使用Dockerfile创建Ubuntu+Pytorch+CUDA 镜像

过程

1. 安装Docker 参考ubuntu安装docker
2. 安装NVIDIA Container Toolkit 参考NVIDIA/nvidia-docker
3. 准备好Python-3.6.9.tar.xz
4. 从nvidia/cuda:10.0-cudnn7-devel-ubuntu16.04 镜像基础上搭建
5. 安装openssh-server、python、pytorch
6. run镜像时加上参数--gpus all --ipc=host

Dockerfile

# BASE IMAGEFROM nvidia/cuda:10.0-cudnn7-devel-ubuntu16.04 # LABEL MAINTAINERLABEL maintainer="ltobenull@gmail.com"SHELL ["/bin/bash","-c"]WORKDIR /tmp# copy安装文件COPY Python-3.6.9.tar.xz /tmp# 设置 root 密码RUN echo 'root:password' | chpasswd \# 安装openssh-server 并配置  && apt-get update && apt-get -y install openssh-server \  && sed -i 's/UsePAM yes/UsePAM no/g' /etc/ssh/sshd_config \   && sed -i 's/PermitRootLogin prohibit-password/PermitRootLogin yes/g' /etc/ssh/sshd_config \  && mkdir /var/run/sshd \# 安装python依赖包  && apt-get -y install build-essential python-dev python-setuptools python-pip python-smbus \  && apt-get -y install build-essential libncursesw5-dev libgdbm-dev libc6-dev \  && apt-get -y install zlib1g-dev libsqlite3-dev tk-dev \  && apt-get -y install libssl-dev openssl \  && apt-get -y install libffi-dev \# 安装python 3.6.9  && mkdir -p /usr/local/python3.6 \  && tar xvf Python-3.6.9.tar.xz \  && cd Python-3.6.9 \  && ./configure --prefix=/usr/local/python3.6 \  && make altinstall \# 建立软链接  && ln -snf /usr/local/python3.6/bin/python3.6 /usr/bin/python3 \  && ln -snf /usr/local/python3.6/bin/pip3.6 /usr/bin/pip3\# 安装pytorch  && mkdir ~/.pip && echo -e '[global] \nindex-url = https://mirrors.aliyun.com/pypi/simple/' >> ~/.pip/pip.conf \  && pip3 install torch===1.2.0 torchvision===0.4.0 -f https://download.pytorch.org/whl/torch_stable.html \# 清理copy的安装文件  && apt-get clean \  && rm -rf /tmp/* /var/tmp/*EXPOSE 22CMD ["/usr/sbin/sshd", "-D"]