装caffe2还是用docker吧 ubuntu安装docker caffe2教程 detectron docker安装教程

喜欢ヅ旅行 2021-09-16 13:54 319阅读 0赞

编译总是出现各种问题，还是用docker快。[Docker常用命令][Docker]

**1、Docker安装**

sudo apt-get remove docker docker-engine docker.io
    
    sudo apt-get -y install \
      apt-transport-https \
      ca-certificates \
      curl
     
    
    curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo apt-key add -
     
    
    sudo add-apt-repository \
           "deb [arch=amd64] https://download.docker.com/linux/ubuntu \
           $(lsb_release -cs) \
           stable"
     
    
    sudo apt-get update
    
    
    sudo apt-get -y install docker-ce

测试：会出现docker的配置信息

docker info

**2、nvidia-docker安装**

# If you have nvidia-docker 1.0 installed: we need to remove it and all existing GPU containers
    docker volume ls -q -f driver=nvidia-docker | xargs -r -I{} -n1 docker ps -q -a -f volume={} | xargs -r docker rm -f
    sudo apt-get purge -y nvidia-docker
    
    
    # Add the package repositories
    curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | \
      sudo apt-key add -
    distribution=$(. /etc/os-release;echo $ID$VERSION_ID)
    curl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.list | \
      sudo tee /etc/apt/sources.list.d/nvidia-docker.list
    sudo apt-get update
    
    
    # Install nvidia-docker2 and reload the Docker daemon configuration
    sudo apt-get install -y nvidia-docker2
    sudo pkill -SIGHUP dockerd

测试：会出现gpu信息

# Test nvidia-smi with the latest official CUDA image
    docker run --runtime=nvidia --rm nvidia/cuda:9.0-base nvidia-smi

**3、caffe2安装**

docker pull caffe2ai/caffe2
    
    
    # to test
    nvidia-docker run -it caffe2ai/caffe2:latest python -m caffe2.python.operator_test.relu_op_test
    
    
    # to interact
    nvidia-docker run -it caffe2ai/caffe2:latest /bin/bash

**4、其他**

**修改docker权限，避免sudo：**

sudo groupadd docker
    
    sudo gpasswd -a ${USER} docker
    
    sudo service docker restart
    
    newgrp - docker

**修改docker默认镜像存储路径：**

$ sudo service docker stop
    
    # 使用软连接到~/.docker文件夹，docker默认文件为/var/lib/docker
    $ sudo mv /var/lib/docker ~/.docker
    
    $ sudo ln -s ~/.docker /var/lib/docker
    
    $ sudo service docker start
    
    #连接成功后可以使用docker info查询Docker Root Dir是否改变

**5、Detectron Docker安装**

安装detectron docker时，不需要前面安装的caffe2，因为detectron在新建docker时自动pull一个caffe2 docker。

#docker build
    
    git clone https://github.com/facebookresearch/detectron
    
    cd detectron/docker
    
    docker build -t detectron:c2-cuda9-cudnn7 .
    
    #test
    
    nvidia-docker run --rm -it detectron:c2-cuda9-cudnn7 python detectron/tests/test_batch_permutation_op.py

使用：

#映射主机路径，后台启用一个容器
    nvidia-docker run -it --name detectron -v /data/sss/vqa:/vqa -d detectron:c2-cuda9-cudnn7
    
    #运行容器
    docker exec -it detectron /bin/bash
    
    #执行代码
    python2 tests/test_batch_permutation_op.py

[Docker]: https://blog.csdn.net/qq_16234613/article/details/61420853