概览
主要功能
- 单次实时目标检测
- 边界框和类别概率预测
- 同时支持检测、分割和姿态估计任务
- 预训练模型在 COCO 等常用数据集上
- 可部署在 GPU、CPU 和边缘设备上
- 根据用户自定义数据进行可定制训练
价格
- 模型
- Freemium
- 评分
- 4.8 / 5 (6)
使用场景
实时视频监控
在实时监控摄像头视频流中使用 YOLO 的快速单次推理检测和跟踪人员、车辆或感兴趣的对象。
自主车辆感知
通过 YOLO 的实时识别识别行人、车辆、交通标志和障碍以在无人驾驶系统中支持驾驶和导航决策。
机器人和边缘部署
在嵌入式硬件和机器人上运行对象检测，从而在不依赖于云的情况下使响应性与环境的交互成为可能。
自定义数据集检测训练
在工业、医疗和零售应用中检测域特定对象的预训练 YOLO 模型进行定制训练。
优点 & 缺点
优点
- 适合实时应用的极速推理
- 强大的开源生态系统和社区支持
- 单次检测多个物体类别
- 支持边缘硬件和嵌入式设备
- 模型版本中持续改进
- 不依赖于云端
缺点
- 小或密集的目标检测可能存在困难
- 需要标记的数据集和训练专家
- 不同版本及分支下的许可变异
- 可能比两阶段检测器慢
评测
6 个评分的平均值。
登录以留下评测。
Does the job
Pretty happy overall. Support for detection, segmentation, and pose tasks just works and runs on edge hardware and embedded devices. Requires labeled datasets and training expertise can be annoying, but no dealbreakers — I'd recommend it to a friend without hesitating.
Solid for our team
We rolled this out across the team last quarter and continual improvements across model versions. Pretrained models on common datasets like COCO fits neatly into how we already work, and deployable on GPU, CPU, and edge devices removed a step we used to do by hand. but it has held up under daily use.
Use it every day
Honestly didn't expect to like it this much. Support for detection, segmentation, and pose tasks is exactly what I needed, and strong open-source ecosystem and community support. I do wish requires labeled datasets and training expertise, but I reach for it almost every day now and it just clicks.
Use it every day
Honestly didn't expect to like it this much. Customizable training on user datasets is exactly what I needed, and continual improvements across model versions. I do wish can struggle with small or densely packed objects, but I reach for it almost every day now and it just clicks.
Years in this space
I've evaluated a lot of these over the years. What stands out here is pretrained models on common datasets like COCO — handled better than most — and extremely fast inference suitable for real-time use. Requires labeled datasets and training expertise is my one real gripe. Worth the time if this is your use case.
Compared a few options
Evaluated this against two competitors. Where it wins: customizable training on user datasets and extremely fast inference suitable for real-time use. Where it lags: requires labeled datasets and training expertise. On balance the feature set — especially customizable training on user datasets — justifies the 5 stars for our use case.
问答
暂无问题 — 来当第一个提问的人吧。
提问
Computer Vision 的替代品
PimEyes
Computer Vision
AI 面部搜索引擎，用于在网络上找到特定人的照片
Qate AI
Computer Vision
模拟用户行为的 GenAI 质量保证工具
Self-Parking Car Evolution
Computer Vision
基于遗传算法的演化学演示——让虚拟汽车在浏览器中自己学习停车。
Roboco AI
Computer Vision
未知工会 AI器作外会类合端会方法代球学本会带家设器招跹纷
Mapless AI
Computer Vision
无线远程汽车操作平台,安全、高效的无人驾驶车队管理
Pykaso
Computer Vision
通过自定义LoRA模型训练实现超真实的AI图像和视频生成
ExpertDevTech
Computer Vision
定制软件、AI 与数字解决方案，助力业务增长。
Retouch4me
Computer Vision
通过自动化皮肤、颜色和细节工作，保留自然纹理的 AI 退描插件
