callback('on_predict_start', partial(on_predict_start, persist=persist)) 65 | model.add_callback('on_predict_postprocess_end', on_predict_postprocess_end) 66 | -------------------------------------------------------------------------------- /ultralytics/tracker/trackers/__init__.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | from .bot_sort import BOTSORT 4 | from .byte_tracker import BYTETracker 5 | 6 | __all__ = 'BOTSORT', 'BYTETracker' # allow simpler import 7 | -------------------------------------------------------------------------------- /ultralytics/tracker/trackers/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/tracker/trackers/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/tracker/trackers/__pycache__/basetrack.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/tracker/trackers/__pycache__/basetrack.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/tracker/trackers/__pycache__/bot_sort.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/tracker/trackers/__pycache__/bot_sort.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/tracker/trackers/__pycache__/byte_tracker.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/tracker/trackers/__pycache__/byte_tracker.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/tracker/trackers/basetrack.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | from collections import OrderedDict 4 | 5 | import numpy as np 6 | 7 | 8 | class TrackState: 9 | New = 0 10 | Tracked = 1 11 | Lost = 2 12 | Removed = 3 13 | 14 | 15 | class BaseTrack: 16 | _count = 0 17 | 18 | track_id = 0 19 | is_activated = False 20 | state = TrackState.New 21 | 22 | history = OrderedDict() 23 | features = [] 24 | curr_feature = None 25 | score = 0 26 | start_frame = 0 27 | frame_id = 0 28 | time_since_update = 0 29 | 30 | # multi-camera 31 | location = (np.inf, np.inf) 32 | 33 | @property 34 | def end_frame(self): 35 | return self.frame_id 36 | 37 | @staticmethod 38 | def next_id(): 39 | BaseTrack._count += 1 40 | return BaseTrack._count 41 | 42 | def activate(self, *args): 43 | raise NotImplementedError 44 | 45 | def predict(self): 46 | raise NotImplementedError 47 | 48 | def update(self, *args, **kwargs): 49 | raise NotImplementedError 50 | 51 | def mark_lost(self): 52 | self.state = TrackState.Lost 53 | 54 | def mark_removed(self): 55 | self.state = TrackState.Removed 56 | 57 | @staticmethod 58 | def reset_id(): 59 | BaseTrack._count = 0 60 | -------------------------------------------------------------------------------- /ultralytics/tracker/trackers/bot_sort.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | from collections import deque 4 | 5 | import numpy as np 6 | 7 | from ..utils import matching 8 | from ..utils.gmc import GMC 9 | from ..utils.kalman_filter import KalmanFilterXYWH 10 | from .basetrack import TrackState 11 | from .byte_tracker import BYTETracker, STrack 12 | 13 | 14 | class BOTrack(STrack): 15 | shared_kalman = KalmanFilterXYWH() 16 | 17 | def __init__(self, tlwh, score, cls, feat=None, feat_history=50): 18 | super().__init__(tlwh, score, cls) 19 | 20 | self.smooth_feat = None 21 | self.curr_feat = None 22 | if feat is not None: 23 | self.update_features(feat) 24 | self.features = deque([], maxlen=feat_history) 25 | self.alpha = 0.9 26 | 27 | def update_features(self, feat): 28 | feat /= np.linalg.norm(feat) 29 | self.curr_feat = feat 30 | if self.smooth_feat is None: 31 | self.smooth_feat = feat 32 | else: 33 | self.smooth_feat = self.alpha * self.smooth_feat + (1 - self.alpha) * feat 34 | self.features.append(feat) 35 | self.smooth_feat /= np.linalg.norm(self.smooth_feat) 36 | 37 | def predict(self): 38 | mean_state = self.mean.copy() 39 | if self.state != TrackState.Tracked: 40 | mean_state[6] = 0 41 | mean_state[7] = 0 42 | 43 | self.mean, self.covariance = self.kalman_filter.predict(mean_state, self.covariance) 44 | 45 | def re_activate(self, new_track, frame_id, new_id=False): 46 | if new_track.curr_feat is not None: 47 | self.update_features(new_track.curr_feat) 48 | super().re_activate(new_track, frame_id, new_id) 49 | 50 | def update(self, new_track, frame_id): 51 | if new_track.curr_feat is not None: 52 | self.update_features(new_track.curr_feat) 53 | super().update(new_track, frame_id) 54 | 55 | @property 56 | def tlwh(self): 57 | """Get current position in bounding box format `(top left x, top left y, 58 | width, height)`. 59 | """ 60 | if self.mean is None: 61 | return self._tlwh.copy() 62 | ret = self.mean[:4].copy() 63 | ret[:2] -= ret[2:] / 2 64 | return ret 65 | 66 | @staticmethod 67 | def multi_predict(stracks): 68 | if len(stracks) <= 0: 69 | return 70 | multi_mean = np.asarray([st.mean.copy() for st in stracks]) 71 | multi_covariance = np.asarray([st.covariance for st in stracks]) 72 | for i, st in enumerate(stracks): 73 | if st.state != TrackState.Tracked: 74 | multi_mean[i][6] = 0 75 | multi_mean[i][7] = 0 76 | multi_mean, multi_covariance = BOTrack.shared_kalman.multi_predict(multi_mean, multi_covariance) 77 | for i, (mean, cov) in enumerate(zip(multi_mean, multi_covariance)): 78 | stracks[i].mean = mean 79 | stracks[i].covariance = cov 80 | 81 | def convert_coords(self, tlwh): 82 | return self.tlwh_to_xywh(tlwh) 83 | 84 | @staticmethod 85 | def tlwh_to_xywh(tlwh): 86 | """Convert bounding box to format `(center x, center y, width, 87 | height)`. 88 | """ 89 | ret = np.asarray(tlwh).copy() 90 | ret[:2] += ret[2:] / 2 91 | return ret 92 | 93 | 94 | class BOTSORT(BYTETracker): 95 | 96 | def __init__(self, args, frame_rate=30): 97 | super().__init__(args, frame_rate) 98 | # ReID module 99 | self.proximity_thresh = args.proximity_thresh 100 | self.appearance_thresh = args.appearance_thresh 101 | 102 | if args.with_reid: 103 | # haven't supported BoT-SORT(reid) yet 104 | self.encoder = None 105 | # self.gmc = GMC(method=args.cmc_method, verbose=[args.name, args.ablation]) 106 | self.gmc = GMC(method=args.cmc_method) 107 | 108 | def get_kalmanfilter(self): 109 | return KalmanFilterXYWH() 110 | 111 | def init_track(self, dets, scores, cls, img=None): 112 | if len(dets) == 0: 113 | return [] 114 | if self.args.with_reid and self.encoder is not None: 115 | features_keep = self.encoder.inference(img, dets) 116 | return [BOTrack(xyxy, s, c, f) for (xyxy, s, c, f) in zip(dets, scores, cls, features_keep)] # detections 117 | else: 118 | return [BOTrack(xyxy, s, c) for (xyxy, s, c) in zip(dets, scores, cls)] # detections 119 | 120 | def get_dists(self, tracks, detections): 121 | dists = matching.iou_distance(tracks, detections) 122 | dists_mask = (dists > self.proximity_thresh) 123 | 124 | # TODO: mot20 125 | # if not self.args.mot20: 126 | dists = matching.fuse_score(dists, detections) 127 | 128 | if self.args.with_reid and self.encoder is not None: 129 | emb_dists = matching.embedding_distance(tracks, detections) / 2.0 130 | emb_dists[emb_dists > self.appearance_thresh] = 1.0 131 | emb_dists[dists_mask] = 1.0 132 | dists = np.minimum(dists, emb_dists) 133 | return dists 134 | 135 | def multi_predict(self, tracks): 136 | BOTrack.multi_predict(tracks) 137 | -------------------------------------------------------------------------------- /ultralytics/tracker/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/tracker/utils/__init__.py -------------------------------------------------------------------------------- /ultralytics/tracker/utils/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/tracker/utils/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/tracker/utils/__pycache__/gmc.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/tracker/utils/__pycache__/gmc.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/tracker/utils/__pycache__/kalman_filter.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/tracker/utils/__pycache__/kalman_filter.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/tracker/utils/__pycache__/matching.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/tracker/utils/__pycache__/matching.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/__init__.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | from . import v8 4 | 5 | __all__ = 'v8', # tuple or list 6 | -------------------------------------------------------------------------------- /ultralytics/yolo/cfg/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/cfg/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/cfg/default.yaml: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | # Default training settings and hyperparameters for medium-augmentation COCO training 3 | 4 | task: detect # YOLO task, i.e. detect, segment, classify, pose 5 | mode: train # YOLO mode, i.e. train, val, predict, export, track, benchmark 6 | 7 | # Train settings ------------------------------------------------------------------------------------------------------- 8 | model: # path to model file, i.e. yolov8n.pt, yolov8n.yaml 9 | data: # path to data file, i.e. coco128.yaml 10 | epochs: 100 # number of epochs to train for 11 | patience: 50 # epochs to wait for no observable improvement for early stopping of training 12 | batch: 16 # number of images per batch (-1 for AutoBatch) 13 | imgsz: 640 # size of input images as integer or w,h 14 | save: True # save train checkpoints and predict results 15 | save_period: -1 # Save checkpoint every x epochs (disabled if < 1) 16 | cache: False # True/ram, disk or False. Use cache for data loading 17 | device: # device to run on, i.e. cuda device=0 or device=0,1,2,3 or device=cpu 18 | workers: 8 # number of worker threads for data loading (per RANK if DDP) 19 | project: # project name 20 | name: # experiment name, results saved to 'project/name' directory 21 | exist_ok: False # whether to overwrite existing experiment 22 | pretrained: False # whether to use a pretrained model 23 | optimizer: SGD # optimizer to use, choices=['SGD', 'Adam', 'AdamW', 'RMSProp'] 24 | verbose: True # whether to print verbose output 25 | seed: 0 # random seed for reproducibility 26 | deterministic: True # whether to enable deterministic mode 27 | single_cls: False # train multi-class data as single-class 28 | image_weights: False # use weighted image selection for training 29 | rect: False # rectangular training if mode='train' or rectangular validation if mode='val' 30 | cos_lr: False # use cosine learning rate scheduler 31 | close_mosaic: 0 # (int) disable mosaic augmentation for final epochs 32 | resume: False # resume training from last checkpoint 33 | amp: True # Automatic Mixed Precision (AMP) training, choices=[True, False], True runs AMP check 34 | # Segmentation 35 | overlap_mask: True # masks should overlap during training (segment train only) 36 | mask_ratio: 4 # mask downsample ratio (segment train only) 37 | # Classification 38 | dropout: 0.0 # use dropout regularization (classify train only) 39 | 40 | # Val/Test settings ---------------------------------------------------------------------------------------------------- 41 | val: True # validate/test during training 42 | split: val # dataset split to use for validation, i.e. 'val', 'test' or 'train' 43 | save_json: False # save results to JSON file 44 | save_hybrid: False # save hybrid version of labels (labels + additional predictions) 45 | conf: # object confidence threshold for detection (default 0.25 predict, 0.001 val) 46 | iou: 0.7 # intersection over union (IoU) threshold for NMS 47 | max_det: 300 # maximum number of detections per image 48 | half: False # use half precision (FP16) 49 | dnn: False # use OpenCV DNN for ONNX inference 50 | plots: True # save plots during train/val 51 | 52 | # Prediction settings -------------------------------------------------------------------------------------------------- 53 | source: # source directory for images or videos 54 | show: False # show results if possible 55 | save_txt: False # save results as .txt file 56 | save_conf: False # save results with confidence scores 57 | save_crop: False # save cropped images with results 58 | show_labels: True # show object labels in plots 59 | show_conf: True # show object confidence scores in plots 60 | vid_stride: 1 # video frame-rate stride 61 | line_thickness: 3 # bounding box thickness (pixels) 62 | visualize: False # visualize model features 63 | augment: False # apply image augmentation to prediction sources 64 | agnostic_nms: False # class-agnostic NMS 65 | classes: # filter results by class, i.e. class=0, or class=[0,2,3] 66 | retina_masks: False # use high-resolution segmentation masks 67 | boxes: True # Show boxes in segmentation predictions 68 | 69 | # Export settings ------------------------------------------------------------------------------------------------------ 70 | format: torchscript # format to export to 71 | keras: False # use Keras 72 | optimize: False # TorchScript: optimize for mobile 73 | int8: False # CoreML/TF INT8 quantization 74 | dynamic: False # ONNX/TF/TensorRT: dynamic axes 75 | simplify: False # ONNX: simplify model 76 | opset: # ONNX: opset version (optional) 77 | workspace: 4 # TensorRT: workspace size (GB) 78 | nms: False # CoreML: add NMS 79 | 80 | # Hyperparameters ------------------------------------------------------------------------------------------------------ 81 | lr0: 0.01 # initial learning rate (i.e. SGD=1E-2, Adam=1E-3) 82 | lrf: 0.01 # final learning rate (lr0 * lrf) 83 | momentum: 0.937 # SGD momentum/Adam beta1 84 | weight_decay: 0.0005 # optimizer weight decay 5e-4 85 | warmup_epochs: 3.0 # warmup epochs (fractions ok) 86 | warmup_momentum: 0.8 # warmup initial momentum 87 | warmup_bias_lr: 0.1 # warmup initial bias lr 88 | box: 7.5 # box loss gain 89 | cls: 0.5 # cls loss gain (scale with pixels) 90 | dfl: 1.5 # dfl loss gain 91 | pose: 12.0 # pose loss gain 92 | kobj: 1.0 # keypoint obj loss gain 93 | label_smoothing: 0.0 # label smoothing (fraction) 94 | nbs: 64 # nominal batch size 95 | hsv_h: 0.015 # image HSV-Hue augmentation (fraction) 96 | hsv_s: 0.7 # image HSV-Saturation augmentation (fraction) 97 | hsv_v: 0.4 # image HSV-Value augmentation (fraction) 98 | degrees: 0.0 # image rotation (+/- deg) 99 | translate: 0.1 # image translation (+/- fraction) 100 | scale: 0.5 # image scale (+/- gain) 101 | shear: 0.0 # image shear (+/- deg) 102 | perspective: 0.0 # image perspective (+/- fraction), range 0-0.001 103 | flipud: 0.0 # image flip up-down (probability) 104 | fliplr: 0.5 # image flip left-right (probability) 105 | mosaic: 1.0 # image mosaic (probability) 106 | mixup: 0.0 # image mixup (probability) 107 | copy_paste: 0.0 # segment copy-paste (probability) 108 | 109 | # Custom config.yaml --------------------------------------------------------------------------------------------------- 110 | cfg: # for overriding defaults.yaml 111 | 112 | # Debug, do not modify ------------------------------------------------------------------------------------------------- 113 | v5loader: False # use legacy YOLOv5 dataloader 114 | 115 | # Tracker settings ------------------------------------------------------------------------------------------------------ 116 | tracker: botsort.yaml # tracker type, ['botsort.yaml', 'bytetrack.yaml'] 117 | -------------------------------------------------------------------------------- /ultralytics/yolo/data/__init__.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | from .base import BaseDataset 4 | from .build import build_classification_dataloader, build_dataloader, load_inference_source 5 | from .dataset import ClassificationDataset, SemanticDataset, YOLODataset 6 | from .dataset_wrappers import MixAndRectDataset 7 | 8 | __all__ = ('BaseDataset', 'ClassificationDataset', 'MixAndRectDataset', 'SemanticDataset', 'YOLODataset', 9 | 'build_classification_dataloader', 'build_dataloader', 'load_inference_source') 10 | -------------------------------------------------------------------------------- /ultralytics/yolo/data/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/data/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/data/__pycache__/augment.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/data/__pycache__/augment.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/data/__pycache__/base.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/data/__pycache__/base.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/data/__pycache__/build.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/data/__pycache__/build.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/data/__pycache__/dataset.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/data/__pycache__/dataset.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/data/__pycache__/dataset_wrappers.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/data/__pycache__/dataset_wrappers.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/data/__pycache__/utils.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/data/__pycache__/utils.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/data/dataloaders/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/data/dataloaders/__init__.py -------------------------------------------------------------------------------- /ultralytics/yolo/data/dataloaders/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/data/dataloaders/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/data/dataloaders/__pycache__/stream_loaders.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/data/dataloaders/__pycache__/stream_loaders.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/data/dataloaders/__pycache__/v5augmentations.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/data/dataloaders/__pycache__/v5augmentations.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/data/dataloaders/__pycache__/v5loader.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/data/dataloaders/__pycache__/v5loader.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/data/dataset_wrappers.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | import collections 4 | from copy import deepcopy 5 | 6 | from .augment import LetterBox 7 | 8 | 9 | class MixAndRectDataset: 10 | """A wrapper of multiple images mixed dataset. 11 | 12 | Args: 13 | dataset (:obj:`BaseDataset`): The dataset to be mixed. 14 | transforms (Sequence[dict]): config dict to be composed. 15 | """ 16 | 17 | def __init__(self, dataset): 18 | self.dataset = dataset 19 | self.imgsz = dataset.imgsz 20 | 21 | def __len__(self): 22 | return len(self.dataset) 23 | 24 | def __getitem__(self, index): 25 | labels = deepcopy(self.dataset[index]) 26 | for transform in self.dataset.transforms.tolist(): 27 | # mosaic and mixup 28 | if hasattr(transform, 'get_indexes'): 29 | indexes = transform.get_indexes(self.dataset) 30 | if not isinstance(indexes, collections.abc.Sequence): 31 | indexes = [indexes] 32 | mix_labels = [deepcopy(self.dataset[index]) for index in indexes] 33 | labels['mix_labels'] = mix_labels 34 | if self.dataset.rect and isinstance(transform, LetterBox): 35 | transform.new_shape = self.dataset.batch_shapes[self.dataset.batch[index]] 36 | labels = transform(labels) 37 | if 'mix_labels' in labels: 38 | labels.pop('mix_labels') 39 | return labels 40 | -------------------------------------------------------------------------------- /ultralytics/yolo/engine/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/engine/__init__.py -------------------------------------------------------------------------------- /ultralytics/yolo/engine/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/engine/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/engine/__pycache__/exporter.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/engine/__pycache__/exporter.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/engine/__pycache__/model.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/engine/__pycache__/model.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/engine/__pycache__/predictor.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/engine/__pycache__/predictor.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/engine/__pycache__/results.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/engine/__pycache__/results.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/engine/__pycache__/trainer.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/engine/__pycache__/trainer.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/engine/__pycache__/validator.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/engine/__pycache__/validator.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/utils/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/utils/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/utils/__pycache__/autobatch.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/utils/__pycache__/autobatch.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/utils/__pycache__/benchmarks.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/utils/__pycache__/benchmarks.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/utils/__pycache__/checks.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/utils/__pycache__/checks.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/utils/__pycache__/dist.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/utils/__pycache__/dist.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/utils/__pycache__/downloads.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/utils/__pycache__/downloads.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/utils/__pycache__/files.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/utils/__pycache__/files.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/utils/__pycache__/instance.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/utils/__pycache__/instance.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/utils/__pycache__/loss.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/utils/__pycache__/loss.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/utils/__pycache__/metrics.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/utils/__pycache__/metrics.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/utils/__pycache__/ops.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/utils/__pycache__/ops.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/utils/__pycache__/plotting.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/utils/__pycache__/plotting.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/utils/__pycache__/tal.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/utils/__pycache__/tal.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/utils/__pycache__/torch_utils.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/utils/__pycache__/torch_utils.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/utils/autobatch.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | """ 3 | Functions for estimating the best YOLO batch size to use a fraction of the available CUDA memory in PyTorch. 4 | """ 5 | 6 | from copy import deepcopy 7 | 8 | import numpy as np 9 | import torch 10 | 11 | from ultralytics.yolo.utils import LOGGER, colorstr 12 | from ultralytics.yolo.utils.torch_utils import profile 13 | 14 | 15 | def check_train_batch_size(model, imgsz=640, amp=True): 16 | """ 17 | Check YOLO training batch size using the autobatch() function. 18 | 19 | Args: 20 | model (torch.nn.Module): YOLO model to check batch size for. 21 | imgsz (int): Image size used for training. 22 | amp (bool): If True, use automatic mixed precision (AMP) for training. 23 | 24 | Returns: 25 | int: Optimal batch size computed using the autobatch() function. 26 | """ 27 | 28 | with torch.cuda.amp.autocast(amp): 29 | return autobatch(deepcopy(model).train(), imgsz) # compute optimal batch size 30 | 31 | 32 | def autobatch(model, imgsz=640, fraction=0.67, batch_size=16): 33 | """ 34 | Automatically estimate the best YOLO batch size to use a fraction of the available CUDA memory. 35 | 36 | Args: 37 | model: YOLO model to compute batch size for. 38 | imgsz (int, optional): The image size used as input for the YOLO model. Defaults to 640. 39 | fraction (float, optional): The fraction of available CUDA memory to use. Defaults to 0.67. 40 | batch_size (int, optional): The default batch size to use if an error is detected. Defaults to 16. 41 | 42 | Returns: 43 | int: The optimal batch size. 44 | """ 45 | 46 | # Check device 47 | prefix = colorstr('AutoBatch: ') 48 | LOGGER.info(f'{prefix}Computing optimal batch size for imgsz={imgsz}') 49 | device = next(model.parameters()).device # get model device 50 | if device.type == 'cpu': 51 | LOGGER.info(f'{prefix}CUDA not detected, using default CPU batch-size {batch_size}') 52 | return batch_size 53 | if torch.backends.cudnn.benchmark: 54 | LOGGER.info(f'{prefix} ⚠️ Requires torch.backends.cudnn.benchmark=False, using default batch-size {batch_size}') 55 | return batch_size 56 | 57 | # Inspect CUDA memory 58 | gb = 1 << 30 # bytes to GiB (1024 ** 3) 59 | d = str(device).upper() # 'CUDA:0' 60 | properties = torch.cuda.get_device_properties(device) # device properties 61 | t = properties.total_memory / gb # GiB total 62 | r = torch.cuda.memory_reserved(device) / gb # GiB reserved 63 | a = torch.cuda.memory_allocated(device) / gb # GiB allocated 64 | f = t - (r + a) # GiB free 65 | LOGGER.info(f'{prefix}{d} ({properties.name}) {t:.2f}G total, {r:.2f}G reserved, {a:.2f}G allocated, {f:.2f}G free') 66 | 67 | # Profile batch sizes 68 | batch_sizes = [1, 2, 4, 8, 16] 69 | try: 70 | img = [torch.empty(b, 3, imgsz, imgsz) for b in batch_sizes] 71 | results = profile(img, model, n=3, device=device) 72 | 73 | # Fit a solution 74 | y = [x[2] for x in results if x] # memory [2] 75 | p = np.polyfit(batch_sizes[:len(y)], y, deg=1) # first degree polynomial fit 76 | b = int((f * fraction - p[1]) / p[0]) # y intercept (optimal batch size) 77 | if None in results: # some sizes failed 78 | i = results.index(None) # first fail index 79 | if b >= batch_sizes[i]: # y intercept above failure point 80 | b = batch_sizes[max(i - 1, 0)] # select prior safe point 81 | if b < 1 or b > 1024: # b outside of safe range 82 | b = batch_size 83 | LOGGER.info(f'{prefix}WARNING ⚠️ CUDA anomaly detected, using default batch-size {batch_size}.') 