许可证: agpl-3.0 任务标签: 零样本目标检测 标签:

• 模型中心混合
• PyTorch模型中心混合

模型描述

YOLOE：实时视觉全能模型

• arXiv论文: https://arxiv.org/abs/2503.07465
• GitHub代码库: https://github.com/THU-MIG/yoloe

安装指南

pip install git+https://github.com/THU-MIG/yoloe.git#subdirectory=third_party/CLIP
pip install git+https://github.com/THU-MIG/yoloe.git#subdirectory=third_party/ml-mobileclip
pip install git+https://github.com/THU-MIG/yoloe.git#subdirectory=third_party/lvis-api
pip install git+https://github.com/THU-MIG/yoloe.git

wget https://docs-assets.developer.apple.com/ml-research/datasets/mobileclip/mobileclip_blt.pt

预测使用

详见 https://github.com/THU-MIG/yoloe?tab=readme-ov-file#prediction。

迁移学习

详见 https://github.com/THU-MIG/yoloe?tab=readme-ov-file#transferring。

验证评估

详见 https://github.com/THU-MIG/yoloe?tab=readme-ov-file#validation。

训练模型

详见 https://github.com/THU-MIG/yoloe?tab=readme-ov-file#training。

BibTeX引用信息

@misc{wang2025yoloerealtimeseeing,
      title={YOLOE：实时视觉全能模型}, 
      author={王傲 and 刘立浩 and 陈辉 and 林子佳 and 韩军功 and 丁贵广},
      year={2025},
      eprint={2503.07465},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2503.07465}, 
}