Tensorflow Serving Ubuntu GPU服务器安装Docker Part I

 

1. 先在GPU服务器上安装Docker-CE

• 命令行输入

curl -fsSL https://get.docker.com | bash -s docker --mirror Aliyun

• 安装完成后验证一下是否安装成功

sudo docker run hello-world

• 以下消息代表安装成功

Unable to find image 'hello-world:latest' locally
latest: Pulling from library/hello-world
0e03bdcc26d7: Pull complete 
Digest: sha256:d58e752213a51785838f9eed2b7a498ffa1cb3aa7f946dda11af39286c3db9a9
Status: Downloaded newer image for hello-world:latest

Hello from Docker!

This message shows that your installation appears to be working correctly.

2. 安装Nvidia相关

• 注意Docker 19.03后可以直接安装Nvidia Package,

# Add the package repositories
distribution=$(. /etc/os-release;echo $ID$VERSION_ID)
curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | sudo apt-key add -
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 && sudo apt-get install -y nvidia-container-toolkit
sudo systemctl restart docker

• 安装完成后验证

#### Test nvidia-smi with the latest official CUDA image
docker run --gpus all nvidia/cuda:10.0-base nvidia-smi

• 看到如下信息代表成功

Wed Jul 15 08:43:29 2020       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 418.67       Driver Version: 418.67       CUDA Version: 10.1     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  Tesla V100-SXM2...  On   | 00000000:00:09.0 Off |                    0 |
| N/A   63C    P0   234W / 300W |  17185MiB / 32480MiB |     99%      Default |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID   Type   Process name                             Usage      |
|=============================================================================|
+-----------------------------------------------------------------------------+

如有疑问可参考官方文档 https://github.com/NVIDIA/nvidia-docker

 

3. 从Docker上Pull一个GPU的Docker

docker pull tensorflow/serving:latest-gpu

 

4. 调用GPU端口 ：

• 下载一个tensorflow的Demo Repo

git clone https://github.com/tensorflow/serving

• 运行Docker

# Location of demo models
TESTDATA="$(pwd)/serving/tensorflow_serving/servables/tensorflow/testdata"

# Start TensorFlow Serving container and open the REST API port
docker run -t --rm -p 8501:8501 \
    -v "$TESTDATA/saved_model_half_plus_two_cpu:/models/half_plus_two" \
    -e MODEL_NAME=half_plus_two \
    -t tensorflow/serving:latest-gpu \
    tensorflow/serving &

• 调用Docker 8501端口

curl -d '{"instances": [1.0, 2.0, 5.0]}' \
    -X POST http://localhost:8501/v1/models/half_plus_two:predict

• 讲道理应该会出现如下图所示的代码

{
    "predictions": [2.5, 3.0, 4.5
    ]
}%    

OK,暂时就先这样,下次告诉你怎么部署自己的模型