84 | 85 | fraction = (np.polyval(p, b) + r + a) / t # actual fraction predicted 86 | LOGGER.info(f'{prefix}Using batch-size {b} for {d} {t * fraction:.2f}G/{t:.2f}G ({fraction * 100:.0f}%) ✅') 87 | return b 88 | except Exception as e: 89 | LOGGER.warning(f'{prefix}WARNING ⚠️ error detected: {e}, using default batch-size {batch_size}.') 90 | return batch_size 91 | -------------------------------------------------------------------------------- /ultralytics/yolo/utils/benchmarks.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | """ 3 | Benchmark a YOLO model formats for speed and accuracy 4 | 5 | Usage: 6 | from ultralytics.yolo.utils.benchmarks import run_benchmarks 7 | run_benchmarks(model='yolov8n.pt', imgsz=160) 8 | 9 | Format | `format=argument` | Model 10 | --- | --- | --- 11 | PyTorch | - | yolov8n.pt 12 | TorchScript | `torchscript` | yolov8n.torchscript 13 | ONNX | `onnx` | yolov8n.onnx 14 | OpenVINO | `openvino` | yolov8n_openvino_model/ 15 | TensorRT | `engine` | yolov8n.engine 16 | CoreML | `coreml` | yolov8n.mlmodel 17 | TensorFlow SavedModel | `saved_model` | yolov8n_saved_model/ 18 | TensorFlow GraphDef | `pb` | yolov8n.pb 19 | TensorFlow Lite | `tflite` | yolov8n.tflite 20 | TensorFlow Edge TPU | `edgetpu` | yolov8n_edgetpu.tflite 21 | TensorFlow.js | `tfjs` | yolov8n_web_model/ 22 | PaddlePaddle | `paddle` | yolov8n_paddle_model/ 23 | """ 24 | 25 | import platform 26 | import time 27 | from pathlib import Path 28 | 29 | from ultralytics import YOLO 30 | from ultralytics.yolo.engine.exporter import export_formats 31 | from ultralytics.yolo.utils import LINUX, LOGGER, MACOS, ROOT, SETTINGS 32 | from ultralytics.yolo.utils.checks import check_yolo 33 | from ultralytics.yolo.utils.downloads import download 34 | from ultralytics.yolo.utils.files import file_size 35 | from ultralytics.yolo.utils.torch_utils import select_device 36 | 37 | 38 | def benchmark(model=Path(SETTINGS['weights_dir']) / 'yolov8n.pt', imgsz=160, half=False, device='cpu', hard_fail=False): 39 | import pandas as pd 40 | pd.options.display.max_columns = 10 41 | pd.options.display.width = 120 42 | device = select_device(device, verbose=False) 43 | if isinstance(model, (str, Path)): 44 | model = YOLO(model) 45 | 46 | y = [] 47 | t0 = time.time() 48 | for i, (name, format, suffix, cpu, gpu) in export_formats().iterrows(): # index, (name, format, suffix, CPU, GPU) 49 | emoji, filename = '❌', None # export defaults 50 | try: 51 | assert i != 9 or LINUX, 'Edge TPU export only supported on Linux' 52 | if i == 10: 53 | assert MACOS or LINUX, 'TF.js export only supported on macOS and Linux' 54 | if 'cpu' in device.type: 55 | assert cpu, 'inference not supported on CPU' 56 | if 'cuda' in device.type: 57 | assert gpu, 'inference not supported on GPU' 58 | 59 | # Export 60 | if format == '-': 61 | filename = model.ckpt_path or model.cfg 62 | export = model # PyTorch format 63 | else: 64 | filename = model.export(imgsz=imgsz, format=format, half=half, device=device) # all others 65 | export = YOLO(filename, task=model.task) 66 | assert suffix in str(filename), 'export failed' 67 | emoji = '❎' # indicates export succeeded 68 | 69 | # Predict 70 | assert i not in (9, 10), 'inference not supported' # Edge TPU and TF.js are unsupported 71 | assert i != 5 or platform.system() == 'Darwin', 'inference only supported on macOS>=10.13' # CoreML 72 | if not (ROOT / 'assets/bus.jpg').exists(): 73 | download(url='https://ultralytics.com/images/bus.jpg', dir=ROOT / 'assets') 74 | export.predict(ROOT / 'assets/bus.jpg', imgsz=imgsz, device=device, half=half) 75 | 76 | # Validate 77 | if model.task == 'detect': 78 | data, key = 'coco8.yaml', 'metrics/mAP50-95(B)' 79 | elif model.task == 'segment': 80 | data, key = 'coco8-seg.yaml', 'metrics/mAP50-95(M)' 81 | elif model.task == 'classify': 82 | data, key = 'imagenet100', 'metrics/accuracy_top5' 83 | elif model.task == 'pose': 84 | data, key = 'coco8-pose.yaml', 'metrics/mAP50-95(P)' 85 | 86 | results = export.val(data=data, batch=1, imgsz=imgsz, plots=False, device=device, half=half, verbose=False) 87 | metric, speed = results.results_dict[key], results.speed['inference'] 88 | y.append([name, '✅', round(file_size(filename), 1), round(metric, 4), round(speed, 2)]) 89 | except Exception as e: 90 | if hard_fail: 91 | assert type(e) is AssertionError, f'Benchmark hard_fail for {name}: {e}' 92 | LOGGER.warning(f'ERROR ❌️ Benchmark failure for {name}: {e}') 93 | y.append([name, emoji, round(file_size(filename), 1), None, None]) # mAP, t_inference 94 | 95 | # Print results 96 | check_yolo(device=device) # print system info 97 | df = pd.DataFrame(y, columns=['Format', 'Status❔', 'Size (MB)', key, 'Inference time (ms/im)']) 98 | 99 | name = Path(model.ckpt_path).name 100 | s = f'\nBenchmarks complete for {name} on {data} at imgsz={imgsz} ({time.time() - t0:.2f}s)\n{df}\n' 101 | LOGGER.info(s) 102 | with open('benchmarks.log', 'a', errors='ignore', encoding='utf-8') as f: 103 | f.write(s) 104 | 105 | if hard_fail and isinstance(hard_fail, float): 106 | metrics = df[key].array # values to compare to floor 107 | floor = hard_fail # minimum metric floor to pass, i.e. = 0.29 mAP for YOLOv5n 108 | assert all(x > floor for x in metrics if pd.notna(x)), f'HARD FAIL: one or more metric(s) < floor {floor}' 109 | 110 | return df 111 | 112 | 113 | if __name__ == '__main__': 114 | benchmark() 115 | -------------------------------------------------------------------------------- /ultralytics/yolo/utils/callbacks/__init__.py: -------------------------------------------------------------------------------- 1 | from .base import add_integration_callbacks, default_callbacks, get_default_callbacks 2 | 3 | __all__ = 'add_integration_callbacks', 'default_callbacks', 'get_default_callbacks' 4 | -------------------------------------------------------------------------------- /ultralytics/yolo/utils/callbacks/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/utils/callbacks/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/utils/callbacks/__pycache__/base.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/utils/callbacks/__pycache__/base.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/utils/callbacks/__pycache__/clearml.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/utils/callbacks/__pycache__/clearml.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/utils/callbacks/__pycache__/comet.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/utils/callbacks/__pycache__/comet.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/utils/callbacks/__pycache__/hub.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/utils/callbacks/__pycache__/hub.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/utils/callbacks/__pycache__/mlflow.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/utils/callbacks/__pycache__/mlflow.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/utils/callbacks/__pycache__/tensorboard.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/utils/callbacks/__pycache__/tensorboard.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/utils/callbacks/base.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | """ 3 | Base callbacks 4 | """ 5 | from collections import defaultdict 6 | from copy import deepcopy 7 | 8 | 9 | # Trainer callbacks ---------------------------------------------------------------------------------------------------- 10 | def on_pretrain_routine_start(trainer): 11 | pass 12 | 13 | 14 | def on_pretrain_routine_end(trainer): 15 | pass 16 | 17 | 18 | def on_train_start(trainer): 19 | pass 20 | 21 | 22 | def on_train_epoch_start(trainer): 23 | pass 24 | 25 | 26 | def on_train_batch_start(trainer): 27 | pass 28 | 29 | 30 | def optimizer_step(trainer): 31 | pass 32 | 33 | 34 | def on_before_zero_grad(trainer): 35 | pass 36 | 37 | 38 | def on_train_batch_end(trainer): 39 | pass 40 | 41 | 42 | def on_train_epoch_end(trainer): 43 | pass 44 | 45 | 46 | def on_fit_epoch_end(trainer): 47 | pass 48 | 49 | 50 | def on_model_save(trainer): 51 | pass 52 | 53 | 54 | def on_train_end(trainer): 55 | pass 56 | 57 | 58 | def on_params_update(trainer): 59 | pass 60 | 61 | 62 | def teardown(trainer): 63 | pass 64 | 65 | 66 | # Validator callbacks -------------------------------------------------------------------------------------------------- 67 | def on_val_start(validator): 68 | pass 69 | 70 | 71 | def on_val_batch_start(validator): 72 | pass 73 | 74 | 75 | def on_val_batch_end(validator): 76 | pass 77 | 78 | 79 | def on_val_end(validator): 80 | pass 81 | 82 | 83 | # Predictor callbacks -------------------------------------------------------------------------------------------------- 84 | def on_predict_start(predictor): 85 | pass 86 | 87 | 88 | def on_predict_batch_start(predictor): 89 | pass 90 | 91 | 92 | def on_predict_batch_end(predictor): 93 | pass 94 | 95 | 96 | def on_predict_postprocess_end(predictor): 97 | pass 98 | 99 | 100 | def on_predict_end(predictor): 101 | pass 102 | 103 | 104 | # Exporter callbacks --------------------------------------------------------------------------------------------------- 105 | def on_export_start(exporter): 106 | pass 107 | 108 | 109 | def on_export_end(exporter): 110 | pass 111 | 112 | 113 | default_callbacks = { 114 | # Run in trainer 115 | 'on_pretrain_routine_start': [on_pretrain_routine_start], 116 | 'on_pretrain_routine_end': [on_pretrain_routine_end], 117 | 'on_train_start': [on_train_start], 118 | 'on_train_epoch_start': [on_train_epoch_start], 119 | 'on_train_batch_start': [on_train_batch_start], 120 | 'optimizer_step': [optimizer_step], 121 | 'on_before_zero_grad': [on_before_zero_grad], 122 | 'on_train_batch_end': [on_train_batch_end], 123 | 'on_train_epoch_end': [on_train_epoch_end], 124 | 'on_fit_epoch_end': [on_fit_epoch_end], # fit = train + val 125 | 'on_model_save': [on_model_save], 126 | 'on_train_end': [on_train_end], 127 | 'on_params_update': [on_params_update], 128 | 'teardown': [teardown], 129 | 130 | # Run in validator 131 | 'on_val_start': [on_val_start], 132 | 'on_val_batch_start': [on_val_batch_start], 133 | 'on_val_batch_end': [on_val_batch_end], 134 | 'on_val_end': [on_val_end], 135 | 136 | # Run in predictor 137 | 'on_predict_start': [on_predict_start], 138 | 'on_predict_batch_start': [on_predict_batch_start], 139 | 'on_predict_postprocess_end': [on_predict_postprocess_end], 140 | 'on_predict_batch_end': [on_predict_batch_end], 141 | 'on_predict_end': [on_predict_end], 142 | 143 | # Run in exporter 144 | 'on_export_start': [on_export_start], 145 | 'on_export_end': [on_export_end]} 146 | 147 | 148 | def get_default_callbacks(): 149 | return defaultdict(list, deepcopy(default_callbacks)) 150 | 151 | 152 | def add_integration_callbacks(instance): 153 | from .clearml import callbacks as clearml_callbacks 154 | from .comet import callbacks as comet_callbacks 155 | from .hub import callbacks as hub_callbacks 156 | from .mlflow import callbacks as mf_callbacks 157 | from .tensorboard import callbacks as tb_callbacks 158 | 159 | for x in clearml_callbacks, comet_callbacks, hub_callbacks, tb_callbacks, mf_callbacks: 160 | for k, v in x.items(): 161 | if v not in instance.callbacks[k]: # prevent duplicate callbacks addition 162 | instance.callbacks[k].append(v) # callback[name].append(func) 163 | -------------------------------------------------------------------------------- /ultralytics/yolo/utils/callbacks/clearml.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | import re 3 | 4 | import matplotlib.image as mpimg 5 | import matplotlib.pyplot as plt 6 | 7 | from ultralytics.yolo.utils import LOGGER, TESTS_RUNNING 8 | from ultralytics.yolo.utils.torch_utils import get_flops, get_num_params 9 | 10 | try: 11 | import clearml 12 | from clearml import Task 13 | from clearml.binding.frameworks.pytorch_bind import PatchPyTorchModelIO 14 | from clearml.binding.matplotlib_bind import PatchedMatplotlib 15 | 16 | assert hasattr(clearml, '__version__') # verify package is not directory 17 | assert not TESTS_RUNNING # do not log pytest 18 | except (ImportError, AssertionError): 19 | clearml = None 20 | 21 | 22 | def _log_debug_samples(files, title='Debug Samples'): 23 | """ 24 | Log files (images) as debug samples in the ClearML task. 25 | 26 | arguments: 27 | files (List(PosixPath)) a list of file paths in PosixPath format 28 | title (str) A title that groups together images with the same values 29 | """ 30 | task = Task.current_task() 31 | if task: 32 | for f in files: 33 | if f.exists(): 34 | it = re.search(r'_batch(\d+)', f.name) 35 | iteration = int(it.groups()[0]) if it else 0 36 | task.get_logger().report_image(title=title, 37 | series=f.name.replace(it.group(), ''), 38 | local_path=str(f), 39 | iteration=iteration) 40 | 41 | 42 | def _log_plot(title, plot_path): 43 | """ 44 | Log image as plot in the plot section of ClearML 45 | 46 | arguments: 47 | title (str) Title of the plot 48 | plot_path (PosixPath or str) Path to the saved image file 49 | """ 50 | img = mpimg.imread(plot_path) 51 | fig = plt.figure() 52 | ax = fig.add_axes([0, 0, 1, 1], frameon=False, aspect='auto', xticks=[], yticks=[]) # no ticks 53 | ax.imshow(img) 54 | 55 | Task.current_task().get_logger().report_matplotlib_figure(title, '', figure=fig, report_interactive=False) 56 | 57 | 58 | def on_pretrain_routine_start(trainer): 59 | try: 60 | task = Task.current_task() 61 | if task: 62 | # Make sure the automatic pytorch and matplotlib bindings are disabled! 