diff --git a/python/examples/deeplabv3/README.md b/python/examples/deeplabv3/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..3eb5c84e2d5be7c7a1448940c758e60d77bd56e6
--- /dev/null
+++ b/python/examples/deeplabv3/README.md
@@ -0,0 +1,22 @@
+# Image Segmentation
+
+## Get Model
+
+```
+python -m paddle_serving_app.package --get_model deeplabv3
+tar -xzvf deeplabv3.tar.gz
+```
+
+## RPC Service
+
+### Start Service
+
+```
+python -m paddle_serving_server_gpu.serve --model deeplabv3_server --gpu_ids 0 --port 9494
+```
+
+### Client Prediction
+
+```
+python deeplabv3_client.py
+```
diff --git a/python/examples/deeplabv3/README_CN.md b/python/examples/deeplabv3/README_CN.md
new file mode 100644
index 0000000000000000000000000000000000000000..fad65ceb57cc61522d5d4558cda141df7a066fd8
--- /dev/null
+++ b/python/examples/deeplabv3/README_CN.md
@@ -0,0 +1,21 @@
+# i图像分割
+
+## 获取模型
+
+```
+python -m paddle_serving_app.package --get_model deeplabv3
+tar -xzvf deeplabv3.tar.gz
+```
+
+## RPC 服务
+
+### 启动服务端
+
+```
+python -m paddle_serving_server_gpu.serve --model deeplabv3_server --gpu_ids 0 --port 9494
+```
+
+### 客户端预测
+
+```
+python deeplabv3_client.py
diff --git a/python/examples/deeplabv3/deeplabv3_client.py b/python/examples/deeplabv3/deeplabv3_client.py
index 75ea6b0a01868af30c94fb0686159571c2c1c966..77e25d5f5a24d0aa1dad8939c1e7845eaf5e4122 100644
--- a/python/examples/deeplabv3/deeplabv3_client.py
+++ b/python/examples/deeplabv3/deeplabv3_client.py
@@ -18,7 +18,7 @@ import sys
 import cv2
 
 client = Client()
-client.load_client_config("seg_client/serving_client_conf.prototxt")
+client.load_client_config("deeplabv3_client/serving_client_conf.prototxt")
 client.connect(["127.0.0.1:9494"])
 
 preprocess = Sequential(