前言

• 由于本人水平有限，难免出现错漏，敬请批评改正。
• 更多精彩内容，可点击进入Python日常小操作专栏、OpenCV-Python小应用专栏、YOLO系列专栏、自然语言处理专栏或我的个人主页查看
• YOLOv8 Ultralytics：使用Ultralytics框架训练RT-DETR实时目标检测模型
• 基于DETR的人脸伪装检测
• YOLOv7训练自己的数据集（口罩检测）
• YOLOv8训练自己的数据集（足球检测）
• YOLOv5：TensorRT加速YOLOv5模型推理
• YOLOv5：IoU、GIoU、DIoU、CIoU、EIoU
• 玩转Jetson Nano（五）：TensorRT加速YOLOv5目标检测
• YOLOv5：添加SE、CBAM、CoordAtt、ECA注意力机制
• YOLOv5：yolov5s.yaml配置文件解读、增加小目标检测层
• Python将COCO格式实例分割数据集转换为YOLO格式实例分割数据集
• YOLOv5：使用7.0版本训练自己的实例分割模型（车辆、行人、路标、车道线等实例分割）
• 使用Kaggle GPU资源免费体验Stable Diffusion开源项目

前提条件

• 熟悉Python

相关介绍

• Python是一种跨平台的计算机程序设计语言。是一个高层次的结合了解释性、编译性、互动性和面向对象的脚本语言。最初被设计用于编写自动化脚本(shell)，随着版本的不断更新和语言新功能的添加，越多被用于独立的、大型项目的开发。
• PyTorch 是一个深度学习框架，封装好了很多网络和深度学习相关的工具方便我们调用，而不用我们一个个去单独写了。它分为 CPU 和 GPU 版本，其他框架还有 TensorFlow、Caffe 等。PyTorch 是由 Facebook 人工智能研究院（FAIR）基于 Torch 推出的，它是一个基于 Python 的可续计算包，提供两个高级功能：1、具有强大的 GPU 加速的张量计算（如 NumPy）；2、构建深度神经网络时的自动微分机制。
• YOLO是一种单阶段目标检测算法，它是一个在COCO数据集上预训练的物体检测架构和模型系列，代表了Ultralytics对未来视觉AI方法的开源研究，其中包含了经过数千小时的研究和开发而形成的经验教训和最佳实践。
• Labelme是一款图像标注工具，由麻省理工(MIT)的计算机科学和人工智能实验室(CSAIL)研发。它是用Python和PyQT编写的，开源且免费。Labelme支持Windows、Linux和Mac等操作系统。

COCO 格式简介（实例分割）

COCO 是一种常用的目标检测与实例分割数据集格式，支持图像、标注和类别信息。

---

📁 主要目录结构：

coco/
├── JPEGImages/        # 存放所有图像（JPG/PNG）
└── annotations.json   # COCO 格式的标注文件（JSON）

---

📄 JSON 标注文件结构示例：

{"images": [{"id": 1,"file_name": "001.jpg","width": 640,"height": 480}],"annotations": [{"id": 1,"image_id": 1,"category_id": 1,           # 类别 ID（对应 class_names）"segmentation": [[x1,y1,x2,y2,...]],  # 多边形坐标点"area": 1000,               # 区域面积"bbox": [x, y, w, h],       # 边界框"iscrowd": 0}],"categories": [{"id": 1,"name": "person"}]
}