63 | # We are logging these plots and model files manually in the integration 64 | PatchPyTorchModelIO.update_current_task(None) 65 | PatchedMatplotlib.update_current_task(None) 66 | else: 67 | task = Task.init(project_name=trainer.args.project or 'YOLOv8', 68 | task_name=trainer.args.name, 69 | tags=['YOLOv8'], 70 | output_uri=True, 71 | reuse_last_task_id=False, 72 | auto_connect_frameworks={ 73 | 'pytorch': False, 74 | 'matplotlib': False}) 75 | LOGGER.warning('ClearML Initialized a new task. If you want to run remotely, ' 76 | 'please add clearml-init and connect your arguments before initializing YOLO.') 77 | task.connect(vars(trainer.args), name='General') 78 | except Exception as e: 79 | LOGGER.warning(f'WARNING ⚠️ ClearML installed but not initialized correctly, not logging this run. {e}') 80 | 81 | 82 | def on_train_epoch_end(trainer): 83 | if trainer.epoch == 1 and Task.current_task(): 84 | _log_debug_samples(sorted(trainer.save_dir.glob('train_batch*.jpg')), 'Mosaic') 85 | 86 | 87 | def on_fit_epoch_end(trainer): 88 | task = Task.current_task() 89 | if task: 90 | # You should have access to the validation bboxes under jdict 91 | task.get_logger().report_scalar(title='Epoch Time', 92 | series='Epoch Time', 93 | value=trainer.epoch_time, 94 | iteration=trainer.epoch) 95 | if trainer.epoch == 0: 96 | model_info = { 97 | 'model/parameters': get_num_params(trainer.model), 98 | 'model/GFLOPs': round(get_flops(trainer.model), 3), 99 | 'model/speed(ms)': round(trainer.validator.speed['inference'], 3)} 100 | for k, v in model_info.items(): 101 | task.get_logger().report_single_value(k, v) 102 | 103 | 104 | def on_val_end(validator): 105 | if Task.current_task(): 106 | # Log val_labels and val_pred 107 | _log_debug_samples(sorted(validator.save_dir.glob('val*.jpg')), 'Validation') 108 | 109 | 110 | def on_train_end(trainer): 111 | task = Task.current_task() 112 | if task: 113 | # Log final results, CM matrix + PR plots 114 | files = ['results.png', 'confusion_matrix.png', *(f'{x}_curve.png' for x in ('F1', 'PR', 'P', 'R'))] 115 | files = [(trainer.save_dir / f) for f in files if (trainer.save_dir / f).exists()] # filter 116 | for f in files: 117 | _log_plot(title=f.stem, plot_path=f) 118 | # Report final metrics 119 | for k, v in trainer.validator.metrics.results_dict.items(): 120 | task.get_logger().report_single_value(k, v) 121 | # Log the final model 122 | task.update_output_model(model_path=str(trainer.best), model_name=trainer.args.name, auto_delete_file=False) 123 | 124 | 125 | callbacks = { 126 | 'on_pretrain_routine_start': on_pretrain_routine_start, 127 | 'on_train_epoch_end': on_train_epoch_end, 128 | 'on_fit_epoch_end': on_fit_epoch_end, 129 | 'on_val_end': on_val_end, 130 | 'on_train_end': on_train_end} if clearml else {} 131 | -------------------------------------------------------------------------------- /ultralytics/yolo/utils/callbacks/hub.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | import json 4 | from time import time 5 | 6 | from ultralytics.hub.utils import PREFIX, traces 7 | from ultralytics.yolo.utils import LOGGER 8 | from ultralytics.yolo.utils.torch_utils import get_flops, get_num_params 9 | 10 | 11 | def on_pretrain_routine_end(trainer): 12 | session = getattr(trainer, 'hub_session', None) 13 | if session: 14 | # Start timer for upload rate limit 15 | LOGGER.info(f'{PREFIX}View model at https://hub.ultralytics.com/models/{session.model_id} 🚀') 16 | session.timers = {'metrics': time(), 'ckpt': time()} # start timer on session.rate_limit 17 | 18 | 19 | def on_fit_epoch_end(trainer): 20 | session = getattr(trainer, 'hub_session', None) 21 | if session: 22 | # Upload metrics after val end 23 | all_plots = {**trainer.label_loss_items(trainer.tloss, prefix='train'), **trainer.metrics} 24 | if trainer.epoch == 0: 25 | model_info = { 26 | 'model/parameters': get_num_params(trainer.model), 27 | 'model/GFLOPs': round(get_flops(trainer.model), 3), 28 | 'model/speed(ms)': round(trainer.validator.speed['inference'], 3)} 29 | all_plots = {**all_plots, **model_info} 30 | session.metrics_queue[trainer.epoch] = json.dumps(all_plots) 31 | if time() - session.timers['metrics'] > session.rate_limits['metrics']: 32 | session.upload_metrics() 33 | session.timers['metrics'] = time() # reset timer 34 | session.metrics_queue = {} # reset queue 35 | 36 | 37 | def on_model_save(trainer): 38 | session = getattr(trainer, 'hub_session', None) 39 | if session: 40 | # Upload checkpoints with rate limiting 41 | is_best = trainer.best_fitness == trainer.fitness 42 | if time() - session.timers['ckpt'] > session.rate_limits['ckpt']: 43 | LOGGER.info(f'{PREFIX}Uploading checkpoint https://hub.ultralytics.com/models/{session.model_id}') 44 | session.upload_model(trainer.epoch, trainer.last, is_best) 45 | session.timers['ckpt'] = time() # reset timer 46 | 47 | 48 | def on_train_end(trainer): 49 | session = getattr(trainer, 'hub_session', None) 50 | if session: 51 | # Upload final model and metrics with exponential standoff 52 | LOGGER.info(f'{PREFIX}Syncing final model...') 53 | session.upload_model(trainer.epoch, trainer.best, map=trainer.metrics.get('metrics/mAP50-95(B)', 0), final=True) 54 | session.alive = False # stop heartbeats 55 | LOGGER.info(f'{PREFIX}Done ✅\n' 56 | f'{PREFIX}View model at https://hub.ultralytics.com/models/{session.model_id} 🚀') 57 | 58 | 59 | def on_train_start(trainer): 60 | traces(trainer.args, traces_sample_rate=1.0) 61 | 62 | 63 | def on_val_start(validator): 64 | traces(validator.args, traces_sample_rate=1.0) 65 | 66 | 67 | def on_predict_start(predictor): 68 | traces(predictor.args, traces_sample_rate=1.0) 69 | 70 | 71 | def on_export_start(exporter): 72 | traces(exporter.args, traces_sample_rate=1.0) 73 | 74 | 75 | callbacks = { 76 | 'on_pretrain_routine_end': on_pretrain_routine_end, 77 | 'on_fit_epoch_end': on_fit_epoch_end, 78 | 'on_model_save': on_model_save, 79 | 'on_train_end': on_train_end, 80 | 'on_train_start': on_train_start, 81 | 'on_val_start': on_val_start, 82 | 'on_predict_start': on_predict_start, 83 | 'on_export_start': on_export_start} 84 | -------------------------------------------------------------------------------- /ultralytics/yolo/utils/callbacks/mlflow.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | import os 4 | import re 5 | from pathlib import Path 6 | 7 | from ultralytics.yolo.utils import LOGGER, TESTS_RUNNING, colorstr 8 | 9 | try: 10 | import mlflow 11 | 12 | assert not TESTS_RUNNING # do not log pytest 13 | assert hasattr(mlflow, '__version__') # verify package is not directory 14 | except (ImportError, AssertionError): 15 | mlflow = None 16 | 17 | 18 | def on_pretrain_routine_end(trainer): 19 | global mlflow, run, run_id, experiment_name 20 | 21 | if os.environ.get('MLFLOW_TRACKING_URI') is None: 22 | mlflow = None 23 | 24 | if mlflow: 25 | mlflow_location = os.environ['MLFLOW_TRACKING_URI'] # "http://192.168.xxx.xxx:5000" 26 | mlflow.set_tracking_uri(mlflow_location) 27 | 28 | experiment_name = trainer.args.project or '/Shared/YOLOv8' 29 | experiment = mlflow.get_experiment_by_name(experiment_name) 30 | if experiment is None: 31 | mlflow.create_experiment(experiment_name) 32 | mlflow.set_experiment(experiment_name) 33 | 34 | prefix = colorstr('MLFlow: ') 35 | try: 36 | run, active_run = mlflow, mlflow.active_run() 37 | if not active_run: 38 | active_run = mlflow.start_run(experiment_id=experiment.experiment_id) 39 | run_id = active_run.info.run_id 40 | LOGGER.info(f'{prefix}Using run_id({run_id}) at {mlflow_location}') 41 | run.log_params(vars(trainer.model.args)) 42 | except Exception as err: 43 | LOGGER.error(f'{prefix}Failing init - {repr(err)}') 44 | LOGGER.warning(f'{prefix}Continuing without Mlflow') 45 | 46 | 47 | def on_fit_epoch_end(trainer): 48 | if mlflow: 49 | metrics_dict = {f"{re.sub('[()]', '', k)}": float(v) for k, v in trainer.metrics.items()} 50 | run.log_metrics(metrics=metrics_dict, step=trainer.epoch) 51 | 52 | 53 | def on_model_save(trainer): 54 | if mlflow: 55 | run.log_artifact(trainer.last) 56 | 57 | 58 | def on_train_end(trainer): 59 | if mlflow: 60 | root_dir = Path(__file__).resolve().parents[3] 61 | run.log_artifact(trainer.best) 62 | model_uri = f'runs:/{run_id}/' 63 | run.register_model(model_uri, experiment_name) 64 | run.pyfunc.log_model(artifact_path=experiment_name, 65 | code_path=[str(root_dir)], 66 | artifacts={'model_path': str(trainer.save_dir)}, 67 | python_model=run.pyfunc.PythonModel()) 68 | 69 | 70 | callbacks = { 71 | 'on_pretrain_routine_end': on_pretrain_routine_end, 72 | 'on_fit_epoch_end': on_fit_epoch_end, 73 | 'on_model_save': on_model_save, 74 | 'on_train_end': on_train_end} if mlflow else {} 75 | -------------------------------------------------------------------------------- /ultralytics/yolo/utils/callbacks/tensorboard.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | from ultralytics.yolo.utils import LOGGER, TESTS_RUNNING, colorstr 3 | 4 | try: 5 | from torch.utils.tensorboard import SummaryWriter 6 | 7 | assert not TESTS_RUNNING # do not log pytest 8 | except (ImportError, AssertionError): 9 | SummaryWriter = None 10 | 11 | writer = None # TensorBoard SummaryWriter instance 12 | 13 | 14 | def _log_scalars(scalars, step=0): 15 | if writer: 16 | for k, v in scalars.items(): 17 | writer.add_scalar(k, v, step) 18 | 19 | 20 | def on_pretrain_routine_start(trainer): 21 | if SummaryWriter: 22 | try: 23 | global writer 24 | writer = SummaryWriter(str(trainer.save_dir)) 25 | prefix = colorstr('TensorBoard: ') 26 | LOGGER.info(f"{prefix}Start with 'tensorboard --logdir {trainer.save_dir}', view at http://localhost:6006/") 27 | except Exception as e: 28 | LOGGER.warning(f'WARNING ⚠️ TensorBoard not initialized correctly, not logging this run. {e}') 29 | 30 | 31 | def on_batch_end(trainer): 32 | _log_scalars(trainer.label_loss_items(trainer.tloss, prefix='train'), trainer.epoch + 1) 33 | 34 | 35 | def on_fit_epoch_end(trainer): 36 | _log_scalars(trainer.metrics, trainer.epoch + 1) 37 | 38 | 39 | callbacks = { 40 | 'on_pretrain_routine_start': on_pretrain_routine_start, 41 | 'on_fit_epoch_end': on_fit_epoch_end, 42 | 'on_batch_end': on_batch_end} 43 | -------------------------------------------------------------------------------- /ultralytics/yolo/utils/dist.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | import os 4 | import re 5 | import shutil 6 | import socket 7 | import sys 8 | import tempfile 9 | from pathlib import Path 10 | 11 | from . import USER_CONFIG_DIR 12 | from .torch_utils import TORCH_1_9 13 | 14 | 15 | def find_free_network_port() -> int: 16 | """Finds a free port on localhost. 17 | 18 | It is useful in single-node training when we don't want to connect to a real main node but have to set the 19 | `MASTER_PORT` environment variable. 20 | """ 21 | with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: 22 | s.bind(('127.0.0.1', 0)) 23 | return s.getsockname()[1] # port 24 | 25 | 26 | def generate_ddp_file(trainer): 27 | module, name = f'{trainer.__class__.__module__}.{trainer.__class__.__name__}'.rsplit('.', 1) 28 | 29 | content = f'''cfg = {vars(trainer.args)} \nif __name__ == "__main__": 30 | from {module} import {name} 31 | 32 | trainer = {name}(cfg=cfg) 33 | trainer.train()''' 34 | (USER_CONFIG_DIR / 'DDP').mkdir(exist_ok=True) 35 | with tempfile.NamedTemporaryFile(prefix='_temp_', 36 | suffix=f'{id(trainer)}.py', 37 | mode='w+', 38 | encoding='utf-8', 39 | dir=USER_CONFIG_DIR / 'DDP', 40 | delete=False) as file: 41 | file.write(content) 42 | return file.name 43 | 44 | 45 | def generate_ddp_command(world_size, trainer): 46 | import __main__ # noqa local import to avoid https://github.com/Lightning-AI/lightning/issues/15218 47 | if not trainer.resume: 48 | shutil.rmtree(trainer.save_dir) # remove the save_dir 49 | file = str(Path(sys.argv[0]).resolve()) 50 | safe_pattern = re.compile(r'^[a-zA-Z0-9_. /\\-]{1,128}$') # allowed characters and maximum of 100 characters 51 | if not (safe_pattern.match(file) and Path(file).exists() and file.endswith('.py')): # using CLI 52 | file = generate_ddp_file(trainer) 53 | dist_cmd = 'torch.distributed.run' if TORCH_1_9 else 'torch.distributed.launch' 54 | port = find_free_network_port() 55 | exclude_args = ['save_dir'] 56 | args = [f'{k}={v}' for k, v in vars(trainer.args).items() if k not in exclude_args] 57 | cmd = [sys.executable, '-m', dist_cmd, '--nproc_per_node', f'{world_size}', '--master_port', f'{port}', file] + args 58 | return cmd, file 59 | 60 | 61 | def ddp_cleanup(trainer, file): 62 | # delete temp file if created 63 | if f'{id(trainer)}.py' in file: # if temp_file suffix in file 64 | os.remove(file) 65 | -------------------------------------------------------------------------------- /ultralytics/yolo/utils/files.