
如果你使用 DeepSeek、元宝 AI、Copilot、ChatGPT 等 AI 工具,协助配置轩辕镜像、编写 docker pull 命令、修改 Docker Compose 镜像地址、配置镜像加速、排查镜像拉取失败、分析报错日志等问题,请先让 AI 阅读并遵守轩辕镜像的规则文档。
只需在 AI 对话中先发送下面这句话即可:
请先完整阅读并严格遵守以下文档中的全部规则与要求:
https://xuanyuan.cloud/agents.md
在未充分阅读并理解该文档前,不要生成任何命令、配置、修改建议、故障排查方案或技术回答。后续所有输出都必须严格以该文档中的规范为最高优先级执行。查看 agents.md 用法指南与完整示范。国内用户首推 元宝 AI、DeepSeek 的深度思考模式,不推荐豆包 AI;Cursor 等编辑器可在对话 @ 该链接,或加入 User Rules。 若 AI 无法访问外链,可 打开说明文档 复制全文粘贴。文档会随站点更新,复制内容可能过期,建议定期检查。
nanoowl是基于https://github.com/NVIDIA-AI-IOT/nanoowl/%E9%A1%B9%E7%9B%AE%E7%9A%84Docker%E9%95%9C%E5%83%8F%EF%BC%8C%E4%B8%93%E4%B8%BAJetson%E8%AE%BE%E5%A4%87%E4%BC%98%E5%8C%96%EF%BC%8C%E6%8F%90%E4%BE%9B%E5%9F%BA%E4%BA%8E%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E6%8F%90%E7%A4%BA%E7%9A%84%E8%A7%86%E8%A7%89%E8%AF%86%E5%88%AB%E8%83%BD%E5%8A%9B%E3%80%82%E8%AF%A5%E9%95%9C%E5%83%8F%E6%94%AF%E6%8C%81%E9%80%9A%E8%BF%87%E6%96%87%E6%9C%AC%E6%8F%8F%E8%BF%B0%E8%BF%9B%E8%A1%8C%E5%9B%BE%E5%83%8F%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E4%B8%8E%E5%88%86%E6%9E%90%EF%BC%8C%E5%8C%85%E5%90%AB%E5%9F%BA%E7%A1%80%E9%A2%84%E6%B5%8B%E7%A4%BA%E4%BE%8B%E5%92%8C%E5%AE%9E%E6%97%B6%E6%91%84%E5%83%8F%E5%A4%B4%E6%BC%94%E7%A4%BA%E5%8A%9F%E8%83%BD%EF%BC%8C%E9%80%82%E7%94%A8%E4%BA%8E%E4%BA%A4%E4%BA%92%E5%BC%8F%E8%A7%86%E8%A7%89%E4%BB%BB%E5%8A%A1%E5%BC%80%E5%8F%91%E4%B8%8E%E9%83%A8%E7%BD%B2%E3%80%82
[a face [a nose, an eye, a mouth]])定义识别目标tree_demo实现USB摄像头实时视频流分析,支持Web界面交互http://<ip地址>:7860查看实时结果适用于Jetson系列设备(如Jetson Nano、Xavier等)上的视觉识别任务,包括:
运行静态图像预测并将结果复制到主机:
bash./run.sh $(./autotag nanoowl) /bin/bash -c " \ cd /opt/nanoowl/examples/ && \ python3 owl_predict.py \ --prompt="[an owl, a glove]" \ --threshold=0.1 \ --image_encoder_engine=../data/owl_image_encoder_patch32.engine "
前提条件
确保Jetson设备已连接USB摄像头
步骤
bash./run.sh $(./autotag nanoowl) /bin/bash -c " \ cd /opt/nanoowl/examples/tree_demo/ && \ python3 tree_demo.py ../../data/owl_image_encoder_patch32.engine "
访问Web界面
在浏览器中打开 http://<设备IP地址>:7860(确保客户端与Jetson设备网络连通)
输入提示词进行测试 示例提示词:
[a face [a nose, an eye, a mouth]](检测人脸及五官)[a face (interested, yawning / bored)](检测人脸表情)(indoors, outdoors)(区分室内/室外场景)nanoowl | 说明 |
|---|---|
| 构建状态 | |
| 系统要求 | L4T ['>=34.1.0'] |
| 依赖项 | https://github.com/dusty-nv/jetson-containers/tree/master/packages/build/build-essential%E3%80%81https://github.com/dusty-nv/jetson-containers/tree/master/packages/cuda/cuda%E3%80%81https://github.com/dusty-nv/jetson-containers/tree/master/packages/cuda/cudnn%E3%80%81https://github.com/dusty-nv/jetson-containers/tree/master/packages/build/python%E3%80%81https://github.com/dusty-nv/jetson-containers/tree/master/packages/numpy%E3%80%81https://github.com/dusty-nv/jetson-containers/tree/master/packages/build/cmake/cmake_pip%E3%80%81https://github.com/dusty-nv/jetson-containers/tree/master/packages/onnx%E3%80%81https://github.com