diff --git a/deploy/pdserving/README.md b/deploy/pdserving/README.md
index 3aae4781897deff3268e97bd4fe18096f11131d2..046aa5c74673e564592cc312c737cca04ad25dab 100644
--- a/deploy/pdserving/README.md
+++ b/deploy/pdserving/README.md
@@ -37,11 +37,11 @@ PaddleOCR operating environment and Paddle Serving operating environment are nee
 
     Install serving which used to start the service
     ```
-    pip3 install paddle-serving-server==0.6.0 # for CPU
-    pip3 install paddle-serving-server-gpu==0.6.0 # for GPU
+    pip3 install paddle-serving-server==0.6.1 # for CPU
+    pip3 install paddle-serving-server-gpu==0.6.1 # for GPU
     # Other GPU environments need to confirm the environment and then choose to execute the following commands
-    pip3 install paddle-serving-server-gpu==0.6.0.post101 # GPU with CUDA10.1 + TensorRT6
-    pip3 install paddle-serving-server-gpu==0.6.0.post11 # GPU with CUDA11 + TensorRT7
+    pip3 install paddle-serving-server-gpu==0.6.1.post101 # GPU with CUDA10.1 + TensorRT6
+    pip3 install paddle-serving-server-gpu==0.6.1.post11 # GPU with CUDA11 + TensorRT7
     ```
 
 3. Install the client to send requests to the service
@@ -55,7 +55,7 @@ PaddleOCR operating environment and Paddle Serving operating environment are nee
 
 4. Install serving-app
     ```
-    pip3 install paddle-serving-app==0.6.0
+    pip3 install paddle-serving-app==0.6.1
     ```
 
    **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).
@@ -204,7 +204,9 @@ Windows does not support Pipeline Serving, if we want to lauch paddle serving on
 
 ```
 cd win
-python3 ocr_web_server.py
+python3 ocr_web_server.py gpu(for gpu user)
+or
+python3 ocr_web_server.py cpu(for cpu user)
 ```
 
 2. Client Send Requests
diff --git a/deploy/pdserving/README_CN.md b/deploy/pdserving/README_CN.md
index 5ac609ee1780ac57d8b7ba8b5073e1a6de62d618..2e60d5f17610b2bc5e23183703cec1a2444788fa 100644
--- a/deploy/pdserving/README_CN.md
+++ b/deploy/pdserving/README_CN.md
@@ -36,11 +36,11 @@ PaddleOCR提供2种服务部署方式：
 
 1. 安装serving，用于启动服务
     ```
-    pip3 install paddle-serving-server==0.6.0 # for CPU
-    pip3 install paddle-serving-server-gpu==0.6.0 # for GPU
+    pip3 install paddle-serving-server==0.6.1 # for CPU
+    pip3 install paddle-serving-server-gpu==0.6.1 # for GPU
     # 其他GPU环境需要确认环境再选择执行如下命令
-    pip3 install paddle-serving-server-gpu==0.6.0.post101 # GPU with CUDA10.1 + TensorRT6
-    pip3 install paddle-serving-server-gpu==0.6.0.post11 # GPU with CUDA11 + TensorRT7
+    pip3 install paddle-serving-server-gpu==0.6.1.post101 # GPU with CUDA10.1 + TensorRT6
+    pip3 install paddle-serving-server-gpu==0.6.1.post11 # GPU with CUDA11 + TensorRT7
     ```
 
 2. 安装client，用于向服务发送请求
@@ -53,7 +53,7 @@ PaddleOCR提供2种服务部署方式：
 
 3. 安装serving-app
     ```
-    pip3 install paddle-serving-app==0.6.0
+    pip3 install paddle-serving-app==0.6.1
     ```
 
     **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)。
@@ -200,7 +200,9 @@ Windows用户不能使用上述的启动方式，需要使用Web Service，详
 
 ```
 cd win 
-python3 ocr_web_server.py
+python3 ocr_web_server.py gpu(使用gpu方式)
+或者
+python3 ocr_web_server.py cpu(使用cpu方式)
 ```
 
 2. 发送服务请求
diff --git a/deploy/pdserving/win/ocr_web_server.py b/deploy/pdserving/win/ocr_web_server.py
index 1f1394fb72acebe58ef5b2a03bf27cd25838c536..9fc94901295d2470a4a16289b67daf0a6cbdc52a 100644
--- a/deploy/pdserving/win/ocr_web_server.py
+++ b/deploy/pdserving/win/ocr_web_server.py
@@ -42,7 +42,7 @@ class OCRService(WebService):
         self.det_client = LocalPredictor()
         if sys.argv[1] == 'gpu':
             self.det_client.load_model_config(
-                det_model_config, use_gpu=True, gpu_id=1)
+                det_model_config, use_gpu=True, gpu_id=0)
         elif sys.argv[1] == 'cpu':
             self.det_client.load_model_config(det_model_config)
         self.ocr_reader = OCRReader(