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | import contextlib 4 | import glob 5 | import os 6 | from datetime import datetime 7 | from pathlib import Path 8 | 9 | 10 | class WorkingDirectory(contextlib.ContextDecorator): 11 | # Usage: @WorkingDirectory(dir) decorator or 'with WorkingDirectory(dir):' context manager 12 | def __init__(self, new_dir): 13 | self.dir = new_dir # new dir 14 | self.cwd = Path.cwd().resolve() # current dir 15 | 16 | def __enter__(self): 17 | os.chdir(self.dir) 18 | 19 | def __exit__(self, exc_type, exc_val, exc_tb): 20 | os.chdir(self.cwd) 21 | 22 | 23 | def increment_path(path, exist_ok=False, sep='', mkdir=False): 24 | """ 25 | Increments a file or directory path, i.e. runs/exp --> runs/exp{sep}2, runs/exp{sep}3, ... etc. 26 | 27 | If the path exists and exist_ok is not set to True, the path will be incremented by appending a number and sep to 28 | the end of the path. If the path is a file, the file extension will be preserved. If the path is a directory, the 29 | number will be appended directly to the end of the path. If mkdir is set to True, the path will be created as a 30 | directory if it does not already exist. 31 | 32 | Args: 33 | path (str or pathlib.Path): Path to increment. 34 | exist_ok (bool, optional): If True, the path will not be incremented and will be returned as-is. Defaults to False. 35 | sep (str, optional): Separator to use between the path and the incrementation number. Defaults to an empty string. 36 | mkdir (bool, optional): If True, the path will be created as a directory if it does not exist. Defaults to False. 37 | 38 | Returns: 39 | pathlib.Path: Incremented path. 40 | """ 41 | path = Path(path) # os-agnostic 42 | if path.exists() and not exist_ok: 43 | path, suffix = (path.with_suffix(''), path.suffix) if path.is_file() else (path, '') 44 | 45 | # Method 1 46 | for n in range(2, 9999): 47 | p = f'{path}{sep}{n}{suffix}' # increment path 48 | if not os.path.exists(p): # 49 | break 50 | path = Path(p) 51 | 52 | if mkdir: 53 | path.mkdir(parents=True, exist_ok=True) # make directory 54 | 55 | return path 56 | 57 | 58 | def file_age(path=__file__): 59 | # Return days since last file update 60 | dt = (datetime.now() - datetime.fromtimestamp(Path(path).stat().st_mtime)) # delta 61 | return dt.days # + dt.seconds / 86400 # fractional days 62 | 63 | 64 | def file_date(path=__file__): 65 | # Return human-readable file modification date, i.e. '2021-3-26' 66 | t = datetime.fromtimestamp(Path(path).stat().st_mtime) 67 | return f'{t.year}-{t.month}-{t.day}' 68 | 69 | 70 | def file_size(path): 71 | # Return file/dir size (MB) 72 | if isinstance(path, (str, Path)): 73 | mb = 1 << 20 # bytes to MiB (1024 ** 2) 74 | path = Path(path) 75 | if path.is_file(): 76 | return path.stat().st_size / mb 77 | elif path.is_dir(): 78 | return sum(f.stat().st_size for f in path.glob('**/*') if f.is_file()) / mb 79 | return 0.0 80 | 81 | 82 | def get_latest_run(search_dir='.'): 83 | # Return path to most recent 'last.pt' in /runs (i.e. to --resume from) 84 | last_list = glob.glob(f'{search_dir}/**/last*.pt', recursive=True) 85 | return max(last_list, key=os.path.getctime) if last_list else '' 86 | -------------------------------------------------------------------------------- /ultralytics/yolo/utils/loss.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | import torch 4 | import torch.nn as nn 5 | import torch.nn.functional as F 6 | 7 | from .metrics import bbox_iou 8 | from .tal import bbox2dist 9 | 10 | 11 | class VarifocalLoss(nn.Module): 12 | # Varifocal loss by Zhang et al. https://arxiv.org/abs/2008.13367 13 | def __init__(self): 14 | super().__init__() 15 | 16 | def forward(self, pred_score, gt_score, label, alpha=0.75, gamma=2.0): 17 | weight = alpha * pred_score.sigmoid().pow(gamma) * (1 - label) + gt_score * label 18 | with torch.cuda.amp.autocast(enabled=False): 19 | loss = (F.binary_cross_entropy_with_logits(pred_score.float(), gt_score.float(), reduction='none') * 20 | weight).sum() 21 | return loss 22 | 23 | 24 | class BboxLoss(nn.Module): 25 | 26 | def __init__(self, reg_max, use_dfl=False): 27 | super().__init__() 28 | self.reg_max = reg_max 29 | self.use_dfl = use_dfl 30 | 31 | def forward(self, pred_dist, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask): 32 | # IoU loss 33 | weight = torch.masked_select(target_scores.sum(-1), fg_mask).unsqueeze(-1) 34 | iou = bbox_iou(pred_bboxes[fg_mask], target_bboxes[fg_mask], xywh=False, CIoU=True) 35 | loss_iou = ((1.0 - iou) * weight).sum() / target_scores_sum 36 | 37 | # DFL loss 38 | if self.use_dfl: 39 | target_ltrb = bbox2dist(anchor_points, target_bboxes, self.reg_max) 40 | loss_dfl = self._df_loss(pred_dist[fg_mask].view(-1, self.reg_max + 1), target_ltrb[fg_mask]) * weight 41 | loss_dfl = loss_dfl.sum() / target_scores_sum 42 | else: 43 | loss_dfl = torch.tensor(0.0).to(pred_dist.device) 44 | 45 | return loss_iou, loss_dfl 46 | 47 | @staticmethod 48 | def _df_loss(pred_dist, target): 49 | # Return sum of left and right DFL losses 50 | # Distribution Focal Loss (DFL) proposed in Generalized Focal Loss https://ieeexplore.ieee.org/document/9792391 51 | tl = target.long() # target left 52 | tr = tl + 1 # target right 53 | wl = tr - target # weight left 54 | wr = 1 - wl # weight right 55 | return (F.cross_entropy(pred_dist, tl.view(-1), reduction='none').view(tl.shape) * wl + 56 | F.cross_entropy(pred_dist, tr.view(-1), reduction='none').view(tl.shape) * wr).mean(-1, keepdim=True) 57 | 58 | 59 | class KeypointLoss(nn.Module): 60 | 61 | def __init__(self, sigmas) -> None: 62 | super().__init__() 63 | self.sigmas = sigmas 64 | 65 | def forward(self, pred_kpts, gt_kpts, kpt_mask, area): 66 | d = (pred_kpts[..., 0] - gt_kpts[..., 0]) ** 2 + (pred_kpts[..., 1] - gt_kpts[..., 1]) ** 2 67 | kpt_loss_factor = (torch.sum(kpt_mask != 0) + torch.sum(kpt_mask == 0)) / (torch.sum(kpt_mask != 0) + 1e-9) 68 | # e = d / (2 * (area * self.sigmas) ** 2 + 1e-9) # from formula 69 | e = d / (2 * self.sigmas) ** 2 / (area + 1e-9) / 2 # from cocoeval 70 | return kpt_loss_factor * ((1 - torch.exp(-e)) * kpt_mask).mean() 71 | -------------------------------------------------------------------------------- /ultralytics/yolo/v8/__init__.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | from ultralytics.yolo.v8 import classify, detect, pose, segment 4 | 5 | __all__ = 'classify', 'segment', 'detect', 'pose' 6 | -------------------------------------------------------------------------------- /ultralytics/yolo/v8/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/v8/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/v8/classify/__init__.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | from ultralytics.yolo.v8.classify.predict import ClassificationPredictor, predict 4 | from ultralytics.yolo.v8.classify.train import ClassificationTrainer, train 5 | from ultralytics.yolo.v8.classify.val import ClassificationValidator, val 6 | 7 | __all__ = 'ClassificationPredictor', 'predict', 'ClassificationTrainer', 'train', 'ClassificationValidator', 'val' 8 | -------------------------------------------------------------------------------- /ultralytics/yolo/v8/classify/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/v8/classify/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/v8/classify/__pycache__/predict.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/v8/classify/__pycache__/predict.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/v8/classify/__pycache__/train.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/v8/classify/__pycache__/train.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/v8/classify/__pycache__/val.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/v8/classify/__pycache__/val.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/v8/classify/predict.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | import torch 4 | 5 | from ultralytics.yolo.engine.predictor import BasePredictor 6 | from ultralytics.yolo.engine.results import Results 7 | from ultralytics.yolo.utils import DEFAULT_CFG, ROOT 8 | 9 | 10 | class ClassificationPredictor(BasePredictor): 11 | 12 | def preprocess(self, img): 13 | img = (img if isinstance(img, torch.Tensor) else torch.from_numpy(img)).to(self.model.device) 14 | return img.half() if self.model.fp16 else img.float() # uint8 to fp16/32 15 | 16 | def postprocess(self, preds, img, orig_imgs): 17 | results = [] 18 | for i, pred in enumerate(preds): 19 | orig_img = orig_imgs[i] if isinstance(orig_imgs, list) else orig_imgs 20 | path, _, _, _, _ = self.batch 21 | img_path = path[i] if isinstance(path, list) else path 22 | results.append(Results(orig_img=orig_img, path=img_path, names=self.model.names, probs=pred)) 23 | 24 | return results 25 | 26 | 27 | def predict(cfg=DEFAULT_CFG, use_python=False): 28 | model = cfg.model or 'yolov8n-cls.pt' # or "resnet18" 29 | source = cfg.source if cfg.source is not None else ROOT / 'assets' if (ROOT / 'assets').exists() \ 30 | else 'https://ultralytics.com/images/bus.jpg' 31 | 32 | args = dict(model=model, source=source) 33 | if use_python: 34 | from ultralytics import YOLO 35 | YOLO(model)(**args) 36 | else: 37 | predictor = ClassificationPredictor(overrides=args) 38 | predictor.predict_cli() 39 | 40 | 41 | if __name__ == '__main__': 42 | predict() 43 | -------------------------------------------------------------------------------- /ultralytics/yolo/v8/classify/train.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | import torch 4 | import torchvision 5 | 6 | from ultralytics.nn.tasks import ClassificationModel, attempt_load_one_weight 7 | from ultralytics.yolo import v8 8 | from ultralytics.yolo.data import build_classification_dataloader 9 | from ultralytics.yolo.engine.trainer import BaseTrainer 10 | from ultralytics.yolo.utils import DEFAULT_CFG, LOGGER, RANK, colorstr 11 | from ultralytics.yolo.utils.torch_utils import is_parallel, strip_optimizer 12 | 13 | 14 | class ClassificationTrainer(BaseTrainer): 15 | 16 | def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None): 17 | if overrides is None: 18 | overrides = {} 19 | overrides['task'] = 'classify' 20 | super().__init__(cfg, overrides, _callbacks) 21 | 22 | def set_model_attributes(self): 23 | self.model.names = self.data['names'] 24 | 25 | def get_model(self, cfg=None, weights=None, verbose=True): 26 | model = ClassificationModel(cfg, nc=self.data['nc'], verbose=verbose and RANK == -1) 27 | if weights: 28 | model.load(weights) 29 | 30 | pretrained = False 31 | for m in model.modules(): 32 | if not pretrained and hasattr(m, 'reset_parameters'): 33 | m.reset_parameters() 34 | if isinstance(m, torch.nn.Dropout) and self.args.dropout: 35 | m.p = self.args.dropout # set dropout 36 | for p in model.parameters(): 37 | p.requires_grad = True # for training 38 | 39 | # Update defaults 40 | if self.args.imgsz == 640: 41 | self.args.imgsz = 224 42 | 43 | return model 44 | 45 | def setup_model(self): 46 | """ 47 | load/create/download model for any task 48 | """ 49 | # classification models require special handling 50 | 51 | if isinstance(self.model, torch.nn.Module): # if model is loaded beforehand. No setup needed 52 | return 53 | 54 | model = str(self.model) 55 | # Load a YOLO model locally, from torchvision, or from Ultralytics assets 56 | if model.endswith('.pt'): 57 | self.model, _ = attempt_load_one_weight(model, device='cpu') 58 | for p in self.model.parameters(): 59 | p.requires_grad = True # for training 60 | elif model.endswith('.yaml'): 61 | self.model = self.get_model(cfg=model) 62 | elif model in torchvision.models.__dict__: 63 | pretrained = True 64 | self.model = torchvision.models.