最近在用Docker搭建TensorFlow Serving, 在查閱了官方資料後，發現其文檔內有不少冗余的步驟，便一步步排查，終於找到了更簡單的Docker鏡像構建方法。這裏有兩種方式：

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鏡像更小些，所以比較推薦第一種方法。至於為何會有第二個版本，因為是從官方的文檔上找到的，而第一個來源自別人所提出問題的解答。

將上述代碼保存為dockerfile文件，再執行docker build命令：

docker build -t tensorflow-serving -f dockerfile .

之後，再通過docker run啟動容器即可：

docker run -p 9000:9000 tensorflow-serving

通過Docker構建TensorFlow Serving