---

✅ 特点：

• 支持多个对象、多边形标注
• 图像可为 JPG 或 PNG
• 常用于 Mask R-CNN、YOLOv8-seg 等模型训练

---

如需生成或转换数据集，可用脚本自动处理 YOLO 标注转 COCO。

实验环境

• Python 3.x （面向对象的高级语言）

Python将COCO格式分割标签绘制到对应的图片上

实例分割标签：

{"images": [{"id": 1,"file_name": "1.png","width": 579,"height": 484}],"annotations": [{"id": 1,"image_id": 1,"category_id": 3,"segmentation": [[329.30625,330.659604,329.30625,333.37339199999997,328.401273,334.277988,328.401273,335.18258399999996,327.49687500000005,336.087664,327.49687500000005,337.896856,326.592477,338.80145200000004,326.592477,339.706048,325.6875,340.611128,325.6875,342.42032,324.782523,343.32491600000003,324.782523,345.13459200000005,323.87812499999995,346.03918799999997,323.87812499999995,346.943784,322.06875,348.752976,322.06875,349.658056,321.16435199999995,350.562652,321.16435199999995,351.46724800000004,320.259375,352.371844,320.259375,353.27644,319.354398,354.181036,319.354398,355.086116,318.45000000000005,355.99071200000003,318.45000000000005,357.799904,317.545602,358.7045,317.545602,359.609096,315.735648,361.418772,315.735648,362.323368,313.926273,364.13256,313.926273,365.942236,312.11689800000005,367.751428,309.40312500000005,367.751428,309.40312500000005,428.365652,313.021875,428.365652,313.926273,429.270248,314.83124999999995,429.270248,315.735648,430.174844,316.640625,430.174844,317.545602,429.270248,318.45000000000005,429.270248,323.87812499999995,423.842188,379.96875,423.842188,380.873727,424.746784,394.44375,424.746784,395.348148,425.65138,403.490625,425.65138,404.395023,426.55645999999996,406.204398,426.55645999999996,407.109375,427.461056,408.014352,427.461056,408.91875000000005,428.365652,409.823148,428.365652,410.728125,429.270248,411.63310199999995,429.270248,412.5375,430.174844,418.870023,430.174844,419.775,429.270248,420.67939800000005,429.270248,422.488773,427.461056,422.488773,426.55645999999996,423.39374999999995,425.65138,423.39374999999995,424.746784,424.298148,423.842188,424.298148,422.937592,425.203125,422.032996,425.203125,421.12791599999997,426.108102,420.22332,426.108102,418.414128,427.01250000000005,417.50953200000004,427.01250000000005,414.79526,427.916898,413.89066399999996,427.916898,412.986068,428.821875,412.081472,428.821875,410.271796,429.72685199999995,409.3672,429.72685199999995,406.65292800000003,430.63125,405.748332,430.63125,393.08302,429.72685199999995,392.17794000000004,429.72685199999995,388.559556,428.821875,387.654476,428.821875,383.131012,427.916898,382.226416,427.916898,379.51262799999995,427.01250000000005,378.607548,427.01250000000005,376.798356,426.108102,375.89376,426.108102,374.084568,425.203125,373.17948800000005,425.203125,372.274892,424.298148,371.370296,424.298148,370.4657,423.39374999999995,369.561104,423.39374999999995,367.751428,421.584375,365.942236,421.584375,365.03764,419.775,363.227964,419.775,362.323368,418.870023,361.418772,418.870023,360.51417599999996,416.15625,357.799904,416.15625,356.895308,415.251273,355.99071200000003,415.251273,355.086116,413.441898,353.27644,413.441898,352.371844,410.728125,349.658056,410.728125,348.752976,408.91875000000005,346.943784,408.91875000000005,346.03918799999997,405.29999999999995,342.42032,405.29999999999995,341.515724,400.776273,336.99226,399.87187500000005,336.99226,398.0625,335.18258399999996,396.25312499999995,335.18258399999996,395.348148,334.277988,394.44375,334.277988,393.53935199999995,333.37339199999997,393.53935199999995,330.659604]],"area": 10106,"bbox": [309,330,121,99],"iscrowd": 0},{"id": 