__dict__[model](weights='IMAGENET1K_V1' if pretrained else None) 65 | else: 66 | FileNotFoundError(f'ERROR: model={model} not found locally or online. Please check model name.') 67 | ClassificationModel.reshape_outputs(self.model, self.data['nc']) 68 | 69 | return # dont return ckpt. Classification doesn't support resume 70 | 71 | def get_dataloader(self, dataset_path, batch_size=16, rank=0, mode='train'): 72 | loader = build_classification_dataloader(path=dataset_path, 73 | imgsz=self.args.imgsz, 74 | batch_size=batch_size if mode == 'train' else (batch_size * 2), 75 | augment=mode == 'train', 76 | rank=rank, 77 | workers=self.args.workers) 78 | # Attach inference transforms 79 | if mode != 'train': 80 | if is_parallel(self.model): 81 | self.model.module.transforms = loader.dataset.torch_transforms 82 | else: 83 | self.model.transforms = loader.dataset.torch_transforms 84 | return loader 85 | 86 | def preprocess_batch(self, batch): 87 | batch['img'] = batch['img'].to(self.device) 88 | batch['cls'] = batch['cls'].to(self.device) 89 | return batch 90 | 91 | def progress_string(self): 92 | return ('\n' + '%11s' * (4 + len(self.loss_names))) % \ 93 | ('Epoch', 'GPU_mem', *self.loss_names, 'Instances', 'Size') 94 | 95 | def get_validator(self): 96 | self.loss_names = ['loss'] 97 | return v8.classify.ClassificationValidator(self.test_loader, self.save_dir) 98 | 99 | def criterion(self, preds, batch): 100 | loss = torch.nn.functional.cross_entropy(preds, batch['cls'], reduction='sum') / self.args.nbs 101 | loss_items = loss.detach() 102 | return loss, loss_items 103 | 104 | # def label_loss_items(self, loss_items=None, prefix="train"): 105 | # """ 106 | # Returns a loss dict with labelled training loss items tensor 107 | # """ 108 | # # Not needed for classification but necessary for segmentation & detection 109 | # keys = [f"{prefix}/{x}" for x in self.loss_names] 110 | # if loss_items is not None: 111 | # loss_items = [round(float(x), 5) for x in loss_items] # convert tensors to 5 decimal place floats 112 | # return dict(zip(keys, loss_items)) 113 | # else: 114 | # return keys 115 | 116 | def label_loss_items(self, loss_items=None, prefix='train'): 117 | """ 118 | Returns a loss dict with labelled training loss items tensor 119 | """ 120 | # Not needed for classification but necessary for segmentation & detection 121 | keys = [f'{prefix}/{x}' for x in self.loss_names] 122 | if loss_items is None: 123 | return keys 124 | loss_items = [round(float(loss_items), 5)] 125 | return dict(zip(keys, loss_items)) 126 | 127 | def resume_training(self, ckpt): 128 | pass 129 | 130 | def final_eval(self): 131 | for f in self.last, self.best: 132 | if f.exists(): 133 | strip_optimizer(f) # strip optimizers 134 | # TODO: validate best.pt after training completes 135 | # if f is self.best: 136 | # LOGGER.info(f'\nValidating {f}...') 137 | # self.validator.args.save_json = True 138 | # self.metrics = self.validator(model=f) 139 | # self.metrics.pop('fitness', None) 140 | # self.run_callbacks('on_fit_epoch_end') 141 | LOGGER.info(f"Results saved to {colorstr('bold', self.save_dir)}") 142 | 143 | 144 | def train(cfg=DEFAULT_CFG, use_python=False): 145 | model = cfg.model or 'yolov8n-cls.pt' # or "resnet18" 146 | data = cfg.data or 'mnist160' # or yolo.ClassificationDataset("mnist") 147 | device = cfg.device if cfg.device is not None else '' 148 | 149 | args = dict(model=model, data=data, device=device) 150 | if use_python: 151 | from ultralytics import YOLO 152 | YOLO(model).train(**args) 153 | else: 154 | trainer = ClassificationTrainer(overrides=args) 155 | trainer.train() 156 | 157 | 158 | if __name__ == '__main__': 159 | train() 160 | -------------------------------------------------------------------------------- /ultralytics/yolo/v8/classify/val.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | from ultralytics.yolo.data import build_classification_dataloader 4 | from ultralytics.yolo.engine.validator import BaseValidator 5 | from ultralytics.yolo.utils import DEFAULT_CFG, LOGGER 6 | from ultralytics.yolo.utils.metrics import ClassifyMetrics 7 | 8 | 9 | class ClassificationValidator(BaseValidator): 10 | 11 | def __init__(self, dataloader=None, save_dir=None, pbar=None, args=None, _callbacks=None): 12 | super().__init__(dataloader, save_dir, pbar, args, _callbacks) 13 | self.args.task = 'classify' 14 | self.metrics = ClassifyMetrics() 15 | 16 | def get_desc(self): 17 | return ('%22s' + '%11s' * 2) % ('classes', 'top1_acc', 'top5_acc') 18 | 19 | def init_metrics(self, model): 20 | self.pred = [] 21 | self.targets = [] 22 | 23 | def preprocess(self, batch): 24 | batch['img'] = batch['img'].to(self.device, non_blocking=True) 25 | batch['img'] = batch['img'].half() if self.args.half else batch['img'].float() 26 | batch['cls'] = batch['cls'].to(self.device) 27 | return batch 28 | 29 | def update_metrics(self, preds, batch): 30 | n5 = min(len(self.model.names), 5) 31 | self.pred.append(preds.argsort(1, descending=True)[:, :n5]) 32 | self.targets.append(batch['cls']) 33 | 34 | def finalize_metrics(self, *args, **kwargs): 35 | self.metrics.speed = self.speed 36 | # self.metrics.confusion_matrix = self.confusion_matrix # TODO: classification ConfusionMatrix 37 | 38 | def get_stats(self): 39 | self.metrics.process(self.targets, self.pred) 40 | return self.metrics.results_dict 41 | 42 | def get_dataloader(self, dataset_path, batch_size): 43 | return build_classification_dataloader(path=dataset_path, 44 | imgsz=self.args.imgsz, 45 | batch_size=batch_size, 46 | augment=False, 47 | shuffle=False, 48 | workers=self.args.workers) 49 | 50 | def print_results(self): 51 | pf = '%22s' + '%11.3g' * len(self.metrics.keys) # print format 52 | LOGGER.info(pf % ('all', self.metrics.top1, self.metrics.top5)) 53 | 54 | 55 | def val(cfg=DEFAULT_CFG, use_python=False): 56 | model = cfg.model or 'yolov8n-cls.pt' # or "resnet18" 57 | data = cfg.data or 'mnist160' 58 | 59 | args = dict(model=model, data=data) 60 | if use_python: 61 | from ultralytics import YOLO 62 | YOLO(model).val(**args) 63 | else: 64 | validator = ClassificationValidator(args=args) 65 | validator(model=args['model']) 66 | 67 | 68 | if __name__ == '__main__': 69 | val() 70 | -------------------------------------------------------------------------------- /ultralytics/yolo/v8/detect/__init__.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | from .predict import DetectionPredictor, predict 4 | from .train import DetectionTrainer, train 5 | from .val import DetectionValidator, val 6 | 7 | __all__ = 'DetectionPredictor', 'predict', 'DetectionTrainer', 'train', 'DetectionValidator', 'val' 8 | -------------------------------------------------------------------------------- /ultralytics/yolo/v8/detect/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/v8/detect/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/v8/detect/__pycache__/predict.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/v8/detect/__pycache__/predict.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/v8/detect/__pycache__/train.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/v8/detect/__pycache__/train.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/v8/detect/__pycache__/val.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/v8/detect/__pycache__/val.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/v8/detect/predict.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | import torch 4 | 5 | from ultralytics.yolo.engine.predictor import BasePredictor 6 | from ultralytics.yolo.engine.results import Results 7 | from ultralytics.yolo.utils import DEFAULT_CFG, ROOT, ops 8 | 9 | 10 | class DetectionPredictor(BasePredictor): 11 | 12 | def preprocess(self, img): 13 | img = (img if isinstance(img, torch.Tensor) else torch.from_numpy(img)).to(self.model.device) 14 | img = img.half() if self.model.fp16 else img.float() # uint8 to fp16/32 15 | img /= 255 # 0 - 255 to 0.0 - 1.0 16 | return img 17 | 18 | def postprocess(self, preds, img, orig_imgs): 19 | preds = ops.non_max_suppression(preds, 20 | self.args.conf, 21 | self.args.iou, 22 | agnostic=self.args.agnostic_nms, 23 | max_det=self.args.max_det, 24 | classes=self.args.classes) 25 | 26 | results = [] 27 | for i, pred in enumerate(preds): 28 | orig_img = orig_imgs[i] if isinstance(orig_imgs, list) else orig_imgs 29 | if not isinstance(orig_imgs, torch.Tensor): 30 | pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape) 31 | path, _, _, _, _ = self.batch 32 | img_path = path[i] if isinstance(path, list) else path 33 | results.append(Results(orig_img=orig_img, path=img_path, names=self.model.names, boxes=pred)) 34 | return results 35 | 36 | 37 | def predict(cfg=DEFAULT_CFG, use_python=False): 38 | model = cfg.model or 'yolov8n.pt' 39 | source = cfg.source if cfg.source is not None else ROOT / 'assets' if (ROOT / 'assets').exists() \ 40 | else 'https://ultralytics.com/images/bus.jpg' 41 | 42 | args = dict(model=model, source=source) 43 | if use_python: 44 | from ultralytics import YOLO 45 | YOLO(model)(**args) 46 | else: 47 | predictor = DetectionPredictor(overrides=args) 48 | predictor.predict_cli() 49 | 50 | 51 | if __name__ == '__main__': 52 | predict() 53 | -------------------------------------------------------------------------------- /ultralytics/yolo/v8/pose/__init__.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | from .predict import PosePredictor, predict 4 | from .train import PoseTrainer, train 5 | from .val import PoseValidator, val 6 | 7 | __all__ = 'PoseTrainer', 'train', 'PoseValidator', 'val', 'PosePredictor', 'predict' 8 | -------------------------------------------------------------------------------- /ultralytics/yolo/v8/pose/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/v8/pose/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/v8/pose/__pycache__/predict.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/v8/pose/__pycache__/predict.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/v8/pose/__pycache__/train.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/v8/pose/__pycache__/train.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/v8/pose/__pycache__/val.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/v8/pose/__pycache__/val.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/v8/pose/predict.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | from ultralytics.yolo.engine.results import Results 4 | from ultralytics.yolo.utils import DEFAULT_CFG, ROOT, ops 5 | from ultralytics.yolo.v8.detect.predict import DetectionPredictor 6 | 7 | 8 | class PosePredictor(DetectionPredictor): 9 | 10 | def postprocess(self, preds, img, orig_img): 11 | preds = ops.non_max_suppression(preds, 12 | self.args.conf, 13 | self.args.iou, 14 | agnostic=self.args.agnostic_nms, 15 | max_det=self.args.max_det, 16 | classes=self.args.classes, 17 | nc=len(self.model.names)) 18 | 19 | results = [] 20 | for i, pred in enumerate(preds): 21 | orig_img = orig_img[i] if isinstance(orig_img, list) else orig_img 22 | shape = orig_img.shape 23 | pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], shape).round() 24 | pred_kpts = pred[:, 6:].view(len(pred), *self.model.kpt_shape) if len(pred) else pred[:, 6:] 25 | pred_kpts = ops.scale_coords(img.shape[2:], pred_kpts, shape) 26 | path, _, _, _, _ = self.batch 27 | img_path = path[i] if isinstance(path, list) else path 28 | results.append( 29 | Results(orig_img=orig_img, 30 | path=img_path, 31 | names=self.model.names, 32 | boxes=pred[:, :6], 33 | keypoints=pred_kpts)) 34 | return results 35 | 36 | 37 | def predict(cfg=DEFAULT_CFG, use_python=False): 38 | model = cfg.model or 'yolov8n-pose.pt' 39 | source = cfg.source if cfg.source is not None else ROOT / 'assets' if (ROOT / 'assets').exists() \ 40 | else 'https://ultralytics.com/images/bus.jpg' 41 | 42 | args = dict(model=model, source=source) 43 | if use_python: 44 | from ultralytics import YOLO 45 | YOLO(model)(**args) 46 | else: 47 | predictor = PosePredictor(overrides=args) 48 | predictor.predict_cli() 49 | 50 | 51 | if __name__ == '__main__': 52 | predict() 53 | -------------------------------------------------------------------------------- /ultralytics/yolo/v8/pose/train.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | from copy import copy 4 | 5 | import torch 6 | import torch.nn as nn 7 | 8 | from ultralytics.nn.tasks import PoseModel 9 | from ultralytics.yolo import v8 10 | from ultralytics.yolo.utils import DEFAULT_CFG 11 | from ultralytics.yolo.utils.loss import KeypointLoss 12 | from ultralytics.yolo.utils.metrics import OKS_SIGMA 13 | from ultralytics.yolo.utils.ops import xyxy2xywh 14 | from ultralytics.yolo.utils.plotting import plot_images, plot_results 15 | from ultralytics.yolo.utils.tal import make_anchors 16 | from ultralytics.yolo.utils.torch_utils import de_parallel 17 | from ultralytics.yolo.v8.detect.train import Loss 18 | 19 | 20 | # BaseTrainer python usage 21 | class PoseTrainer(v8.detect.DetectionTrainer): 22 | 23 | def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None): 24 | if overrides is None: 25 | overrides = {} 26 | overrides['task'] = 'pose' 27 | super().__init__(cfg, overrides, _callbacks) 28 | 29 | def get_model(self, cfg=None, weights=None, verbose=True): 30 | model = PoseModel(cfg, ch=3, nc=self.data['nc'], data_kpt_shape=self.data['kpt_shape'], verbose=verbose) 31 | if weights: 32 | model.load(weights) 33 | 34 | return model 35 | 36 | def set_model_attributes(self): 37 | super().set_model_attributes() 38 | self.model.kpt_shape = self.data['kpt_shape'] 39 | 40 | def get_validator(self): 41 | self.loss_names = 'box_loss', 'pose_loss', 'kobj_loss', 'cls_loss', 'dfl_loss' 42 | return v8.pose.PoseValidator(self.test_loader, save_dir=self.save_dir, args=copy(self.args)) 43 | 44 | def criterion(self, preds, batch): 45 | if not hasattr(self, 'compute_loss'): 46 | self.compute_loss = PoseLoss(de_parallel(self.model)) 47 | return self.compute_loss(preds, batch) 48 | 49 | def plot_training_samples(self, batch, ni): 50 | images = batch['img'] 51 | kpts = batch['keypoints'] 52 | cls = batch['cls'].squeeze(-1) 53 | bboxes = batch['bboxes'] 54 | paths = batch['im_file'] 55 | batch_idx = batch['batch_idx'] 56 | plot_images(images, 57 | batch_idx, 58 | cls, 59 | bboxes, 60 | kpts=kpts, 61 | paths=paths, 62 | fname=self.save_dir / f'train_batch{ni}.jpg') 63 | 64 | def plot_metrics(self): 65 | plot_results(file=self.csv, pose=True) # save results.png 66 | 67 | 68 | # Criterion class for computing training losses 69 | class PoseLoss(Loss): 70 | 71 | def __init__(self, model): # model must be de-paralleled 72 | super().