diff --git a/deploy/paddleserving/README.md b/deploy/paddleserving/README.md
index 8244b2597..75eb3e35b 100644
--- a/deploy/paddleserving/README.md
+++ b/deploy/paddleserving/README.md
@@ -8,7 +8,7 @@ PaddleClas provides two service deployment methods:
 
 # Service deployment based on PaddleServing  
 
-This document will introduce how to use the [PaddleServing](https://github.com/PaddlePaddle/Serving/blob/develop/README.md) to deploy the PPOCR dynamic graph model as a pipeline online service.
+This document will introduce how to use the [PaddleServing](https://github.com/PaddlePaddle/Serving/blob/develop/README.md) to deploy the ResNet50_vd model as a pipeline online service.
 
 Some Key Features of Paddle Serving:
 - Integrate with Paddle training pipeline seamlessly, most paddle models can be deployed with one line command.
@@ -137,7 +137,7 @@ fetch_var {
 2. Run the following command to start the service.
     ```
     # Start the service and save the running log in log.txt
-    python3 resnet50_web_service.py &>log.txt &
+    python3 classification_web_service.py &>log.txt &
     ```
     After the service is successfully started, a log similar to the following will be printed in log.txt
     ![](./imgs/start_server.png)
diff --git a/deploy/paddleserving/README_CN.md b/deploy/paddleserving/README_CN.md
index 447a043d6..3394ae5b5 100644
--- a/deploy/paddleserving/README_CN.md
+++ b/deploy/paddleserving/README_CN.md
@@ -29,7 +29,7 @@ PaddleClas提供2种服务部署方式：
 
 需要准备PaddleClas的运行环境和PaddleServing的运行环境。
 
-- 准备PaddleClas的[运行环境](../../docs/zh_CN/tutorials/install.md), 根据环境下载对应的paddle whl包，推荐安装2.0.1版本
+- 准备PaddleClas的[运行环境](../../docs/zh_CN/tutorials/install.md), 根据环境下载对应的paddle whl包，推荐安装2.1.0版本
 
 - 准备PaddleServing的运行环境，步骤如下
 
@@ -77,7 +77,7 @@ python3 -m paddle_serving_client.convert --dirname ./ResNet50_vd_infer/ \
                                          --serving_server ./ResNet50_vd_serving/ \
                                          --serving_client ./ResNet50_vd_client/
 ```
-检测模型转换完成后，会在当前文件夹多出`ResNet50_vd_serving` 和`ResNet50_vd_client`的文件夹，具备如下格式：
+ResNet50_vd推理模型转换完成后，会在当前文件夹多出`ResNet50_vd_serving` 和`ResNet50_vd_client`的文件夹，具备如下格式：
 ```
 |- ResNet50_vd_client/
   |- __model__  
@@ -133,7 +133,7 @@ fetch_var {
 2. 启动服务可运行如下命令：
     ```
     # 启动服务，运行日志保存在log.txt
-    python3 resnet50_web_service.py &>log.txt &
+    python3 classification_web_service.py &>log.txt &
     ```
     成功启动服务后，log.txt中会打印类似如下日志
     ![](./imgs/start_server.png)
diff --git a/deploy/paddleserving/resnet50_web_service.py b/deploy/paddleserving/classification_web_service.py
similarity index 100%
rename from deploy/paddleserving/resnet50_web_service.py
rename to deploy/paddleserving/classification_web_service.py