Ubuntu18.04安装nvidia-docker（亲测有效，步骤详尽）

Ubuntu 18.04安装NVIDIA-docker

０．前提：　
　　（１）首先安装docker；具体步骤：https://blog.csdn.net/BigData_Mining/article/details/87868711
　　（２）安装Nvidia驱动，CUDA和CUDNN;具体步骤：https://blog.csdn.net/BigData_Mining/article/details/99670642
１．然后执行下面的步骤：

$curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | sudo apt-key add -
$curl -s -L https://nvidia.github.io/nvidia-docker/ubuntu18.04/nvidia-docker.list | sudo tee /etc/apt/sources.list.d/nvidia-docker.list
$sudo apt-get update

2.安装nvidia-docker2软件包并重新加载docker守护程序配置

$sudo apt-get install nvidia-docker2
$sudo pkill -SIGHUP dockerd
$docker run --runtime=nvidia --rm nvidia/cuda nvidia-smi

[注]：运行上一步若报错：

qyh@qyh-mas:~$ sudo docker run --runtime=nvidia --rm nvidia/cuda nvidia-smi
docker: Error response from daemon: Unknown runtime specified nvidia.
See 'docker run --help'.

当显卡驱动安装好的前提下（用指令$nvidia-smi来显示显卡驱动），则换成运行下步，指定安装的cuda版本：

$sudo nvidia-docker run --rm nvidia/cuda:10.1-devel nvidia-smi

qyh@qyh-mas:~$ sudo nvidia-docker run --rm nvidia/cuda:10.1-devel | nvidia-smi
Fri Aug 16 16:30:02 2019       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 430.26       Driver Version: 430.26       CUDA Version: 10.2     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  GeForce 940MX       Off  | 00000000:3C:00.0 Off |                  N/A |
| N/A   52C    P0    N/A /  N/A |    239MiB /  2004MiB |      4%      Default |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID   Type   Process name                             Usage      |
|=============================================================================|
|    0      3038      G   /usr/lib/xorg/Xorg                           121MiB |
|    0      4709      G   /usr/bin/gnome-shell                         109MiB |
|    0     18218      G   /usr/lib/firefox/firefox                       1MiB |
|    0     18402      G   /usr/lib/firefox/firefox                       1MiB |
|    0     18463      G   /usr/lib/firefox/firefox                       1MiB |
+-----------------------------------------------------------------------------+
Unable to find image 'nvidia/cuda:10.1-devel' locally
10.1-devel: Pulling from nvidia/cuda
7413c47ba209: Pulling fs layer
0fe7e7cbb2e8: Pulling fs layer
1d425c982345: Pulling fs layer
344da5c95cec: Pulling fs layer
43bcc41986db: Pulling fs layer
76661327d908: Pulling fs layer
abdc887b90e5: Pulling fs layer
eb38470de0e2: Pulling fs layer
0adb8d7f107f: Pulling fs layer

表示成功了！