__init__(model) 73 | self.kpt_shape = model.model[-1].kpt_shape 74 | self.bce_pose = nn.BCEWithLogitsLoss() 75 | is_pose = self.kpt_shape == [17, 3] 76 | nkpt = self.kpt_shape[0] # number of keypoints 77 | sigmas = torch.from_numpy(OKS_SIGMA).to(self.device) if is_pose else torch.ones(nkpt, device=self.device) / nkpt 78 | self.keypoint_loss = KeypointLoss(sigmas=sigmas) 79 | 80 | def __call__(self, preds, batch): 81 | loss = torch.zeros(5, device=self.device) # box, cls, dfl, kpt_location, kpt_visibility 82 | feats, pred_kpts = preds if isinstance(preds[0], list) else preds[1] 83 | pred_distri, pred_scores = torch.cat([xi.view(feats[0].shape[0], self.no, -1) for xi in feats], 2).split( 84 | (self.reg_max * 4, self.nc), 1) 85 | 86 | # b, grids, .. 87 | pred_scores = pred_scores.permute(0, 2, 1).contiguous() 88 | pred_distri = pred_distri.permute(0, 2, 1).contiguous() 89 | pred_kpts = pred_kpts.permute(0, 2, 1).contiguous() 90 | 91 | dtype = pred_scores.dtype 92 | imgsz = torch.tensor(feats[0].shape[2:], device=self.device, dtype=dtype) * self.stride[0] # image size (h,w) 93 | anchor_points, stride_tensor = make_anchors(feats, self.stride, 0.5) 94 | 95 | # targets 96 | batch_size = pred_scores.shape[0] 97 | batch_idx = batch['batch_idx'].view(-1, 1) 98 | targets = torch.cat((batch_idx, batch['cls'].view(-1, 1), batch['bboxes']), 1) 99 | targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]]) 100 | gt_labels, gt_bboxes = targets.split((1, 4), 2) # cls, xyxy 101 | mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0) 102 | 103 | # pboxes 104 | pred_bboxes = self.bbox_decode(anchor_points, pred_distri) # xyxy, (b, h*w, 4) 105 | pred_kpts = self.kpts_decode(anchor_points, pred_kpts.view(batch_size, -1, *self.kpt_shape)) # (b, h*w, 17, 3) 106 | 107 | _, target_bboxes, target_scores, fg_mask, target_gt_idx = self.assigner( 108 | pred_scores.detach().sigmoid(), (pred_bboxes.detach() * stride_tensor).type(gt_bboxes.dtype), 109 | anchor_points * stride_tensor, gt_labels, gt_bboxes, mask_gt) 110 | 111 | target_scores_sum = max(target_scores.sum(), 1) 112 | 113 | # cls loss 114 | # loss[1] = self.varifocal_loss(pred_scores, target_scores, target_labels) / target_scores_sum # VFL way 115 | loss[3] = self.bce(pred_scores, target_scores.to(dtype)).sum() / target_scores_sum # BCE 116 | 117 | # bbox loss 118 | if fg_mask.sum(): 119 | target_bboxes /= stride_tensor 120 | loss[0], loss[4] = self.bbox_loss(pred_distri, pred_bboxes, anchor_points, target_bboxes, target_scores, 121 | target_scores_sum, fg_mask) 122 | keypoints = batch['keypoints'].to(self.device).float().clone() 123 | keypoints[..., 0] *= imgsz[1] 124 | keypoints[..., 1] *= imgsz[0] 125 | for i in range(batch_size): 126 | if fg_mask[i].sum(): 127 | idx = target_gt_idx[i][fg_mask[i]] 128 | gt_kpt = keypoints[batch_idx.view(-1) == i][idx] # (n, 51) 129 | gt_kpt[..., 0] /= stride_tensor[fg_mask[i]] 130 | gt_kpt[..., 1] /= stride_tensor[fg_mask[i]] 131 | area = xyxy2xywh(target_bboxes[i][fg_mask[i]])[:, 2:].prod(1, keepdim=True) 132 | pred_kpt = pred_kpts[i][fg_mask[i]] 133 | kpt_mask = gt_kpt[..., 2] != 0 134 | loss[1] += self.keypoint_loss(pred_kpt, gt_kpt, kpt_mask, area) # pose loss 135 | # kpt_score loss 136 | if pred_kpt.shape[-1] == 3: 137 | loss[2] += self.bce_pose(pred_kpt[..., 2], kpt_mask.float()) # keypoint obj loss 138 | 139 | loss[0] *= self.hyp.box # box gain 140 | loss[1] *= self.hyp.pose / batch_size # pose gain 141 | loss[2] *= self.hyp.kobj / batch_size # kobj gain 142 | loss[3] *= self.hyp.cls # cls gain 143 | loss[4] *= self.hyp.dfl # dfl gain 144 | 145 | return loss.sum() * batch_size, loss.detach() # loss(box, cls, dfl) 146 | 147 | def kpts_decode(self, anchor_points, pred_kpts): 148 | y = pred_kpts.clone() 149 | y[..., :2] *= 2.0 150 | y[..., 0] += anchor_points[:, [0]] - 0.5 151 | y[..., 1] += anchor_points[:, [1]] - 0.5 152 | return y 153 | 154 | 155 | def train(cfg=DEFAULT_CFG, use_python=False): 156 | model = cfg.model or 'yolov8n-pose.yaml' 157 | data = cfg.data or 'coco8-pose.yaml' 158 | device = cfg.device if cfg.device is not None else '' 159 | 160 | args = dict(model=model, data=data, device=device) 161 | if use_python: 162 | from ultralytics import YOLO 163 | YOLO(model).train(**args) 164 | else: 165 | trainer = PoseTrainer(overrides=args) 166 | trainer.train() 167 | 168 | 169 | if __name__ == '__main__': 170 | train() 171 | -------------------------------------------------------------------------------- /ultralytics/yolo/v8/segment/__init__.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | from .predict import SegmentationPredictor, predict 4 | from .train import SegmentationTrainer, train 5 | from .val import SegmentationValidator, val 6 | 7 | __all__ = 'SegmentationPredictor', 'predict', 'SegmentationTrainer', 'train', 'SegmentationValidator', 'val' 8 | -------------------------------------------------------------------------------- /ultralytics/yolo/v8/segment/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/v8/segment/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/v8/segment/__pycache__/predict.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/v8/segment/__pycache__/predict.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/v8/segment/__pycache__/train.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/v8/segment/__pycache__/train.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/v8/segment/__pycache__/val.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/ultralytics/yolo/v8/segment/__pycache__/val.cpython-39.pyc -------------------------------------------------------------------------------- /ultralytics/yolo/v8/segment/predict.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | 3 | import torch 4 | 5 | from ultralytics.yolo.engine.results import Results 6 | from ultralytics.yolo.utils import DEFAULT_CFG, ROOT, ops 7 | from ultralytics.yolo.v8.detect.predict import DetectionPredictor 8 | 9 | 10 | class SegmentationPredictor(DetectionPredictor): 11 | 12 | def postprocess(self, preds, img, orig_imgs): 13 | # TODO: filter by classes 14 | p = ops.non_max_suppression(preds[0], 15 | self.args.conf, 16 | self.args.iou, 17 | agnostic=self.args.agnostic_nms, 18 | max_det=self.args.max_det, 19 | nc=len(self.model.names), 20 | classes=self.args.classes) 21 | results = [] 22 | proto = preds[1][-1] if len(preds[1]) == 3 else preds[1] # second output is len 3 if pt, but only 1 if exported 23 | for i, pred in enumerate(p): 24 | orig_img = orig_imgs[i] if isinstance(orig_imgs, list) else orig_imgs 25 | path, _, _, _, _ = self.batch 26 | img_path = path[i] if isinstance(path, list) else path 27 | if not len(pred): # save empty boxes 28 | results.append(Results(orig_img=orig_img, path=img_path, names=self.model.names, boxes=pred[:, :6])) 29 | continue 30 | if self.args.retina_masks: 31 | if not isinstance(orig_imgs, torch.Tensor): 32 | pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape) 33 | masks = ops.process_mask_native(proto[i], pred[:, 6:], pred[:, :4], orig_img.shape[:2]) # HWC 34 | else: 35 | masks = ops.process_mask(proto[i], pred[:, 6:], pred[:, :4], img.shape[2:], upsample=True) # HWC 36 | if not isinstance(orig_imgs, torch.Tensor): 37 | pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape) 38 | results.append( 39 | Results(orig_img=orig_img, path=img_path, names=self.model.names, boxes=pred[:, :6], masks=masks)) 40 | return results 41 | 42 | 43 | def predict(cfg=DEFAULT_CFG, use_python=False): 44 | model = cfg.model or 'yolov8n-seg.pt' 45 | source = cfg.source if cfg.source is not None else ROOT / 'assets' if (ROOT / 'assets').exists() \ 46 | else 'https://ultralytics.com/images/bus.jpg' 47 | 48 | args = dict(model=model, source=source) 49 | if use_python: 50 | from ultralytics import YOLO 51 | YOLO(model)(**args) 52 | else: 53 | predictor = SegmentationPredictor(overrides=args) 54 | predictor.predict_cli() 55 | 56 | 57 | if __name__ == '__main__': 58 | predict() 59 | -------------------------------------------------------------------------------- /ultralytics/yolo/v8/segment/train.py: -------------------------------------------------------------------------------- 1 | # Ultralytics YOLO 🚀, GPL-3.0 license 2 | from copy import copy 3 | 4 | import torch 5 | import torch.nn.functional as F 6 | 7 | from ultralytics.nn.tasks import SegmentationModel 8 | from ultralytics.yolo import v8 9 | from ultralytics.yolo.utils import DEFAULT_CFG, RANK 10 | from ultralytics.yolo.utils.ops import crop_mask, xyxy2xywh 11 | from ultralytics.yolo.utils.plotting import plot_images, plot_results 12 | from ultralytics.yolo.utils.tal import make_anchors 13 | from ultralytics.yolo.utils.torch_utils import de_parallel 14 | from ultralytics.yolo.v8.detect.train import Loss 15 | 16 | 17 | # BaseTrainer python usage 18 | class SegmentationTrainer(v8.detect.DetectionTrainer): 19 | 20 | def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None): 21 | if overrides is None: 22 | overrides = {} 23 | overrides['task'] = 'segment' 24 | super().__init__(cfg, overrides, _callbacks) 25 | 26 | def get_model(self, cfg=None, weights=None, verbose=True): 27 | model = SegmentationModel(cfg, ch=3, nc=self.data['nc'], verbose=verbose and RANK == -1) 28 | if weights: 29 | model.load(weights) 30 | 31 | return model 32 | 33 | def get_validator(self): 34 | self.loss_names = 'box_loss', 'seg_loss', 'cls_loss', 'dfl_loss' 35 | return v8.segment.SegmentationValidator(self.test_loader, save_dir=self.save_dir, args=copy(self.args)) 36 | 37 | def criterion(self, preds, batch): 38 | if not hasattr(self, 'compute_loss'): 39 | self.compute_loss = SegLoss(de_parallel(self.model), overlap=self.args.overlap_mask) 40 | return self.compute_loss(preds, batch) 41 | 42 | def plot_training_samples(self, batch, ni): 43 | images = batch['img'] 44 | masks = batch['masks'] 45 | cls = batch['cls'].squeeze(-1) 46 | bboxes = batch['bboxes'] 47 | paths = batch['im_file'] 48 | batch_idx = batch['batch_idx'] 49 | plot_images(images, batch_idx, cls, bboxes, masks, paths=paths, fname=self.save_dir / f'train_batch{ni}.jpg') 50 | 51 | def plot_metrics(self): 52 | plot_results(file=self.csv, segment=True) # save results.png 53 | 54 | 55 | # Criterion class for computing training losses 56 | class SegLoss(Loss): 57 | 58 | def __init__(self, model, overlap=True): # model must be de-paralleled 59 | super().__init__(model) 60 | self.nm = model.model[-1].nm # number of masks 61 | self.overlap = overlap 62 | 63 | def __call__(self, preds, batch): 64 | loss = torch.zeros(4, device=self.device) # box, cls, dfl 65 | feats, pred_masks, proto = preds if len(preds) == 3 else preds[1] 66 | batch_size, _, mask_h, mask_w = proto.shape # batch size, number of masks, mask height, mask width 67 | pred_distri, pred_scores = torch.cat([xi.view(feats[0].shape[0], self.no, -1) for xi in feats], 2).split( 68 | (self.reg_max * 4, self.nc), 1) 69 | 70 | # b, grids, .. 71 | pred_scores = pred_scores.permute(0, 2, 1).contiguous() 72 | pred_distri = pred_distri.permute(0, 2, 1).contiguous() 73 | pred_masks = pred_masks.permute(0, 2, 1).contiguous() 74 | 75 | dtype = pred_scores.dtype 76 | imgsz = torch.tensor(feats[0].shape[2:], device=self.device, dtype=dtype) * self.stride[0] # image size (h,w) 77 | anchor_points, stride_tensor = make_anchors(feats, self.stride, 0.5) 78 | 79 | # targets 80 | try: 81 | batch_idx = batch['batch_idx'].view(-1, 1) 82 | targets = torch.cat((batch_idx, batch['cls'].view(-1, 1), batch['bboxes']), 1) 83 | targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]]) 84 | gt_labels, gt_bboxes = targets.split((1, 4), 2) # cls, xyxy 85 | mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0) 86 | except RuntimeError as e: 87 | raise TypeError('ERROR ❌ segment dataset incorrectly formatted or not a segment dataset.\n' 88 | "This error can occur when incorrectly training a 'segment' model on a 'detect' dataset, " 89 | "i.e. 'yolo train model=yolov8n-seg.pt data=coco128.yaml'.\nVerify your dataset is a " 90 | "correctly formatted 'segment' dataset using 'data=coco128-seg.yaml' " 91 | 'as an example.