YOLO11旋转目标识别（OBB）手把手教程: 如何训练自己的数据集（QR码为案列）

class_index, x1, y1, x2, y2, x3, y3, x4, y4

# 安装labelme
pip install labelme

labelme

path: D:/ultralytics-11/data/qrcode-obb/ 
train: train/images
val: valid/images
test: test/images

names: 
  0: qr_code

import warnings
warnings.filterwarnings('ignore')
from ultralytics import YOLO

if __name__ == '__main__':
    model = YOLO('ultralytics/cfg/models/11/yolo11-obb.yaml')
    #model.load('yolov11.pt') # loading pretrain weights
    model.train(data='data/qrcode-obb.yaml',
                cache=False,
                imgsz=640,
                epochs=200,
                batch=16,
                close_mosaic=10,
                device='0',
                optimizer='SGD', # using SGD
                project='runs/train',
                name='exp',
                )

YOLO11-obb summary (fused): 300 layers, 2,897,630 parameters, 0 gradients, 6.6 GFLOPs
                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 7/7 [00:04<00:00,  1.53it/s]
                   all         99        128      0.953      0.955      0.966      0.908