2,"image_id": 1,"category_id": 3,"segmentation": [[88.65937500000001,312.565748,88.65937500000001,316.184132,87.754398,317.08921200000003,86.85,317.08921200000003,84.135648,319.803,84.135648,320.70759599999997,83.23124999999999,321.612676,83.23124999999999,322.517272,82.326273,323.421868,82.326273,324.326464,81.421875,325.23106,81.421875,326.13613999999995,80.517477,327.040736,80.517477,328.849928,79.61250000000001,329.754524,79.61250000000001,330.659604,78.707523,331.5642,78.707523,333.37339199999997,77.803125,334.277988,77.803125,336.087664,76.898148,336.99226,76.898148,337.896856,75.99375,338.80145200000004,75.99375,340.611128,75.088773,341.515724,75.088773,344.229512,74.18437499999999,345.13459200000005,74.18437499999999,346.943784,73.279398,347.84837999999996,73.279398,348.752976,72.375,349.658056,72.375,351.46724800000004,71.470602,352.371844,71.470602,354.181036,69.660648,355.99071200000003,66.946875,355.99071200000003,66.946875,409.3672,69.660648,409.3672,72.375,412.081472,72.375,412.986068,80.517477,421.12791599999997,81.421875,421.12791599999997,87.754398,427.461056,88.65937500000001,427.461056,89.564352,428.365652,96.801273,428.365652,97.70625000000001,427.461056,98.611227,427.461056,101.32499999999999,424.746784,102.229398,424.746784,104.94375,422.032996,105.848148,422.032996,106.75312500000001,421.12791599999997,128.465625,421.12791599999997,129.370602,422.032996,138.417477,422.032996,139.321875,422.937592,149.273148,422.937592,150.17812500000002,423.842188,155.60625,423.842188,156.51122700000002,424.746784,163.74814800000001,424.746784,164.653125,425.65138,169.17627299999998,425.65138,170.08125,426.55645999999996,171.890625,426.55645999999996,172.79502300000001,427.461056,173.7,427.461056,174.60497700000002,428.365652,175.50937499999998,428.365652,176.414352,429.270248,177.31875000000002,429.270248,179.128125,431.079924,180.032523,431.079924,180.9375,431.98452000000003,181.84189800000001,431.98452000000003,182.746875,432.889116,183.65185200000002,432.889116,184.55624999999998,433.79371199999997,189.079398,433.79371199999997,190.88877300000001,431.98452000000003,190.88877300000001,431.079924,191.79375,430.174844,191.79375,429.270248,192.69872700000002,428.365652,192.69872700000002,427.461056,193.60312499999998,426.55645999999996,193.60312499999998,425.65138,194.508102,424.746784,194.508102,423.842188,195.41250000000002,422.937592,195.41250000000002,422.032996,196.31689799999998,421.12791599999997,196.31689799999998,420.22332,198.126273,418.414128,198.126273,417.50953200000004,201.74560200000002,413.89066399999996,202.64999999999998,413.89066399999996,204.45937500000002,412.081472,206.26875,412.081472,207.173148,411.176392,223.45752299999998,411.176392,224.3625,410.271796,225.266898,410.271796,227.07627300000001,408.462604,227.07627300000001,407.558008,227.98125,406.65292800000003,227.98125,401.22486799999996,228.88622700000002,400.320272,228.88622700000002,383.131012,227.98125,382.226416,227.98125,379.51262799999995,227.07627300000001,378.607548,227.07627300000001,376.798356,226.171875,375.89376,226.171875,374.989164,225.266898,374.084568,225.266898,373.17948800000005,224.3625,372.274892,224.3625,370.4657,223.45752299999998,369.561104,223.45752299999998,368.656024,222.55312500000002,367.751428,222.55312500000002,366.846832,221.648148,365.942236,221.648148,364.13256,220.74374999999998,363.227964,220.74374999999998,361.418772,219.83935200000002,360.51417599999996,219.83935200000002,358.7045,218.934375,357.799904,