\nSee https://docs.ultralytics.com/tasks/segment/ for help.') from e 92 | 93 | # pboxes 94 | pred_bboxes = self.bbox_decode(anchor_points, pred_distri) # xyxy, (b, h*w, 4) 95 | 96 | _, target_bboxes, target_scores, fg_mask, target_gt_idx = self.assigner( 97 | pred_scores.detach().sigmoid(), (pred_bboxes.detach() * stride_tensor).type(gt_bboxes.dtype), 98 | anchor_points * stride_tensor, gt_labels, gt_bboxes, mask_gt) 99 | 100 | target_scores_sum = max(target_scores.sum(), 1) 101 | 102 | # cls loss 103 | # loss[1] = self.varifocal_loss(pred_scores, target_scores, target_labels) / target_scores_sum # VFL way 104 | loss[2] = self.bce(pred_scores, target_scores.to(dtype)).sum() / target_scores_sum # BCE 105 | 106 | if fg_mask.sum(): 107 | # bbox loss 108 | loss[0], loss[3] = self.bbox_loss(pred_distri, pred_bboxes, anchor_points, target_bboxes / stride_tensor, 109 | target_scores, target_scores_sum, fg_mask) 110 | # masks loss 111 | masks = batch['masks'].to(self.device).float() 112 | if tuple(masks.shape[-2:]) != (mask_h, mask_w): # downsample 113 | masks = F.interpolate(masks[None], (mask_h, mask_w), mode='nearest')[0] 114 | 115 | for i in range(batch_size): 116 | if fg_mask[i].sum(): 117 | mask_idx = target_gt_idx[i][fg_mask[i]] 118 | if self.overlap: 119 | gt_mask = torch.where(masks[[i]] == (mask_idx + 1).view(-1, 1, 1), 1.0, 0.0) 120 | else: 121 | gt_mask = masks[batch_idx.view(-1) == i][mask_idx] 122 | xyxyn = target_bboxes[i][fg_mask[i]] / imgsz[[1, 0, 1, 0]] 123 | marea = xyxy2xywh(xyxyn)[:, 2:].prod(1) 124 | mxyxy = xyxyn * torch.tensor([mask_w, mask_h, mask_w, mask_h], device=self.device) 125 | loss[1] += self.single_mask_loss(gt_mask, pred_masks[i][fg_mask[i]], proto[i], mxyxy, marea) # seg 126 | 127 | # WARNING: lines below prevents Multi-GPU DDP 'unused gradient' PyTorch errors, do not remove 128 | else: 129 | loss[1] += (proto * 0).sum() + (pred_masks * 0).sum() # inf sums may lead to nan loss 130 | 131 | # WARNING: lines below prevent Multi-GPU DDP 'unused gradient' PyTorch errors, do not remove 132 | else: 133 | loss[1] += (proto * 0).sum() + (pred_masks * 0).sum() # inf sums may lead to nan loss 134 | 135 | loss[0] *= self.hyp.box # box gain 136 | loss[1] *= self.hyp.box / batch_size # seg gain 137 | loss[2] *= self.hyp.cls # cls gain 138 | loss[3] *= self.hyp.dfl # dfl gain 139 | 140 | return loss.sum() * batch_size, loss.detach() # loss(box, cls, dfl) 141 | 142 | def single_mask_loss(self, gt_mask, pred, proto, xyxy, area): 143 | # Mask loss for one image 144 | pred_mask = (pred @ proto.view(self.nm, -1)).view(-1, *proto.shape[1:]) # (n, 32) @ (32,80,80) -> (n,80,80) 145 | loss = F.binary_cross_entropy_with_logits(pred_mask, gt_mask, reduction='none') 146 | return (crop_mask(loss, xyxy).mean(dim=(1, 2)) / area).mean() 147 | 148 | 149 | def train(cfg=DEFAULT_CFG, use_python=False): 150 | model = cfg.model or 'yolov8n-seg.pt' 151 | data = cfg.data or 'coco128-seg.yaml' # or yolo.ClassificationDataset("mnist") 152 | device = cfg.device if cfg.device is not None else '' 153 | 154 | args = dict(model=model, data=data, device=device) 155 | if use_python: 156 | from ultralytics import YOLO 157 | YOLO(model).train(**args) 158 | else: 159 | trainer = SegmentationTrainer(overrides=args) 160 | trainer.train() 161 | 162 | 163 | if __name__ == '__main__': 164 | train() 165 | -------------------------------------------------------------------------------- /utils/__pycache__/capnums.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/utils/__pycache__/capnums.cpython-39.pyc -------------------------------------------------------------------------------- /utils/__pycache__/id_dialog.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/utils/__pycache__/id_dialog.cpython-39.pyc -------------------------------------------------------------------------------- /utils/__pycache__/id_win.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/utils/__pycache__/id_win.cpython-39.pyc -------------------------------------------------------------------------------- /utils/__pycache__/rtsp_dialog.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/utils/__pycache__/rtsp_dialog.cpython-39.pyc -------------------------------------------------------------------------------- /utils/__pycache__/rtsp_win.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/utils/__pycache__/rtsp_win.cpython-39.pyc -------------------------------------------------------------------------------- /utils/capnums.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | # @Author : CatfishW🚀 3 | # @Time : 2023/5/1 4 | import cv2 5 | 6 | 7 | class Camera: 8 | def __init__(self, cam_preset_num=5): 9 | self.cam_preset_num = cam_preset_num 10 | 11 | def get_cam_num(self): 12 | cnt = 0 13 | devices = [] 14 | for device in range(0, self.cam_preset_num): 15 | stream = cv2.VideoCapture(device, cv2.CAP_DSHOW) 16 | grabbed = stream.grab() 17 | stream.release() 18 | if not grabbed: 19 | continue 20 | else: 21 | cnt = cnt + 1 22 | devices.append(device) 23 | return cnt, devices 24 | 25 | 26 | if __name__ == '__main__': 27 | cam = Camera() 28 | cam_num, devices = cam.get_cam_num() 29 | print(cam_num, devices) 30 | -------------------------------------------------------------------------------- /utils/id_dialog.py: -------------------------------------------------------------------------------- 1 | 2 | # -*- coding: utf-8 -*- 3 | # @Author : CatfishW🚀 4 | # @Time : 2023/5/1 5 | from PySide6 import QtCore, QtGui, QtWidgets 6 | 7 | 8 | class id_form(object): 9 | def setupUi(self, Form): 10 | Form.setObjectName("Form") 11 | Form.resize(783, 40) 12 | Form.setMinimumSize(QtCore.QSize(0, 40)) 13 | Form.setMaximumSize(QtCore.QSize(16777215, 41)) 14 | icon = QtGui.QIcon() 15 | icon.addPixmap(QtGui.QPixmap(":/img/None.png"), QtGui.QIcon.Normal, QtGui.QIcon.Off) 16 | Form.setWindowIcon(icon) 17 | Form.setStyleSheet("#Form{background:rgba(120,120,120,255)}") 18 | self.horizontalLayout = QtWidgets.QHBoxLayout(Form) 19 | self.horizontalLayout.setContentsMargins(-1, 5, -1, 5) 20 | self.horizontalLayout.setObjectName("horizontalLayout") 21 | self.label = QtWidgets.QLabel(Form) 22 | self.label.setMinimumSize(QtCore.QSize(0, 30)) 23 | self.label.setMaximumSize(QtCore.QSize(16777215, 30)) 24 | self.label.setStyleSheet("QLabel{font-family: \"Microsoft YaHei\";\n" 25 | "font-size: 18px;\n" 26 | "font-weight: bold;\n" 27 | "color:white;}") 28 | self.label.setObjectName("label") 29 | self.horizontalLayout.addWidget(self.label) 30 | self.idEdit = QtWidgets.QLineEdit(Form) 31 | self.idEdit.setMinimumSize(QtCore.QSize(0, 31)) 32 | self.idEdit.setStyleSheet("background-color: rgb(207, 207, 207);") 33 | self.idEdit.setObjectName("rtspEdit") 34 | self.horizontalLayout.addWidget(self.idEdit) 35 | self.idButton = QtWidgets.QPushButton(Form) 36 | self.idButton.setStyleSheet("QPushButton{font-family: \"Microsoft YaHei\";\n" 37 | "font-size: 18px;\n" 38 | "font-weight: bold;\n" 39 | "color:white;\n" 40 | "text-align: center center;\n" 41 | "padding-left: 5px;\n" 42 | "padding-right: 5px;\n" 43 | "padding-top: 4px;\n" 44 | "padding-bottom: 4px;\n" 45 | "border-style: solid;\n" 46 | "border-width: 0px;\n" 47 | "border-color: rgba(255, 255, 255, 255);\n" 48 | "border-radius: 3px;\n" 49 | "background-color: rgba(255,255,255,30);}\n" 50 | "\n" 51 | "QPushButton:focus{outline: none;}\n" 52 | "\n" 53 | "QPushButton::pressed{font-family: \"Microsoft YaHei\";\n" 54 | " font-size: 16px;\n" 55 | " font-weight: bold;\n" 56 | " color:rgb(200,200,200);\n" 57 | " text-align: center center;\n" 58 | " padding-left: 5px;\n" 59 | " padding-right: 5px;\n" 60 | " padding-top: 4px;\n" 61 | " padding-bottom: 4px;\n" 62 | " border-style: solid;\n" 63 | " border-width: 0px;\n" 64 | " border-color: rgba(255, 255, 255, 255);\n" 65 | " border-radius: 3px;\n" 66 | " background-color: rgba(255,255,255,150);}\n" 67 | "\n" 68 | "QPushButton::hover {\n" 69 | "border-style: solid;\n" 70 | "border-width: 0px;\n" 71 | "border-radius: 0px;\n" 72 | "background-color: rgba(255,255,255,50);}") 73 | self.idButton.setObjectName("rtspButton") 74 | self.horizontalLayout.addWidget(self.idButton) 75 | 76 | self.retranslateUi(Form) 77 | QtCore.QMetaObject.connectSlotsByName(Form) 78 | 79 | def retranslateUi(self, Form): 80 | _translate = QtCore.QCoreApplication.translate 81 | Form.setWindowTitle(_translate("Form", "ID")) 82 | self.label.setText(_translate("Form", "id:")) 83 | self.idButton.setText(_translate("Form", "确定")) 84 | # import apprcc_rc 85 | -------------------------------------------------------------------------------- /utils/id_win.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | # @Author : CatfishW🚀 3 | # @Time : 2023/5/1 4 | import sys 5 | from PySide6.QtWidgets import QApplication, QWidget 6 | from utils.id_dialog import id_form 7 | 8 | 9 | class id_Window(QWidget, id_form): 10 | def __init__(self): 11 | super(id_Window, self).__init__() 12 | self.setupUi(self) 13 | 14 | 15 | if __name__ == '__main__': 16 | app = QApplication(sys.argv) 17 | window = id_Window() 18 | window.show() 19 | sys.exit(app.exec()) 20 | -------------------------------------------------------------------------------- /utils/rtsp_dialog.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | # @Author : CatfishW🚀 3 | # @Time : 2023/5/1 4 | from PySide6 import QtCore, QtGui, QtWidgets 5 | 6 | 7 | class Ui_Form(object): 8 | def setupUi(self, Form): 9 | Form.setObjectName("Form") 10 | Form.resize(783, 40) 11 | Form.setMinimumSize(QtCore.QSize(0, 40)) 12 | Form.setMaximumSize(QtCore.QSize(16777215, 41)) 13 | icon = QtGui.QIcon() 14 | icon.addPixmap(QtGui.QPixmap(":/img/None.png"), QtGui.QIcon.Normal, QtGui.QIcon.Off) 15 | Form.setWindowIcon(icon) 16 | Form.setStyleSheet("#Form{background:rgba(120,120,120,255)}") 17 | self.horizontalLayout = QtWidgets.QHBoxLayout(Form) 18 | self.horizontalLayout.setContentsMargins(-1, 5, -1, 5) 19 | self.horizontalLayout.setObjectName("horizontalLayout") 20 | self.label = QtWidgets.QLabel(Form) 21 | self.label.setMinimumSize(QtCore.QSize(0, 30)) 22 | self.label.setMaximumSize(QtCore.QSize(16777215, 30)) 23 | self.label.setStyleSheet("QLabel{font-family: \"Microsoft YaHei\";\n" 24 | "font-size: 18px;\n" 25 | "font-weight: bold;\n" 26 | "color:white;}") 27 | self.label.setObjectName("label") 28 | self.horizontalLayout.addWidget(self.label) 29 | self.rtspEdit = QtWidgets.QLineEdit(Form) 30 | self.rtspEdit.setMinimumSize(QtCore.QSize(0, 31)) 31 | self.rtspEdit.setStyleSheet("background-color: rgb(207, 207, 207);") 32 | self.rtspEdit.setObjectName("rtspEdit") 33 | self.horizontalLayout.addWidget(self.rtspEdit) 34 | self.rtspButton = QtWidgets.QPushButton(Form) 35 | self.rtspButton.setStyleSheet("QPushButton{font-family: \"Microsoft YaHei\";\n" 36 | "font-size: 18px;\n" 37 | "font-weight: bold;\n" 38 | "color:white;\n" 39 | "text-align: center center;\n" 40 | "padding-left: 5px;\n" 41 | "padding-right: 5px;\n" 42 | "padding-top: 4px;\n" 43 | "padding-bottom: 4px;\n" 44 | "border-style: solid;\n" 45 | "border-width: 0px;\n" 46 | "border-color: rgba(255, 255, 255, 255);\n" 47 | "border-radius: 3px;\n" 48 | "background-color: rgba(255,255,255,30);}\n" 49 | "\n" 50 | "QPushButton:focus{outline: none;}\n" 51 | "\n" 52 | "QPushButton::pressed{font-family: \"Microsoft YaHei\";\n" 53 | " font-size: 16px;\n" 54 | " font-weight: bold;\n" 55 | " color:rgb(200,200,200);\n" 56 | " text-align: center center;\n" 57 | " padding-left: 5px;\n" 58 | " padding-right: 5px;\n" 59 | " padding-top: 4px;\n" 60 | " padding-bottom: 4px;\n" 61 | " border-style: solid;\n" 62 | " border-width: 0px;\n" 63 | " border-color: rgba(255, 255, 255, 255);\n" 64 | " border-radius: 3px;\n" 65 | " background-color: rgba(255,255,255,150);}\n" 66 | "\n" 67 | "QPushButton::hover {\n" 68 | "border-style: solid;\n" 69 | "border-width: 0px;\n" 70 | "border-radius: 0px;\n" 71 | "background-color: rgba(255,255,255,50);}") 72 | self.rtspButton.setObjectName("rtspButton") 73 | self.horizontalLayout.addWidget(self.rtspButton) 74 | 75 | self.retranslateUi(Form) 76 | QtCore.QMetaObject.connectSlotsByName(Form) 77 | 78 | def retranslateUi(self, Form): 79 | _translate = QtCore.QCoreApplication.translate 80 | Form.setWindowTitle(_translate("Form", "RTSP")) 81 | self.label.setText(_translate("Form", "rtsp地址:")) 82 | self.rtspButton.setText(_translate("Form", "确定")) 83 | # import apprcc_rc 84 | -------------------------------------------------------------------------------- /utils/rtsp_win.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | # @Author : CatfishW🚀 3 | # @Time : 2023/5/1 4 | import sys 5 | from PySide6.QtWidgets import QApplication, QWidget 6 | from utils.rtsp_dialog import Ui_Form 7 | 8 | 9 | class Window(QWidget, Ui_Form): 10 | def __init__(self): 11 | super(Window, self).__init__() 12 | self.setupUi(self) 13 | 14 | 15 | if __name__ == '__main__': 16 | app = QApplication(sys.argv) 17 | window = Window() 18 | window.show() 19 | sys.exit(app.exec()) 20 | -------------------------------------------------------------------------------- /utils/video_transform.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | # @Author : CatfishW🚀 3 | # @Time : 2023/5/1 4 | #把视频转换为裁剪好的avi格式 5 | import cv2 6 | video = 'tests/test.mp4'#视频地址 7 | cap = cv2.VideoCapture(video) 8 | video_writer = cv2.VideoWriter('test_4_1.avi', cv2.VideoWriter_fourcc(*'XVID'), 30, (640, 480))#转换格式 9 | while cap.isOpened(): 10 | ret, frame = cap.read() 11 | if ret: 12 | frame = cv2.resize(frame, (640, 480)) 13 | video_writer.write(frame) 14 | if cv2.waitKey(1) & 0xFF == ord('q'): 15 | break 16 | else: 17 | video_writer.release() 18 | break -------------------------------------------------------------------------------- /weights/轻量级模型.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CatfishW/MOT/eb905fad73488077b470de84d7dcf6089d808ce3/weights/轻量级模型.pt --------------------------------------------------------------------------------