许可证：agpl-3.0
标签：

• 目标检测
• 计算机视觉
• yolov10
• pypi
  数据集：
• detection-datasets/coco

模型描述

YOLOv10：可训练的无额外代价方案为实时目标检测器树立新标杆

论文代码库：YOLOv10论文实现

安装方法

pip install supervision git+https://github.com/THU-MIG/yolov10.git  

YOLOv10推理示例

from ultralytics import YOLOv10  
import supervision as sv  
import cv2  

MODEL_PATH = 'yolov10n.pt'  
IMAGE_PATH = 'dog.jpeg'  

model = YOLOv10(MODEL_PATH)  
image = cv2.imread(IMAGE_PATH)  
results = model(source=image, conf=0.25, verbose=False)[0]  
detections = sv.Detections.from_ultralytics(results)  
box_annotator = sv.BoxAnnotator()  

category_dict = {  
    0: '人', 1: '自行车', 2: '汽车', 3: '摩托车', 4: '飞机', 5: '巴士',  
    6: '火车', 7: '卡车', 8: '船', 9: '交通灯', 10: '消防栓',  
    11: '停车标志', 12: '停车计时器', 13: '长椅', 14: '鸟', 15: '猫',  
    16: '狗', 17: '马', 18: '羊', 19: '牛', 20: '大象', 21: '熊',  
    22: '斑马', 23: '长颈鹿', 24: '背包', 25: '雨伞', 26: '手提包',  
    27: '领带', 28: '行李箱', 29: '飞盘', 30: '滑雪板', 31: '滑雪单板',  
    32: '运动球', 33: '风筝', 34: '棒球棒', 35: '棒球手套',  
    36: '滑板', 37: '冲浪板', 38: '网球拍', 39: '瓶子',  
    40: '红酒杯', 41: '杯子', 42: '叉子', 43: '刀', 44: '勺子', 45: '碗',  
    46: '香蕉', 47: '苹果', 48: '三明治', 49: '橙子', 50: '西兰花',  
    51: '胡萝卜', 52: '热狗', 53: '披萨', 54: '甜甜圈', 55: '蛋糕',  
    56: '椅子', 57: '沙发', 58: '盆栽', 59: '床', 60: '餐桌',  
    61: '马桶', 62: '电视', 63: '笔记本电脑', 64: '鼠标', 65: '遥控器', 66: '键盘',  
    67: '手机', 68: '微波炉', 69: '烤箱', 70: '烤面包机', 71: '水槽',  
    72: '冰箱', 73: '书', 74: '时钟', 75: '花瓶', 76: '剪刀',  
    77: '泰迪熊', 78: '吹风机', 79: '牙刷'  
}  

labels = [  
    f"{category_dict[class_id]} {confidence:.2f}"  
    for class_id, confidence in zip(detections.class_id, detections.confidence)  
]  
annotated_image = box_annotator.annotate(  
    image.copy(), detections=detections, labels=labels  
)  

cv2.imwrite('annotated_dog.jpeg', annotated_image)  

BibTeX条目及引用信息

@misc{wang2024yolov10,  
      title={YOLOv10：实时端到端目标检测},  
      author={王傲 and 陈辉 and 刘立浩 and 陈凯 and 林子佳 and 韩军功 and 丁贵广},  
      year={2024},  
      eprint={2405.14458},  
      archivePrefix={arXiv},  
      primaryClass={cs.CV}  
}