diff --git a/deploy/paddle-serving/README.md b/deploy/paddle-serving/README.md
index 5faea824f16e741b8c2fc3767f055e3fcfcae0f3..6e646e3d60d830a0e9bedcbc4cbfa639bf89ac67 100644
--- a/deploy/paddle-serving/README.md
+++ b/deploy/paddle-serving/README.md
@@ -13,7 +13,7 @@ PaddleServing是Paddle的在线预测服务框架，可以快速部署训练好
 ```shell
 pip install paddle_serving_server==0.3.2 #CPU
 pip install paddle_serving_server_gpu==0.3.2.post9 #GPU with CUDA9.0
-pip install paddle_serving_server_gpu==0.3.2.post9 #GPU with CUDA10.0
+pip install paddle_serving_server_gpu==0.3.2.post10 #GPU with CUDA10.0
 ```
 
 客户端安装：
@@ -49,6 +49,10 @@ python pdseg/export_serving_model.py --cfg configs/unet_optic.yaml TEST.TEST_MOD
 
 分别将serving_server和serving_client复制到server和client启动的路径下。
 
+本文中导出的unet模型示例[下载](https://paddle-serving.bj.bcebos.com/paddle_seg_demo/seg_unet_demo.tar.gz)。
+
+解压下载后的压缩包，可以得到seving_server和serving_client两个文件夹，用于以下步骤的测试。
+
 ## 4.部署预测服务
 
 ```shell
@@ -62,3 +66,9 @@ python seg_client.py ../../dataset/optic_disc_seg/JPEGImages/N0060.jpg
 ```
 脚本执行之后，会在输入图片所在的目录下生成处理后的图片
 示例中为`../../dataset/optic_disc_seg/JPEGImages/N0060_jpg_mask.png`和`../../dataset/optic_disc_seg/JPEGImages/N0060_jpg_result.png`
+
+如果需要使用其他模型进行预测，需要修改预处理部分和后处理部分。
+
+本文中使用的是paddle_serving_app中内置的处理方法，用户可以参考导出模型时生成的deploy.yaml修改预处理部分。
+
+后处理部分SegPostprocess初始化时接收的参数为分割的类别数。
diff --git a/deploy/paddle-serving/postprocess.py b/deploy/paddle-serving/postprocess.py
index 6e77879d4d1a4a756210facb9e9e8d7a2dba6c7b..d4d7fb1cb5a0075a40df05483e1978a51b974d19 100644
--- a/deploy/paddle-serving/postprocess.py
+++ b/deploy/paddle-serving/postprocess.py
@@ -56,3 +56,4 @@ class SegPostprocess(object):
                                 fy=0,
                                 interpolation=cv2.INTER_CUBIC)
         cv2.imwrite(vis_result_name, result_png, [cv2.CV_8UC1])
+        return result_png
diff --git a/deploy/paddle-serving/seg_client.py b/deploy/paddle-serving/seg_client.py
index cf90a8ab56fcf4c75ef09fd84958545598785d68..c5c6161b08d0704d853b8344ab3592d021350bcc 100644
--- a/deploy/paddle-serving/seg_client.py
+++ b/deploy/paddle-serving/seg_client.py
@@ -22,4 +22,4 @@ filename = sys.argv[1]
 im = preprocess(filename)
 fetch_map = client.predict(feed={"image": im}, fetch=["transpose_1.tmp_0"])
 fetch_map["filename"] = filename
-postprocess(fetch_map)
+result_png = postprocess(fetch_map)
diff --git a/pdseg/export_serving_model.py b/pdseg/export_serving_model.py
index 7e9ca73bc431cdea8c60362be420c0456c8f24e2..58793b231d26c33ba258aef31c6a91bc61cd82f6 100644
--- a/pdseg/export_serving_model.py
+++ b/pdseg/export_serving_model.py
@@ -1,5 +1,5 @@
 # coding: utf8
-# Copyright (c) 2019 PaddlePaddle Authors. All Rights Reserve.
+# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserve.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.