218.934375,355.99071200000003,218.02939800000001,355.086116,218.02939800000001,353.27644,216.220023,351.46724800000004,216.220023,350.562652,215.315625,349.658056,215.315625,348.752976,214.41064799999998,347.84837999999996,214.41064799999998,346.943784,213.50625000000002,346.03918799999997,213.50625000000002,345.13459200000005,211.69687499999998,343.32491600000003,211.69687499999998,342.42032,210.79247700000002,341.515724,210.79247700000002,339.706048,209.8875,338.80145200000004,209.8875,336.99226,208.98252300000001,336.087664,208.98252300000001,334.277988,208.078125,333.37339199999997,208.078125,331.5642,207.173148,330.659604,207.173148,329.754524,199.93564800000001,322.517272,199.03125,322.517272,198.126273,321.612676,196.31689799999998,321.612676,195.41250000000002,320.70759599999997,194.508102,320.70759599999997,193.60312499999998,319.803,191.79375,319.803,190.88877300000001,318.898404,188.175,318.898404,187.27002299999998,317.993808,184.55624999999998,317.993808,183.65185200000002,317.08921200000003,180.9375,317.08921200000003,180.032523,316.184132,179.128125,316.184132,178.22314799999998,315.279536,178.22314799999998,312.565748]],"area": 15941,"bbox": [66,312,161,121],"iscrowd": 0},{"id": 3,"image_id": 1,"category_id": 3,"segmentation": [[208.078125,330.659604,208.078125,340.611128,210.79247700000002,340.611128,213.50625000000002,343.32491600000003,213.50625000000002,344.229512,216.220023,346.943784,216.220023,347.84837999999996,218.02939800000001,349.658056,218.02939800000001,350.562652,218.934375,351.46724800000004,218.934375,352.371844,219.83935200000002,353.27644,219.83935200000002,355.086116,220.74374999999998,355.99071200000003,220.74374999999998,358.7045,221.648148,359.609096,221.648148,362.323368,222.55312500000002,363.227964,222.55312500000002,364.13256,223.45752299999998,365.03764,223.45752299999998,365.942236,224.3625,366.846832,224.3625,367.751428,225.266898,368.656024,225.266898,370.4657,226.171875,371.370296,226.171875,373.17948800000005,228.88622700000002,375.89376,228.88622700000002,376.798356,229.79062499999998,377.702952,230.695602,377.702952,231.60000000000002,378.607548,234.313773,378.607548,235.21875,379.51262799999995,239.741898,379.51262799999995,240.64687500000002,378.607548,242.45625,378.607548,243.360648,377.702952,244.265625,377.702952,247.88437499999998,374.084568,247.88437499999998,373.17948800000005,248.789352,372.274892,248.789352,371.370296,249.69375000000002,370.4657,249.69375000000002,367.751428,250.59814799999998,366.846832,250.59814799999998,365.03764,249.69375000000002,364.13256,249.69375000000002,357.799904,248.789352,356.895308,248.789352,351.46724800000004,247.88437499999998,350.562652,247.88437499999998,346.03918799999997,246.97997700000002,345.13459200000005,246.97997700000002,343.32491600000003,246.075,342.42032,246.075,340.611128,245.17002300000001,339.706048,245.17002300000001,338.80145200000004,244.265625,337.896856,244.265625,336.99226,243.360648,336.087664,242.45625,336.087664,240.64687500000002,334.277988,240.64687500000002,330.659604]],"area": 1377,"bbox": [208,330,42,48],"iscrowd": 0},{"id": 4,"image_id": 1,"category_id": 