Merge branch 'develop' into optimize-quantization-tool

README.md

@@ -61,9 +61,9 @@ Packages of Paddle Serving support Centos 6/7 and Ubuntu 16/18, or you can use H
 <h3 align="center">Chinese Word Segmentation</h4>
 
 ``` shell
-> python -m paddle_serving_app.package -get_model lac
+> python -m paddle_serving_app.package --get_model lac
 > tar -xzf lac.tar.gz
-> python lac_web_service.py 9292 &
+> python lac_web_service.py lac_model/ lac_workdir 9393 &
 > curl -H "Content-Type:application/json" -X POST -d '{"feed":[{"words": "我爱北京天安门"}], "fetch":["word_seg"]}' http://127.0.0.1:9393/lac/prediction
 {"result":[{"word_seg":"我|爱|北京|天安门"}]}
 ```
@@ -77,7 +77,7 @@ Packages of Paddle Serving support Centos 6/7 and Ubuntu 16/18, or you can use H
 <p>
     
 ``` shell
-> python -m paddle_serving_app.package -get_model resnet_v2_50_imagenet
+> python -m paddle_serving_app.package --get_model resnet_v2_50_imagenet
 > tar -xzf resnet_v2_50_imagenet.tar.gz
 > python resnet50_imagenet_classify.py resnet50_serving_model &
 > curl -H "Content-Type:application/json" -X POST -d '{"feed":[{"image": "https://paddle-serving.bj.bcebos.com/imagenet-example/daisy.jpg"}], "fetch": ["score"]}' http://127.0.0.1:9292/image/prediction
@@ -111,9 +111,9 @@ python -m paddle_serving_server.serve --model uci_housing_model --thread 10 --po
 | `port` | int | `9292` | Exposed port of current service to users|
 | `name` | str | `""` | Service name, can be used to generate HTTP request url |
 | `model` | str | `""` | Path of paddle model directory to be served |
-| `mem_optim` | bool | `False` | Enable memory / graphic memory optimization |
-| `ir_optim` | bool | `False` | Enable analysis and optimization of calculation graph |
-| `use_mkl` (Only for cpu version) | bool | `False` | Run inference with MKL |
+| `mem_optim` | - | - | Enable memory / graphic memory optimization |
+| `ir_optim` | - | - | Enable analysis and optimization of calculation graph |
+| `use_mkl` (Only for cpu version) | - | - | Run inference with MKL |
 
 Here, we use `curl` to send a HTTP POST request to the service we just started. Users can use any python library to send HTTP POST as well, e.g, [requests](https://requests.readthedocs.io/en/master/).
 </center>
@@ -170,13 +170,13 @@ Here, `client.predict` function has two arguments. `feed` is a `python dict` wit
 
 ### About Efficiency
 - [How to profile Paddle Serving latency?](python/examples/util)
-- [How to optimize performance?(Chinese)](doc/PERFORMANCE_OPTIM_CN.md)
+- [How to optimize performance?](doc/PERFORMANCE_OPTIM.md)
 - [Deploy multi-services on one GPU(Chinese)](doc/MULTI_SERVICE_ON_ONE_GPU_CN.md)
 - [CPU Benchmarks(Chinese)](doc/BENCHMARKING.md)
 - [GPU Benchmarks(Chinese)](doc/GPU_BENCHMARKING.md)
 
 ### FAQ
-- [FAQ(Chinese)](doc/deprecated/FAQ.md)
+- [FAQ(Chinese)](doc/FAQ.md)
 
 
 ### Design

README_CN.md

@@ -62,9 +62,9 @@ Paddle Serving安装包支持Centos 6/7和Ubuntu 16/18，或者您可以使用HT
 <h3 align="center">中文分词</h4>
 
 ``` shell
-> python -m paddle_serving_app.package -get_model lac
+> python -m paddle_serving_app.package --get_model lac
 > tar -xzf lac.tar.gz
-> python lac_web_service.py 9292 &
+> python lac_web_service.py lac_model/ lac_workdir 9393 &
 > curl -H "Content-Type:application/json" -X POST -d '{"feed":[{"words": "我爱北京天安门"}], "fetch":["word_seg"]}' http://127.0.0.1:9393/lac/prediction
 {"result":[{"word_seg":"我|爱|北京|天安门"}]}
 ```
@@ -78,7 +78,7 @@ Paddle Serving安装包支持Centos 6/7和Ubuntu 16/18，或者您可以使用HT
 <p>
     
 ``` shell
-> python -m paddle_serving_app.package -get_model resnet_v2_50_imagenet
+> python -m paddle_serving_app.package --get_model resnet_v2_50_imagenet
 > tar -xzf resnet_v2_50_imagenet.tar.gz
 > python resnet50_imagenet_classify.py resnet50_serving_model &
 > curl -H "Content-Type:application/json" -X POST -d '{"feed":[{"image": "https://paddle-serving.bj.bcebos.com/imagenet-example/daisy.jpg"}], "fetch": ["score"]}' http://127.0.0.1:9292/image/prediction
@@ -115,9 +115,9 @@ python -m paddle_serving_server.serve --model uci_housing_model --thread 10 --po
 | `port` | int | `9292` | Exposed port of current service to users|
 | `name` | str | `""` | Service name, can be used to generate HTTP request url |
 | `model` | str | `""` | Path of paddle model directory to be served |
-| `mem_optim` | bool | `False` | Enable memory optimization |
-| `ir_optim` | bool | `False` | Enable analysis and optimization of calculation graph |
-| `use_mkl` (Only for cpu version) | bool | `False` | Run inference with MKL |
+| `mem_optim` | - | - | Enable memory optimization |
+| `ir_optim` | - | - | Enable analysis and optimization of calculation graph |
+| `use_mkl` (Only for cpu version) | - | - | Run inference with MKL |
 
