
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。
This Docker image provides a GPU-accelerated TensorFlow environment with JupyterLab preinstalled.
It is designed for machine learning, deep learning experimentation with NVIDIA GPU support for this project:
https://github.com/jchen8000/MLDLwithPython.git
To start the container with GPU support:
bashdocker run --gpus all -p 8888:8888 \ -v $(pwd):/tf/workspace \ -it --rm \ jchen8000/tf_gpu_jupyterlab:latest bash
To start the container with CPU only:
bashdocker run -p 8888:8888 \ -v $(pwd):/tf/workspace \ -it --rm \ jchen8000/tf_gpu_jupyterlab:latest bash
bashpip list
bashnvidia-smi
Or
bashpython3 -c "import tensorflow as tf; print(tf.config.list_physical_devices('GPU'))"
To launch JupyterLab within the container, run:
bashjupyter-lab --notebook-dir=/tf --ip 0.0.0.0 --no-browser --allow-root --port=8888 --NotebookApp.port_retries=0
JupyterLab will start and output a series of log messages. Look for a line similar to [***] copy this URL and paste it into a browser on your host machine.
JupyterLab will open in your browser and give you full access to your workspace and GPU‑accelerated environment.
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