线下容器镜像迁移指导

docker  run -ti -d -v /${host_dir}:/${container_dir} ${your_image_tag}

docker  cp ${container_id}:/${container_path} .

conda create --name pytorch --clone base
pip install conda-pack
conda pack -n pytorch -o pytorch.tar.gz

FROM nvidia/cuda:11.3.1-cudnn8-devel-ubuntu18.04

USER root

# section1: add user ma-user whose uid is 1000 and user group ma-group whose gid is 100. If there alreay exists 1000:100 but not ma-user:ma-group, below code will remove it
RUN default_user=$(getent passwd 1000 | awk -F ':' '{print $1}') || echo "uid: 1000 does not exist" && \
    default_group=$(getent group 100 | awk -F ':' '{print $1}') || echo "gid: 100 does not exist" && \
    if [ ! -z ${default_group} ] && [ ${default_group} != "ma-group" ]; then \
        groupdel -f ${default_group}; \
        groupadd -g 100 ma-group; \
    fi && \
    if [ -z ${default_group} ]; then \
        groupadd -g 100 ma-group; \
    fi && \
    if [ ! -z ${default_user} ] && [ ${default_user} != "ma-user" ]; then \
        userdel -r ${default_user}; \
        useradd -d /home/ma-user -m -u 1000 -g 100 -s /bin/bash ma-user; \
        chmod -R 750 /home/ma-user; \
    fi && \
    if [ -z ${default_user} ]; then \
        useradd -d /home/ma-user -m -u 1000 -g 100 -s /bin/bash ma-user; \
        chmod -R 750 /home/ma-user; \
    fi && \
    # set bash as default
    rm /bin/sh && ln -s /bin/bash /bin/sh

# section2: config apt source and install tools needed.
RUN sed -i "s@http://.*archive.ubuntu.com@http://repo.huaweicloud.com@g" /etc/apt/sources.list && \
    sed -i "s@http://.*security.ubuntu.com@http://repo.huaweicloud.com@g" /etc/apt/sources.list && \
    apt-get update && \
    apt-get install -y ca-certificates curl ffmpeg git libgl1-mesa-glx libglib2.0-0 libibverbs-dev libjpeg-dev libpng-dev libsm6 libxext6 libxrender-dev ninja-build screen  tmux nfs-common dnsutils tcpdump sudo vim wget zip && \
    apt-get clean  && \
    rm -rf /var/lib/apt/lists/*

USER ma-user

# section3: install miniconda and rebuild conda env
RUN mkdir -p /home/ma-user/work/ && cd /home/ma-user/work/ && \
    wget https://repo.anaconda.com/miniconda/Miniconda3-py37_4.12.0-Linux-x86_64.sh && \
    chmod 777 Miniconda3-py37_4.12.0-Linux-x86_64.sh && \
    bash Miniconda3-py37_4.12.0-Linux-x86_64.sh -bfp /home/ma-user/anaconda3 && \
    wget https://ma-sa.obs.cn-north-4.myhuaweicloud.com/yangzilong/conda_env/pytorch.tar.gz && \
    mkdir -p /home/ma-user/anaconda3/envs/pytorch && \
    tar -xzf pytorch.tar.gz -C /home/ma-user/anaconda3/envs/pytorch && \
    source /home/ma-user/anaconda3/envs/pytorch/bin/activate && conda-unpack && \
    /home/ma-user/anaconda3/bin/conda init bash && \
    rm -rf /home/ma-user/work/*

ENV PATH=/home/ma-user/anaconda3/envs/pytorch/bin:$PATH

# section4: settings of Jupyter Notebook for pytorch env
RUN source /home/ma-user/anaconda3/envs/pytorch/bin/activate && \
    pip install ipykernel==6.7.0 --trusted-host https://repo.huaweicloud.com -i https://repo.huaweicloud.com/repository/pypi/simple && \
    ipython kernel install --user --env PATH /home/ma-user/anaconda3/envs/pytorch/bin:$PATH --name=pytorch && \
    rm -rf /home/ma-user/.local/share/jupyter/kernels/pytorch/logo-* && \
    rm -rf ~/.cache/pip/* && \
    echo 'export PATH=$PATH:/home/ma-user/.local/bin' >> /home/ma-user/.bashrc && \
    echo 'export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/nvidia/lib64' >> /home/ma-user/.bashrc && \
    echo 'conda activate pytorch' >> /home/ma-user/.bashrc