通过Docker构建TensorFlow Serving

最近在用Docker搭建TensorFlow Serving, 在查阅了官方资料后，发现其文档内有不少冗余的步骤，便一步步排查，终于找到了更简单的Docker镜像构建方法。这里有两种方式：

版本一：

FROM ubuntu:18.04

# Install general packages
RUN apt-get update && apt-get install -y wget && \
    apt-get clean && \
    rm -rf /var/lib/apt/lists/*
    
# New installation of tensorflow-model-server    
RUN TEMP_DEB="$(mktemp)" \
    && wget -O "$TEMP_DEB" 'http://storage.googleapis.com/tensorflow-serving-apt/pool/tensorflow-model-server-1.8.0/t/tensorflow-model-server/tensorflow-model-server_1.8.0_all.deb' \ 
    && dpkg -i "$TEMP_DEB" \ 
    && rm -f "$TEMP_DEB" \ 
    && mkdir /tmp/model-export    
    
EXPOSE 9000

# Serve the model when the container starts
ENTRYPOINT ["tensorflow_model_server"]
CMD ["--port=9000", "--model_name=model", "--model_base_path=/tmp/model-export"]

版本二

FROM ubuntu:18.04

# Install general packages
RUN apt-get update && apt-get install -y curl gnupg

# New installation of tensorflow-model-server    
RUN echo "deb [arch=amd64] http://storage.googleapis.com/tensorflow-serving-apt stable tensorflow-model-server tensorflow-model-server-universal" | tee /etc/apt/sources.list.d/tensorflow-serving.list \ 
    && curl https://storage.googleapis.com/tensorflow-serving-apt/tensorflow-serving.release.pub.gpg | apt-key add - \ 
    && apt-get update && apt-get install tensorflow-model-server \ 
    && apt-get clean \ 
    && rm -rf /var/lib/apt/lists/*  \
    && mkdir /tmp/model-export 

EXPOSE 9000

# Serve the model when the container starts
ENTRYPOINT ["tensorflow_model_server"]
CMD ["--port=9000", "--model_name=model", "--model_base_path=/tmp/model-export"]

版本一生成的Docker镜像更小些，所以比较推荐第一种方法。至于为何会有第二个版本，因为是从官方的文档上找到的，而第一个来源自别人所提出问题的解答。

将上述代码保存为dockerfile文件，再执行docker build命令：

docker build -t tensorflow-serving -f dockerfile .

之后，再通过docker run启动容器即可：

docker run -p 9000:9000 tensorflow-serving