 我们使用 `curl` 命令来发送HTTP POST请求给刚刚启动的服务。用户也可以调用python库来发送HTTP POST请求，请参考英文文档 [requests](https://requests.readthedocs.io/en/master/)。
 </center>
@@ -181,7 +181,7 @@ print(fetch_map)
 - [GPU版Benchmarks](doc/GPU_BENCHMARKING.md)
 
 ### FAQ
-- [常见问答](doc/deprecated/FAQ.md)
+- [常见问答](doc/FAQ.md)
 
 ### 设计文档
 - [Paddle Serving设计文档](doc/DESIGN_DOC_CN.md)

doc/BERT_10_MINS.md

@@ -59,7 +59,7 @@ the script of client side bert_client.py is as follow:
 import os
 import sys
 from paddle_serving_client import Client
-from paddle_serving_app import ChineseBertReader
+from paddle_serving_app.reader import ChineseBertReader
 
 reader = ChineseBertReader()
 fetch = ["pooled_output"]

doc/BERT_10_MINS_CN.md

@@ -52,7 +52,7 @@ pip install paddle_serving_app
 ``` python
 import sys
 from paddle_serving_client import Client
-from paddle_serving_app import ChineseBertReader
+from paddle_serving_app.reader import ChineseBertReader
 
 reader = ChineseBertReader()
 fetch = ["pooled_output"]

doc/FAQ.md

+# FAQ
+
+- Q：如何调整RPC服务的等待时间，避免超时？ 
+
+  A：使用set_rpc_timeout_ms设置更长的等待时间，单位为毫秒，默认时间为20秒。
+  
+  示例：
+  ```
+  from paddle_serving_client import Client
+
+  client = Client()
+  client.load_client_config(sys.argv[1])
+  client.set_rpc_timeout_ms(100000)
+  client.connect(["127.0.0.1:9393"])
+  ```

doc/IMDB_GO_CLIENT_CN.md

@@ -99,7 +99,7 @@ func main() {
 ### 基于IMDB测试集的预测
 
 ```python
-go run imdb_client.go serving_client_conf / serving_client_conf.stream.prototxt test.data> result
+go run imdb_client.go serving_client_conf/serving_client_conf.stream.prototxt test.data> result
 ```
 
 ### 计算精度

doc/PERFORMANCE_OPTIM.md

@@ -16,5 +16,5 @@ Parameters for performance optimization:
 
 | Parameters | Type | Default | Description                                                  |
 | ---------- | ---- | ------- | ------------------------------------------------------------ |
-| mem_optim  | bool | False   | Enable memory / graphic memory optimization                                   |
-| ir_optim   | bool | Fasle   | Enable analysis and optimization of calculation graph,including OP fusion, etc |
+| mem_optim  | - | - | Enable memory / graphic memory optimization                                   |
+| ir_optim   | - | -  | Enable analysis and optimization of calculation graph,including OP fusion, etc |

doc/PERFORMANCE_OPTIM_CN.md

@@ -16,5 +16,5 @@
 
 | 参数      | 类型 | 默认值 | 含义                      |
 | --------- | ---- | ------ | -------------------------------- |
-| mem_optim | bool | False  | 开启内存/显存优化                |
-| ir_optim  | bool | Fasle  | 开启计算图分析优化，包括OP融合等 |
+| mem_optim | - | -  | 开启内存/显存优化                |
+| ir_optim  | - | -  | 开启计算图分析优化，包括OP融合等 |

python/paddle_serving_server/serve.py

@@ -40,10 +40,14 @@ def parse_args():  # pylint: disable=doc-string-missing
     parser.add_argument(
         "--device", type=str, default="cpu", help="Type of device")
     parser.add_argument(
-        "--mem_optim", type=bool, default=False, help="Memory optimize")
+        "--mem_optim",
+        default=False,
+        action="store_true",
+        help="Memory optimize")
     parser.add_argument(
-        "--ir_optim", type=bool, default=False, help="Graph optimize")
-    parser.add_argument("--use_mkl", type=bool, default=False, help="Use MKL")
+        "--ir_optim", default=False, action="store_true", help="Graph optimize")
+    parser.add_argument(
+        "--use_mkl", default=False, action="store_true", help="Use MKL")
     parser.add_argument(
         "--max_body_size",
         type=int,

python/paddle_serving_server_gpu/__init__.py

@@ -57,9 +57,12 @@ def serve_args():
     parser.add_argument(
         "--name", type=str, default="None", help="Default service name")
     parser.add_argument(
-        "--mem_optim", type=bool, default=False, help="Memory optimize")
+        "--mem_optim",
+        default=False,
+        action="store_true",
+        help="Memory optimize")
     parser.add_argument(
-        "--ir_optim", type=bool, default=False, help="Graph optimize")
+        "--ir_optim", default=False, action="store_true", help="Graph optimize")
     parser.add_argument(
         "--max_body_size",
         type=int,