一、准备Dockerfile 。

Dockerfile是我修改成百度源后的，清华源速度在我这有点蛋疼。需要修改模型的注意下载路径和修改解压包名。

# Version: 1.0.0
FROM hub.baidubce.com/paddlepaddle/paddle:latest-gpu-cuda9.0-cudnn7-dev

# PaddleOCR base on Python3.7
#RUN pip3.7 install --upgrade pip -i https://pypi.tuna.tsinghua.edu.cn/simple
RUN pip3.7 install --upgrade pip -i https://mirror.baidu.com/pypi/simple
#RUN python3.7 -m pip install paddlepaddle==1.7.2 -i https://pypi.tuna.tsinghua.edu.cn/simple
RUN python3.7 -m pip install paddlepaddle==1.7.2 -i https://mirror.baidu.com/pypi/simple

#RUN pip3.7 install paddlehub --upgrade -i https://pypi.tuna.tsinghua.edu.cn/simple
RUN pip3.7 install paddlehub --upgrade -i https://mirror.baidu.com/pypi/simple

#RUN git clone https://gitee.com/PaddlePaddle/PaddleOCR
RUN cd / && git clone -b develop --depth 1 https://github.com/PaddlePaddle/PaddleOCR.git

WORKDIR /PaddleOCR

#RUN pip3.7 install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
RUN pip3.7 install -r requirements.txt -i https://mirror.baidu.com/pypi/simple

RUN mkdir -p /PaddleOCR/inference/ch_rec_mv3_crnn
RUN mkdir -p /PaddleOCR/inference/ch_det_mv3_db
# Download orc detect model(light version). if you want to change normal version, you can change ch_det_mv3_db_infer to ch_det_r50_vd_db_infer, also remember$
#ADD https://paddleocr.bj.bcebos.com/ch_models/ch_det_mv3_db_infer.tar /PaddleOCR/inference
#ADD https://paddleocr.bj.bcebos.com/ch_models/ch_rec_r34_vd_crnn_enhance_infer.tar  /PaddleOCR/inference
ADD https://paddleocr.bj.bcebos.com/ch_models/ch_rec_r34_vd_crnn_infer.tar  /PaddleOCR/inference
#RUN tar xf /PaddleOCR/inference/ch_rec_r34_vd_crnn_enhance_infer.tar --strip-components 1  -C /PaddleOCR/inference/ch_rec_mv3_crnn
RUN tar xf /PaddleOCR/inference/ch_rec_r34_vd_crnn_infer.tar --strip-components 1  -C /PaddleOCR/inference/ch_rec_mv3_crnn
# Download orc recognition model(light version). If you want to change normal version, you can change ch_rec_mv3_crnn_infer to ch_rec_r34_vd_crnn_enhance_inf$
#ADD https://paddleocr.bj.bcebos.com/ch_models/ch_rec_mv3_crnn_infer.tar /PaddleOCR/inference
ADD https://paddleocr.bj.bcebos.com/ch_models/ch_det_r50_vd_db_infer.tar  /PaddleOCR/inference
RUN tar xf /PaddleOCR/inference/ch_det_r50_vd_db_infer.tar --strip-components 1  -C /PaddleOCR/inference/ch_det_mv3_db

EXPOSE 8866

CMD ["/bin/bash","-c","export PYTHONPATH=. && hub install deploy/hubserving/ocr_system/ && hub serving start -m ocr_system"]

二、构建镜像

docker build -t paddleocr:cpu . 

三、创建容器

docker run -dp 8866:8866 --name paddle_ocr paddleocr:cpu

四、测试CURL

curl -H "Content-Type:application/json" -X POST --data "{\"images\": [\"填入图片Base64编码(需要删除'data:image/jpg;base64,'）\"]}" http://localhost:8866/predict/ocr_system

参考文档
https://gitee.com/paddlepaddle/PaddleOCR/tree/develop/docker/hubserving