Merge pull request #507 from tangmq/develop

增加Docker化部署服务(HubServing模式）

deploy/android_demo/gradle/wrapper/gradle-wrapper.properties

@@ -1,4 +1,4 @@
-#Thu Aug 22 15:05:37 CST 2019
+#Wed Jul 22 23:48:44 CST 2020
 distributionBase=GRADLE_USER_HOME
 distributionPath=wrapper/dists
 zipStoreBase=GRADLE_USER_HOME

docker/hubserving/cpu/Dockerfile

@@ -0,0 +1,28 @@
+# 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 python3.7 -m pip install paddlepaddle==1.7.2 -i https://pypi.tuna.tsinghua.edu.cn/simple
+
+RUN pip3.7 install paddlehub --upgrade -i https://pypi.tuna.tsinghua.edu.cn/simple
+
+RUN git clone https://gitee.com/PaddlePaddle/PaddleOCR
+
+WORKDIR /PaddleOCR
+
+RUN pip3.7 install -r requirments.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
+
+RUN mkdir -p /PaddleOCR/inference
+# 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 change det_model_dir in deploy/hubserving/ocr_system/params.py）
+ADD https://paddleocr.bj.bcebos.com/ch_models/ch_det_mv3_db_infer.tar /PaddleOCR/inference
+RUN tar xf /PaddleOCR/inference/ch_det_mv3_db_infer.tar -C /PaddleOCR/inference
+
+# 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_infer, also remember change rec_model_dir in deploy/hubserving/ocr_system/params.py）
+ADD https://paddleocr.bj.bcebos.com/ch_models/ch_rec_mv3_crnn_infer.tar /PaddleOCR/inference
+RUN tar xf /PaddleOCR/inference/ch_rec_mv3_crnn_infer.tar -C /PaddleOCR/inference
+
+EXPOSE 8866
+
+CMD ["/bin/bash","-c","export PYTHONPATH=. && hub install deploy/hubserving/ocr_system/ && hub serving start -m ocr_system"]

docker/hubserving/gpu/Dockerfile

@@ -0,0 +1,28 @@
+# Version: 1.0.0
+FROM hub.baidubce.com/paddlepaddle/paddle:latest-gpu-cuda10.0-cudnn7-dev
+
+# PaddleOCR base on Python3.7
+RUN pip3.7 install --upgrade pip -i https://pypi.tuna.tsinghua.edu.cn/simple
+
+RUN python3.7 -m pip install paddlepaddle-gpu==1.7.2.post107 -i https://pypi.tuna.tsinghua.edu.cn/simple
+
+RUN pip3.7 install paddlehub --upgrade -i https://pypi.tuna.tsinghua.edu.cn/simple
+
+RUN git clone https://gitee.com/PaddlePaddle/PaddleOCR
+
+WORKDIR /home/PaddleOCR
+
+RUN pip3.7 install -r requirments.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
+
+RUN mkdir -p /PaddleOCR/inference
+# 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 change det_model_dir in deploy/hubserving/ocr_system/params.py）
+ADD https://paddleocr.bj.bcebos.com/ch_models/ch_det_mv3_db_infer.tar /PaddleOCR/inference
+RUN tar xf /PaddleOCR/inference/ch_det_mv3_db_infer.tar -C /PaddleOCR/inference
+
+# 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_infer, also remember change rec_model_dir in deploy/hubserving/ocr_system/params.py）
+ADD https://paddleocr.bj.bcebos.com/ch_models/ch_rec_mv3_crnn_infer.tar /PaddleOCR/inference
+RUN tar xf /PaddleOCR/inference/ch_rec_mv3_crnn_infer.tar -C /PaddleOCR/inference
+
+EXPOSE 8866
+
+CMD ["/bin/bash","-c","export PYTHONPATH=. && hub install deploy/hubserving/ocr_system/ && hub serving start -m ocr_system"]

docker/hubserving/readme.md

@@ -0,0 +1,55 @@
+# Docker化部署服务
+在日常项目应用中，相信大家一般都会希望能通过Docker技术，把PaddleOCR服务打包成一个镜像，以便在Docker或k8s环境里，快速发布上线使用。
+
+本文将提供一些标准化的代码来实现这样的目标。大家通过如下步骤可以把PaddleOCR项目快速发布成可调用的Restful API服务。（目前暂时先实现了基于HubServing模式的部署，后续作者计划增加PaddleServing模式的部署）
+
+## 1.实施前提准备
+
+需要先完成如下基本组件的安装：
+a. Docker环境
+b. 显卡驱动和CUDA 10.0+（GPU）
+c. NVIDIA Container Toolkit（GPU，Docker 19.03以上版本可以跳过此步）
+d. cuDNN 7.6+（GPU）
+
+## 2.制作镜像
+a.下载PaddleOCR项目代码
+```
+git clone https://github.com/PaddlePaddle/PaddleOCR.git
+```
+b.切换至Dockerfile目录（注：需要区分cpu或gpu版本，下文以cpu为例，gpu版本需要替换一下关键字即可）
+```
+cd docker/cpu
+```
+c.生成镜像
+```
+docker build -t paddleocr:cpu . 
+```
+
+## 3.启动Docker容器
+a. CPU 版本
+```
+sudo docker run -dp 8866:8866 --name paddle_ocr paddleocr:cpu
+```
+b. GPU 版本 (通过NVIDIA Container Toolkit)
+```
+sudo nvidia-docker run -dp 8866:8866 --name paddle_ocr paddleocr:gpu
+```
+c. GPU 版本 (Docker 19.03以上版本，可以直接用如下命令)
+```
+sudo docker run -dp 8866:8866 --gpus all --name paddle_ocr paddleocr:gpu
+```
+d. 检查服务运行情况（出现：Successfully installed ocr_system和Running on http://0.0.0.0:8866/等信息，表示运行成功）
+```
+docker logs -f paddle_ocr
+```
+
+## 4.测试服务
+a. 计算待识别图片的Base64编码（如果只是测试一下效果，可以通过免费的在线工具实现，如：http://tool.chinaz.com/tools/imgtobase/）
+b. 发送服务请求（可参见sample_request.txt中的值）
+```
+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
+```
+c. 返回结果（如果调用成功，会返回如下结果）
+```
+{"msg":"","results":[[{"confidence":0.8403433561325073,"text":"约定","text_region":[[345,377],[641,390],[634,540],[339,528]]},{"confidence":0.8131805658340454,"text":"最终相遇","text_region":[[356,532],[624,530],[624,596],[356,598]]}]],"status":"0"}
+```