8,"segmentation": [[229.79062499999998,316.184132,229.79062499999998,331.5642,236.12314800000001,331.5642,237.028125,332.468796,237.93310200000002,332.468796,238.83749999999998,333.37339199999997,239.741898,333.37339199999997,241.55127299999998,335.18258399999996,242.45625,335.18258399999996,245.17002300000001,337.896856,245.17002300000001,338.80145200000004,246.075,339.706048,246.075,341.515724,246.97997700000002,342.42032,246.97997700000002,345.13459200000005,247.88437499999998,346.03918799999997,247.88437499999998,349.658056,248.789352,350.562652,248.789352,355.99071200000003,249.69375000000002,356.895308,249.69375000000002,360.51417599999996,250.59814799999998,361.418772,250.59814799999998,364.13256,254.21689800000001,367.751428,258.740625,367.751428,259.645602,366.846832,270.501273,366.846832,271.40625,367.751428,277.739352,367.751428,278.64375,368.656024,280.453125,368.656024,281.358102,369.561104,282.2625,369.561104,283.166898,370.4657,283.166898,373.17948800000005,283.166898,369.561104,284.071875,368.656024,284.071875,367.751428,284.976852,366.846832,284.976852,333.37339199999997,284.071875,332.468796,284.071875,329.754524,283.166898,328.849928,283.166898,327.040736,282.2625,326.13613999999995,282.2625,324.326464,281.358102,323.421868,281.358102,322.517272,280.453125,321.612676,280.453125,320.70759599999997,278.64375,318.898404,278.64375,316.184132]],"area": 2148,"bbox": [229,316,55,56],"iscrowd": 0},{"id": 5,"image_id": 1,"category_id": 3,"segmentation": [[310.307523,334.277988,310.307523,337.896856,308.498727,339.706048,308.498727,340.611128,306.688773,342.42032,306.688773,344.229512,304.879398,346.03918799999997,302.165625,346.03918799999997,302.165625,359.609096,305.78437499999995,359.609096,306.688773,360.51417599999996,310.307523,360.51417599999996,311.2125,361.418772,314.83124999999995,361.418772,315.735648,360.51417599999996,316.640625,360.51417599999996,317.545602,359.609096,317.545602,358.7045,318.45000000000005,357.799904,318.45000000000005,356.895308,319.354398,355.99071200000003,319.354398,355.086116,320.259375,354.181036,320.259375,352.371844,321.16435199999995,351.46724800000004,321.16435199999995,350.562652,322.06875,349.658056,322.06875,348.752976,322.973148,347.84837999999996,322.973148,346.943784,323.87812499999995,346.03918799999997,323.87812499999995,345.13459200000005,324.782523,344.229512,324.782523,343.32491600000003,325.6875,342.42032,325.6875,341.515724,327.49687500000005,339.706048,330.21064800000005,339.706048,330.21064800000005,334.277988]],"area": 488,"bbox": [302,334,28,27],"iscrowd": 0},{"id": 6,"image_id": 1,"category_id": 3,"segmentation": [[284.071875,330.659604,284.071875,351.46724800000004,293.11875,351.46724800000004,293.11875,348.752976,294.02314800000005,347.84837999999996,296.73749999999995,347.84837999999996,297.641898,346.943784,302.165625,346.943784,305.78437499999995,343.32491600000003,308.498727,343.32491600000003,308.498727,334.277988,305.78437499999995,334.277988,304.879398,333.37339199999997,304.879398,330.659604]],"area": 413,"bbox": [284,330,24,20],"iscrowd": 0}],"categories": [{"id": 1,"name": "person","supercategory": "none"},{"id": 2,"name": "bicycle","supercategory": "none"},{"id": 3,"name": "car","supercategory": "none"},{"id": 4,"name": "motorcycle","supercategory": "none"},{"id": 5,"name": "airplane","supercategory": "none"},{"id": 6,"name": "bus","supercategory": "none"},{"id": 7,"name": "train","supercategory": "none"},{"id": 8,"name": "truck","supercategory": "none"},{"id": 9,"name": "boat","supercategory": "none"},{"id": 10,"name": "traffic light","supercategory": "none"},{"id": 11,"name": "fire hydrant","supercategory": "none"},{"id": 12,"name": "stop sign","supercategory": "none"},{"id": 13,"name": "parking meter","supercategory": "none"},{"id": 14,"name": "bench","supercategory": "none"},{"id": 