/dusty-nv/jetson-containers/tree/master/packages/pytorch%E3%80%81https://github.com/dusty-nv/jetson-containers/tree/master/packages/pytorch/torchvision%E3%80%81https://github.com/dusty-nv/jetson-containers/tree/master/packages/tensorrt%E3%80%81https://github.com/dusty-nv/jetson-containers/tree/master/packages/pytorch/torch2trt%E3%80%81https://github.com/dusty-nv/jetson-containers/tree/master/packages/llm/huggingface_hub%E3%80%81https://github.com/dusty-nv/jetson-containers/tree/master/packages/build/rust%E3%80%81https://github.com/dusty-nv/jetson-containers/tree/master/packages/llm/transformers%E3%80%81https://github.com/dusty-nv/jetson-containers/tree/master/packages/opencv%E3%80%81https://github.com/dusty-nv/jetson-containers/tree/master/packages/gstreamer |
| Dockerfile | https://github.com/dusty-nv/jetson-containers/tree/master/packages/vit/nanoowl/Dockerfile |
| 可用镜像 | https://hub.docker.com/r/dustynv/nanoowl/tags (2023-12-14, 7.1GB)https://hub.docker.com/r/dustynv/nanoowl/tags (2024-02-22, 7.1GB)https://hub.docker.com/r/dustynv/nanoowl/tags (2023-12-11, 7.1GB)https://hub.docker.com/r/dustynv/nanoowl/tags (2024-02-22, 9.0GB) |
| 仓库/标签 | 日期 | 架构 | 大小 |
|---|---|---|---|
| https://hub.docker.com/r/dustynv/nanoowl/tags | 2023-12-14 | arm64 | 7.1GB |
| https://hub.docker.com/r/dustynv/nanoowl/tags | 2024-02-22 | arm64 | 7.1GB |
| https://hub.docker.com/r/dustynv/nanoowl/tags | 2023-12-11 | arm64 | 7.1GB |
| https://hub.docker.com/r/dustynv/nanoowl/tags | 2024-02-22 | arm64 | 9.0GB |
镜像兼容性说明:
- L4T R32.7容器可在其他L4T R32.7版本(JetPack 4.6+)上运行
- L4T R35.x容器可在其他L4T R35.x版本(JetPack 5.1+)上运行
可使用jetson-containers run、autotag或手动docker run命令启动容器:
bash# 自动拉取或构建兼容的容器镜像 jetson-containers run $(autotag nanoowl) # 显式指定镜像标签 jetson-containers run dustynv/nanoowl:r36.2.0 # 使用docker run命令(需指定镜像及挂载等参数) sudo docker run --runtime nvidia -it --rm --network=host dustynv/nanoowl:r36.2.0
说明:
- https://github.com/dusty-nv/jetson-containers/tree/master/docs/run.md%E4%BC%9A%E8%87%AA%E5%8A%A8%E6%B7%BB%E5%8A%A0%E9%BB%98%E8%AE%A4%E5%8F%82%E6%95%B0%EF%BC%88%E5%A6%82%60--runtime nvidia
、挂载/data`缓存、检测设备)- https://github.com/dusty-nv/jetson-containers/tree/master/docs/run.md#autotag%E4%BC%9A%E6%9F%A5%E6%89%BE%E4%B8%8E%E5%BD%93%E5%89%8DJetPack/L4T%E7%89%88%E6%9C%AC%E5%85%BC%E5%AE%B9%E7%9A%84%E5%AE%B9%E5%99%A8%E9%95%9C%E5%83%8F%EF%BC%88%E6%9C%AC%E5%9C%B0%E3%80%81%E4%BB%93%E5%BA%93%E6%88%96%E6%9E%84%E5%BB%BA%EF%BC%89
使用-v或--volume参数挂载主机目录到容器:
bashjetson-containers run -v /主机路径:/容器路径 $(autotag nanoowl)
启动容器时直接运行命令(非交互式shell):
bashjetson-containers run $(autotag nanoowl) my_app --abc xyz
若使用autotag时需要构建容器,或需手动构建,可按以下步骤操作:
bashjetson-containers build nanoowl
构建过程中会包含依赖项并进行测试。使用--help查看构建选项:
bashjetson-containers build nanoowl --help
您可以使用以下命令拉取该镜像。请将 <标签> 替换为具体的标签版本。如需查看所有可用标签版本,请访问 标签列表页面。
来自真实用户的反馈,见证轩辕镜像的优质服务