fix doc

README.md

@@ -66,15 +66,6 @@ For **Windows Users**, please read the document [Paddle Serving for Windows User
 
 <h2 align="center"> Pre-built services with Paddle Serving</h2>
 
-<h3 align="center">Latest release</h4>
-<p align="center">
-    <a href="https://github.com/PaddlePaddle/Serving/tree/develop/python/examples/ocr">Optical Character Recognition</a>
-    <br>
-    <a href="https://github.com/PaddlePaddle/Serving/tree/develop/python/examples/faster_rcnn_model">Object Detection</a>
-    <br>
-    <a href="https://github.com/PaddlePaddle/Serving/tree/develop/python/examples/deeplabv3">Image Segmentation</a>
-<p>
-
 <h3 align="center">Chinese Word Segmentation</h4>
 
 ``` shell
@@ -133,7 +124,8 @@ python -m paddle_serving_server.serve --model uci_housing_model --thread 10 --po
 | `use_trt` (Only for trt version) | - | - | Run inference with TensorRT  |
 
 </center>
-``` python
+
+```python
 # A user can visit rpc service through paddle_serving_client API
 from paddle_serving_client import Client
 import numpy as np

README_CN.md

@@ -148,7 +148,7 @@ print(fetch_map)
 在这里，`client.predict`函数具有两个参数。 `feed`是带有模型输入变量别名和值的`python dict`。 `fetch`被要从服务器返回的预测变量赋值。 在该示例中，在训练过程中保存可服务模型时，被赋值的tensor名为`"x"`和`"price"`。
 
 <h3 align="center">HTTP服务</h3>
-用户也可以将数据格式处理逻辑放在服务器端进行，这样就可以直接用curl去访问服务，参考如下案例，在目录``python/examples/fit_a_line``
+用户也可以将数据格式处理逻辑放在服务器端进行，这样就可以直接用curl去访问服务，参考如下案例，在目录`python/examples/fit_a_line`
 
 ```python
 from paddle_serving_server.web_service import WebService

doc/BERT_10_MINS.md

@@ -56,21 +56,25 @@ the script of client side bert_client.py is as follow:
 
 [//file]:#bert_client.py
 ``` python
-import os
 import sys
 from paddle_serving_client import Client
+from paddle_serving_client.utils import benchmark_args
 from paddle_serving_app.reader import ChineseBertReader
+import numpy as np
+args = benchmark_args()
 
-reader = ChineseBertReader()
+reader = ChineseBertReader({"max_seq_len": 128})
 fetch = ["pooled_output"]
-endpoint_list = ["127.0.0.1:9292"]
+endpoint_list = ['127.0.0.1:9292']
 client = Client()
-client.load_client_config("bert_seq20_client/serving_client_conf.prototxt")
+client.load_client_config(args.model)
 client.connect(endpoint_list)
 
 for line in sys.stdin:
     feed_dict = reader.process(line)
-    result = client.predict(feed=feed_dict, fetch=fetch)
+    for key in feed_dict.keys():
+        feed_dict[key] = np.array(feed_dict[key]).reshape((128, 1))
+    result = client.predict(feed=feed_dict, fetch=fetch, batch=False)
 ```
 
 run

doc/BERT_10_MINS_CN.md

@@ -52,18 +52,23 @@ pip install paddle_serving_app
 ``` python
 import sys
 from paddle_serving_client import Client
+from paddle_serving_client.utils import benchmark_args
 from paddle_serving_app.reader import ChineseBertReader
+import numpy as np
+args = benchmark_args()
 
-reader = ChineseBertReader()
+reader = ChineseBertReader({"max_seq_len": 128})
 fetch = ["pooled_output"]
-endpoint_list = ["127.0.0.1:9292"]
+endpoint_list = ['127.0.0.1:9292']
 client = Client()
-client.load_client_config("bert_seq20_client/serving_client_conf.prototxt")
+client.load_client_config(args.model)
 client.connect(endpoint_list)
 
 for line in sys.stdin:
     feed_dict = reader.process(line)
-    result = client.predict(feed=feed_dict, fetch=fetch)
+    for key in feed_dict.keys():
+        feed_dict[key] = np.array(feed_dict[key]).reshape((128, 1))
+    result = client.predict(feed=feed_dict, fetch=fetch, batch=False)
 ```
 
 执行