15,"name": "bird","supercategory": "none"},{"id": 16,"name": "cat","supercategory": "none"},{"id": 17,"name": "dog","supercategory": "none"},{"id": 18,"name": "horse","supercategory": "none"},{"id": 19,"name": "sheep","supercategory": "none"},{"id": 20,"name": "cow","supercategory": "none"},{"id": 21,"name": "elephant","supercategory": "none"},{"id": 22,"name": "bear","supercategory": "none"},{"id": 23,"name": "zebra","supercategory": "none"},{"id": 24,"name": "giraffe","supercategory": "none"},{"id": 25,"name": "backpack","supercategory": "none"},{"id": 26,"name": "umbrella","supercategory": "none"},{"id": 27,"name": "handbag","supercategory": "none"},{"id": 28,"name": "tie","supercategory": "none"},{"id": 29,"name": "suitcase","supercategory": "none"},{"id": 30,"name": "frisbee","supercategory": "none"},{"id": 31,"name": "skis","supercategory": "none"},{"id": 32,"name": "snowboard","supercategory": "none"},{"id": 33,"name": "sports ball","supercategory": "none"},{"id": 34,"name": "kite","supercategory": "none"},{"id": 35,"name": "baseball bat","supercategory": "none"},{"id": 36,"name": "baseball glove","supercategory": "none"},{"id": 37,"name": "skateboard","supercategory": "none"},{"id": 38,"name": "surfboard","supercategory": "none"},{"id": 39,"name": "tennis racket","supercategory": "none"},{"id": 40,"name": "bottle","supercategory": "none"},{"id": 41,"name": "wine glass","supercategory": "none"},{"id": 42,"name": "cup","supercategory": "none"},{"id": 43,"name": "fork","supercategory": "none"},{"id": 44,"name": "knife","supercategory": "none"},{"id": 45,"name": "spoon","supercategory": "none"},{"id": 46,"name": "bowl","supercategory": "none"},{"id": 47,"name": "banana","supercategory": "none"},{"id": 48,"name": "apple","supercategory": "none"},{"id": 49,"name": "sandwich","supercategory": "none"},{"id": 50,"name": "orange","supercategory": "none"},{"id": 51,"name": "broccoli","supercategory": "none"},{"id": 52,"name": "carrot","supercategory": "none"},{"id": 53,"name": "hot dog","supercategory": "none"},{"id": 54,"name": "pizza","supercategory": "none"},{"id": 55,"name": "donut","supercategory": "none"},{"id": 56,"name": "cake","supercategory": "none"},{"id": 57,"name": "chair","supercategory": "none"},{"id": 58,"name": "couch","supercategory": "none"},{"id": 59,"name": "potted plant","supercategory": "none"},{"id": 60,"name": "bed","supercategory": "none"},{"id": 61,"name": "dining table","supercategory": "none"},{"id": 62,"name": "toilet","supercategory": "none"},{"id": 63,"name": "tv","supercategory": "none"},{"id": 64,"name": "laptop","supercategory": "none"},{"id": 65,"name": "mouse","supercategory": "none"},{"id": 66,"name": "remote","supercategory": "none"},{"id": 67,"name": "keyboard","supercategory": "none"},{"id": 68,"name": "cell phone","supercategory": "none"},{"id": 69,"name": "microwave","supercategory": "none"},{"id": 70,"name": "oven","supercategory": "none"},{"id": 71,"name": "toaster","supercategory": "none"},{"id": 72,"name": "sink","supercategory": "none"},{"id": 73,"name": "refrigerator","supercategory": "none"},{"id": 74,"name": "book","supercategory": "none"},{"id": 75,"name": "clock","supercategory": "none"},{"id": 76,"name": "vase","supercategory": "none"},{"id": 77,"name": "scissors","supercategory": "none"},{"id": 78,"name": "teddy bear","supercategory": "none"},{"id": 79,"name": "hair drier","supercategory": "none"},{"id": 80,"name": "toothbrush","supercategory": "none"}]
}

