
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。
jupyterlab镜像是用于在Jetson设备上快速部署JupyterLab开发环境的Docker镜像。容器启动时默认自动在后台启动JupyterLab服务器,无需手动配置,适用于需要在Jetson平台进行交互式开发、数据分析或AI模型调试的场景。
/start_jupyter脚本,自动在8888端口启动JupyterLab服务器JUPYTER_ROOT)、端口(JUPYTER_PORT)、登录密码(JUPYTER_PASSWORD)和日志路径(JUPYTER_LOG)/start_jupyter启动服务build-essential、python等基础包,作为多个AI/ML相关镜像(如audiocraft、llama-index)的基础依赖使用jetson-containers run工具自动拉取或构建兼容镜像并启动:
bash# 自动选择与当前JetPack/L4T兼容的镜像 jetson-containers run $(autotag jupyterlab) # 或指定具体镜像版本 jetson-containers run dustynv/jupyterlab:r35.3.1 # 直接使用docker run命令(需手动配置nvidia运行时和网络) sudo docker run --runtime nvidia -it --rm --network=host dustynv/jupyterlab:r35.3.1
默认配置下:
/data/logs/jupyter.log(自动映射到宿主机jetson-containers/data目录)通过--env参数设置环境变量自定义JupyterLab行为:
| 环境变量 | 说明 | 默认值 |
|---|---|---|
JUPYTER_ROOT | JupyterLab根目录 | 容器默认工作目录 |
JUPYTER_PORT | 服务器监听端口 | 8888 |
JUPYTER_PASSWORD | 登录密码 | nvidia |
JUPYTER_LOG | 日志文件路径 | /data/logs/jupyter.log |
配置示例:
bashjetson-containers run \ --env JUPYTER_ROOT=/home/user \ # 设置根目录为/home/user --env JUPYTER_PORT=8000 \ # 端口改为8000 --env JUPYTER_PASSWORD=password \ # 密码设为password --env JUPYTER_LOG=/dev/null \ # 禁用日志输出 $(autotag jupyterlab)
默认CMD为启动JupyterLab,可直接指定命令进入终端:
bash# 直接进入容器终端,不启动JupyterLab jetson-containers run /bin/bash
进入终端后,可手动启动JupyterLab服务:
bash/start_jupyter # 执行启动脚本
| jupyterlab | 详情 |
|---|---|
| 构建状态 | https://img.shields.io/github/actions/workflow/status/dusty-nv/jetson-containers/jupyterlab_jp46.yml?label=jupyterlab:jp46](https://github.com/dusty-nv/jetson-containers/actions/workflows/jupyterlab_jp46.yml) https://img.shields.io/github/actions/workflow/status/dusty-nv/jetson-containers/jupyterlab_jp51.yml?label=jupyterlab:jp51](https://github.com/dusty-nv/jetson-containers/actions/workflows/jupyterlab_jp51.yml) https://img.shields.io/github/actions/workflow/status/dusty-nv/jetson-containers/jupyterlab_jp60.yml?label=jupyterlab:jp60](https://github.com/dusty-nv/jetson-containers/actions/workflows/jupyterlab_jp60.yml) |
| 系统要求 | L4T ['>=32.6'] |
| 依赖项 | https://github.com/dusty-nv/jetson-containers/tree/master/packages/build/build-essential https://github.com/dusty-nv/jetson-containers/tree/master/packages/build/python https://github.com/dusty-nv/jetson-containers/tree/master/packages/numpy https://github.com/dusty-nv/jetson-containers/tree/master/packages/build/rust |
| 被依赖项 | https://github.com/dusty-nv/jetson-containers/tree/master/packages/audio/audiocraft https://github.com/dusty-nv/jetson-containers/tree/master/packages/vit/efficientvit https://github.com/dusty-nv/jetson-containers/tree/master/packages/hardware/jupyter_clickable_image_widget https://github.com/dusty-nv/jetson-containers/tree/master/packages/l4t/l4t-ml https://github.com/dusty-nv/jetson-containers/tree/master/packages/rag/langchain https://github.com/dusty-nv/jetson-containers/tree/master/packages/rag/llama-index https://github.com/dusty-nv/jetson-containers/tree/master/packages/vit/sam https://github.com/dusty-nv/jetson-containers/tree/master/packages/vit/tam https://github.com/dusty-nv/jetson-containers/tree/master/packages/audio/voicecraft https://github.com/dusty-nv/jetson-containers/tree/master/packages/audio/whisper |
| Dockerfile | https://github.com/dusty-nv/jetson-containers/tree/master/packages/jupyterlab/Dockerfile |
| 镜像 | https://hub.docker.com/r/dustynv/jupyterlab/tags (2024-03-07, 0.7GB)https://hub.docker.com/r/dustynv/jupyterlab/tags (2023-12-06, 5.3GB)https://hub.docker.com/r/dustynv/jupyterlab/tags (2024-03-07, 5.4GB)https://hub.docker.com/r/dustynv/jupyterlab/tags (2023-10-07, 5.3GB)https://hub.docker.com/r/dustynv/jupyterlab/tags (2024-03-07, 0.6GB) |
| 说明 | 除非覆盖容器启动命令,否则会自动在8888端口启动Jupyter服务器 |
| 仓库/标签 | 日期 | 架构 | 大小 |
|---|---|---|---|
| https://hub.docker.com/r/dustynv/jupyterlab/tags | 2024-03-07 | arm64 | 0.7GB |
| https://hub.docker.com/r/dustynv/jupyterlab/tags | 2023-12-06 | arm64 | 5.3GB |
| https://hub.docker.com/r/dustynv/jupyterlab/tags | 2024-03-07 | arm64 | 5.4GB |
| https://hub.docker.com/r/dustynv/jupyterlab/tags | 2023-10-07 | arm64 | 5.3GB |
| https://hub.docker.com/r/dustynv/jupyterlab/tags | 2024-03-07 | arm64 | 0.6GB |
容器镜像与其他JetPack/L4T次要版本兼容:
• L4T R32.7容器可运行于其他L4T R32.7版本(JetPack 4.6+)
• L4T R35.x容器可运行于其他L4T R35.x版本(JetPack 5.1+)
若使用autotag工具,会在需要时自动构建兼容镜像。手动构建步骤:
bashjetson-containers build jupyterlab
构建过程会自动集成依赖项并进行测试。添加--help查看更多构建选项:
bashjetson-containers build jupyterlab --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