fix readme

deploy/hubserving/readme.md

@@ -2,7 +2,7 @@
 
 PaddleOCR提供2种服务部署方式：
 - 基于PaddleHub Serving的部署：代码路径为"`./deploy/hubserving`"，按照本教程使用；
-- (coming soon)基于PaddleServing的部署：代码路径为"`./deploy/pdserving`"，使用方法参考[文档](../../deploy/pdserving/readme.md)。
+- 基于PaddleServing的部署：代码路径为"`./deploy/pdserving`"，使用方法参考[文档](../../deploy/pdserving/README_CN.md)。
 
 # 基于PaddleHub Serving的服务部署
 

deploy/hubserving/readme_en.md

@@ -2,7 +2,7 @@ English | [简体中文](readme.md)
 
 PaddleOCR provides 2 service deployment methods:
 - Based on **PaddleHub Serving**: Code path is "`./deploy/hubserving`". Please follow this tutorial.
-- (coming soon)Based on **PaddleServing**: Code path is "`./deploy/pdserving`". Please refer to the [tutorial](../../deploy/pdserving/readme.md) for usage.
+- Based on **PaddleServing**: Code path is "`./deploy/pdserving`". Please refer to the [tutorial](../../deploy/pdserving/README.md) for usage.
 
 # Service deployment based on PaddleHub Serving  
 

deploy/pdserving/README.md

@@ -4,7 +4,8 @@
 
 This document will introduce how to use the [PaddleServing](https://github.com/PaddlePaddle/Serving/blob/develop/README_CN.md) to deploy the PPOCR dynamic graph model as a pipeline online service.
 
-**note**: Paddle Serving service deployment framework introduction and tutorial reference [document](https://aistudio.baidu.com/aistudio/projectdetail/1550674).
+Compared with hubserving deployment, PaddleServing supports high concurrency and efficient communication between the client and the server.
+The introduction and tutorial of Paddle Serving service deployment framework reference [document](https://aistudio.baidu.com/aistudio/projectdetail/1550674).
 
 
 ## Contents
@@ -42,8 +43,17 @@ pip3 install paddle-serving-client-gpu==0.5.0 # for GPU
 3. Install serving-app
 ```
 pip3 install paddle-serving-app==0.3.0
+# fix local_predict to support load dynamic model
+# find the install directoory of paddle_serving_app
+vim /usr/local/lib/python3.7/site-packages/paddle_serving_app/local_predict.py
+# replace line 85 of local_predict.py config = AnalysisConfig(model_path) with:
+if os.path.exists(os.path.join(model_path, "__params__")):
+    config = AnalysisConfig(os.path.join(model_path, "__model__"), os.path.join(model_path, "__params__"))
+else:
+    config = AnalysisConfig(model_path)
 ```
 
+
 **note:** If you want to install the latest version of PaddleServing, refer to [link](https://github.com/PaddlePaddle/Serving/blob/develop/doc/LATEST_PACKAGES.md).
 
 

deploy/pdserving/README_CN.md

@@ -5,7 +5,7 @@
 本文档将介绍如何使用[PaddleServing](https://github.com/PaddlePaddle/Serving/blob/develop/README_CN.md)工具部署PPOCR
 动态图模型的pipeline在线服务。
 
-**note**: Paddle Serving服务化部署框架介绍和使用教程参考[文档](https://aistudio.baidu.com/aistudio/projectdetail/1550674)。
+相比较于hubserving部署，PaddleServing支持客户端和服务端之间 高并发和高效通信，更多有关Paddle Serving服务化部署框架介绍和使用教程参考[文档](https://aistudio.baidu.com/aistudio/projectdetail/1550674)。
 
 ## 目录
 - 环境准备
@@ -44,6 +44,16 @@ pip3 install paddle-serving-client-gpu==0.5.0   # for GPU
 ```
 pip3 install paddle-serving-app==0.3.0
 ```
+**note:**  安装0.3.0版本的serving-app后，为了能加载动态图模型，需要修改serving_app的源码，具体为：
+```
+# 找到paddle_serving_app的安装目录，找到并编辑local_predict.py文件
+vim /usr/local/lib/python3.7/site-packages/paddle_serving_app/local_predict.py
+# 将local_predict.py 的第85行 config = AnalysisConfig(model_path)  替换为：
+if os.path.exists(os.path.join(model_path, "__params__")):
+    config = AnalysisConfig(os.path.join(model_path, "__model__"), os.path.join(model_path, "__params__"))
+else:
+    config = AnalysisConfig(model_path)
+```
 
 **note:** 如果要安装最新版本的PaddleServing参考[链接](https://github.com/PaddlePaddle/Serving/blob/develop/doc/LATEST_PACKAGES.md)。