代码实现

import cv2
import numpy as np
from pycocotools.coco import COCO
import os
import random
import argparse# 颜色生成器：为每个类别生成一个随机颜色
def get_color_map(num_classes):color_map = {}for i in range(num_classes):color = (random.randint(0, 255), random.randint(0, 255), random.randint(0, 255))color_map[i] = colorreturn color_mapdef draw_coco_segmentations(annotation_file, image_dir, output_dir, draw_bbox=False, draw_id=False,  alpha=0.5):# 创建输出文件夹if not os.path.exists(output_dir):os.makedirs(output_dir)# 加载 COCO 数据集coco = COCO(annotation_file)cat_ids = coco.getCatIds()color_map = get_color_map(len(cat_ids) + 10)  # 多留几个备用颜色# 获取所有图片 IDimg_ids = coco.getImgIds()for img_id in img_ids:# 获取图片信息img_info = coco.loadImgs(img_id)[0]img_path = os.path.join(image_dir, img_info['file_name'])if not os.path.exists(img_path):print(f"⚠️ 图片不存在: {img_path}")continuetry:# 读取图像img = cv2.imread(img_path)overlay = img.copy()except Exception as e:print(f"❌ 无法读取图片 {img_path}: {e}")continue# 获取该图的所有注解ann_ids = coco.getAnnIds(imgIds=img_info['id'])anns = coco.loadAnns(ann_ids)for ann in anns:# 获取类别颜色和 IDcategory_id = ann['category_id']instance_id = ann['id']  # 实例 ID，也可以使用 category_id 表示类别 IDcolor = color_map[category_id]# 绘制多边形分割区域for seg in ann['segmentation']:poly = np.array(seg).reshape((int(len(seg)/2), 2)).astype(np.int32)cv2.fillPoly(overlay, [poly], color=color)# 可选：绘制边界框if draw_bbox and 'bbox' in ann:x, y, w, h = map(int, ann['bbox'])cv2.rectangle(overlay, (x, y), (x + w, y + h), color=(0, 255, 255), thickness=2)# 可选：绘制 ID 文字if draw_id:# 获取文字起始位置（取第一个点）text_position = tuple(poly[0])text_position = (text_position[0] - 5, text_position[1] - 5)  # 稍微偏移一下text = str(category_id)  # 你可以改为 instance_id# 设置字体和大小font = cv2.FONT_HERSHEY_SIMPLEXfont_scale = 0.5thickness = 1text_color = (255, 255, 255)  # 白色文字bg_color = (0, 0, 0)  # 黑色背景# 获取文字大小并绘制带背景的文字(text_width, text_height), _ = cv2.getTextSize(text, font, font_scale, thickness)cv2.rectangle(overlay, text_position, (text_position[0] + text_width + 2, text_position[1] - text_height - 2),bg_color, -1)cv2.putText(overlay, text, text_position, font, font_scale, text_color, thickness)# 合并原图与覆盖层result = cv2.addWeighted(overlay, alpha, img, 1 - alpha, 0)# 保存结果out_path = os.path.join(output_dir, img_info['file_name'])cv2.imwrite(out_path, result)print(f"✅ 已处理并保存: {out_path}")print("🎉 全部图片标注完成！")if __name__ == '__main__':parser = argparse.ArgumentParser(description="批量绘制 COCO 分割标签到图像上")parser.add_argument('--annotation_file', type=str, required=False, default=r'annotations.json',help='COCO JSON 注解文件路径')parser.add_argument('--image_dir', type=str, required=False, default=r'JPEGImages',help='原始图片所在目录')parser.add_argument('--output_dir', type=str, required=False, default=r'draw',help='标注后图像输出目录')parser.add_argument('--draw_bbox', type=str, choices=['True', 'False'], required=False, default='False',help='是否同时绘制边界框(True/False)')parser.add_argument('--draw_id', type=str, choices=['True', 'False'], required=False, default='False',help='是否绘制类别ID(True/False)')parser.add_argument('--alpha', type=float, default=0.5,help='分割区域的透明度（0~1）')args = parser.parse_args()# 将'draw_bbox'参数从字符串转换为布尔值args.draw_bbox = args.draw_bbox == 'True'args.draw_id = args.draw_id == 'True'draw_coco_segmentations(annotation_file=args.annotation_file,image_dir=args.image_dir,output_dir=args.output_dir,draw_bbox=args.draw_bbox,draw_id=args.draw_id,alpha=args.alpha)

输出结果

• 由于本人水平有限，难免出现错漏，敬请批评改正。
• 更多精彩内容，可点击进入Python日常小操作专栏、OpenCV-Python小应用专栏、YOLO系列专栏、自然语言处理专栏或我的个人主页查看
• YOLOv8 Ultralytics：使用Ultralytics框架训练RT-DETR实时目标检测模型
• 基于DETR的人脸伪装检测
• YOLOv7训练自己的数据集（口罩检测）
• YOLOv8训练自己的数据集（足球检测）
• YOLOv5：TensorRT加速YOLOv5模型推理
• YOLOv5：IoU、GIoU、DIoU、CIoU、EIoU
• 玩转Jetson Nano（五）：TensorRT加速YOLOv5目标检测
• YOLOv5：添加SE、CBAM、CoordAtt、ECA注意力机制
• YOLOv5：yolov5s.yaml配置文件解读、增加小目标检测层
• Python将COCO格式实例分割数据集转换为YOLO格式实例分割数据集
• YOLOv5：使用7.0版本训练自己的实例分割模型（车辆、行人、路标、车道线等实例分割）
• 使用Kaggle GPU资源免费体验Stable Diffusion开源项目