Merge branch 'develop' of https://github.com/PaddlePaddle/Serving into fix-issue-618

README.md

+([简体中文](./README_CN.md)|English)
+
 <p align="center">
     <br>
 <img src='doc/serving_logo.png' width = "600" height = "130">
     <br>
 <p>
 
+
 <p align="center">
     <br>
     <a href="https://travis-ci.com/PaddlePaddle/Serving">
@@ -56,6 +59,8 @@ pip install paddle-serving-server-gpu # GPU
 
 You may need to use a domestic mirror source (in China, you can use the Tsinghua mirror source, add `-i https://pypi.tuna.tsinghua.edu.cn/simple` to pip command) to speed up the download.
 
+If you need install modules compiled with develop branch, please download packages from [latest packages list](./doc/LATEST_PACKAGES.md) and install with `pip install` command.
+
 Client package support Centos 7 and Ubuntu 18, or you can use HTTP service without install client.
 
 <h2 align="center">Quick Start Example</h2>

README_CN.md

+(简体中文|[English](./README.md))
+
 <p align="center">
     <br>
 <img src='https://paddle-serving.bj.bcebos.com/imdb-demo%2FLogoMakr-3Bd2NM-300dpi.png' width = "600" height = "130">
     <br>
 <p>
 
+
 <p align="center">
     <br>
     <a href="https://travis-ci.com/PaddlePaddle/Serving">
@@ -57,6 +60,8 @@ pip install paddle-serving-server-gpu # GPU
 
 您可能需要使用国内镜像源（例如清华源, 在pip命令中添加`-i https://pypi.tuna.tsinghua.edu.cn/simple`）来加速下载。
 
+如果需要使用develop分支编译的安装包，请从[最新安装包列表](./doc/LATEST_PACKAGES.md)中获取下载地址进行下载，使用`pip install`命令进行安装。
+
 客户端安装包支持Centos 7和Ubuntu 18，或者您可以使用HTTP服务，这种情况下不需要安装客户端。
 
 <h2 align="center">快速启动示例</h2>

doc/LATEST_PACKAGES.md

+# Latest Wheel Packages
+
+## CPU server
+### Python 3
+```
+https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server-0.3.0-py3-none-any.whl
+```
+
+### Python 2
+```
+https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server-0.3.0-py2-none-any.whl
+```
+
+## GPU server
+### Python 3
+```
+https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server_gpu-0.3.0-py3-none-any.whl
+```
+### Python 2
+```
+https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server_gpu-0.3.0-py2-none-any.whl
+```
+
+## Client
+### Python 3.7
+```
+https://paddle-serving.bj.bcebos.com/whl/paddle_serving_client-0.3.0-cp37-none-manylinux1_x86_64.whl
+```
+### Python 3.6
+```
+https://paddle-serving.bj.bcebos.com/whl/paddle_serving_client-0.3.0-cp36-none-manylinux1_x86_64.whl
+```
+### Python 2.7
+```
+https://paddle-serving.bj.bcebos.com/whl/paddle_serving_client-0.3.0-cp27-none-manylinux1_x86_64.whl
+```
+
+## App
+### Python 3
+```
+https://paddle-serving.bj.bcebos.com/whl/paddle_serving_app-0.1.0-py3-none-any.whl
+```
+
+### Python 2
+```
+https://paddle-serving.bj.bcebos.com/whl/paddle_serving_app-0.1.0-py2-none-any.whl
+```

python/examples/bert/bert_web_service.py

@@ -21,7 +21,10 @@ import os
 
 class BertService(WebService):
     def load(self):
-        self.reader = ChineseBertReader(vocab_file="vocab.txt", max_seq_len=128)
+        self.reader = ChineseBertReader({
+            "vocab_file": "vocab.txt",
+            "max_seq_len": 128
+        })
 
     def preprocess(self, feed=[], fetch=[]):
         feed_res = [

python/examples/deeplabv3/README.md

+# 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
+```

python/examples/deeplabv3/README_CN.md

+# 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

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(

python/examples/faster_rcnn_model/README.md

@@ -12,8 +12,8 @@ If you want to have more detection models, please refer to [Paddle Detection Mod
 ### Start the service
 ```
 tar xf faster_rcnn_model.tar.gz
-mv faster_rcnn_model/pddet *.
-GLOG_v=2 python -m paddle_serving_server_gpu.serve --model pddet_serving_model --port 9494 --gpu_id 0
+mv faster_rcnn_model/pddet* .
+GLOG_v=2 python -m paddle_serving_server_gpu.serve --model pddet_serving_model --port 9494 --gpu_ids 0
 ```
 
 ### Perform prediction

python/examples/faster_rcnn_model/README_CN.md

@@ -13,7 +13,7 @@ wget https://paddle-serving.bj.bcebos.com/pddet_demo/infer_cfg.yml
 ```
 tar xf faster_rcnn_model.tar.gz
 mv faster_rcnn_model/pddet* ./
-GLOG_v=2 python -m paddle_serving_server_gpu.serve --model pddet_serving_model --port 9494 --gpu_id 0
+GLOG_v=2 python -m paddle_serving_server_gpu.serve --model pddet_serving_model --port 9494 --gpu_ids 0
 ```
 
 ### 执行预测

python/examples/imagenet/README_CN.md

@@ -19,10 +19,10 @@ pip install paddle_serving_app
 
 启动server端
 ```
-python image_classification_service.py ResNet50_vd_model cpu 9696 #cpu预测服务
+python resnet50_web_service.py ResNet50_vd_model cpu 9696 #cpu预测服务
 ```
 ```
-python image_classification_service.py ResNet50_vd_model gpu 9696 #gpu预测服务
+python resnet50_web_service.py ResNet50_vd_model gpu 9696 #gpu预测服务
 ```
 
 

python/examples/mobilenet/README.md

+# Image Classification
+
+## Get Model
+
+```
+python -m paddle_serving_app.package --get_model mobilenet_v2_imagenet
+tar -xzvf mobilenet_v2_imagenet.tar.gz
+```
+
+## RPC Service
+
+### Start Service
+
+```
+python -m paddle_serving_server_gpu.serve --model mobilenet_v2_imagenet_model --gpu_ids 0 --port 9393
+```
+
+### Client Prediction
+
+```
+python mobilenet_tutorial.py
+```

python/examples/mobilenet/README_CN.md

+# 图像分类
+
+## 获取模型
+
+```
+python -m paddle_serving_app.package --get_model mobilenet_v2_imagenet
+tar -xzvf mobilenet_v2_imagenet.tar.gz
+```
+
+## RPC 服务
+
+### 启动服务端
+
+```
+python -m paddle_serving_server_gpu.serve --model mobilenet_v2_imagenet_model --gpu_ids 0 --port 9393
+```
+
+### 客户端预测
+
+```
+python mobilenet_tutorial.py
+```

python/examples/resnet_v2_50/README.md

+# Image Classification
+
+## Get Model
+
+```
+python -m paddle_serving_app.package --get_model resnet_v2_50_imagenet
+tar -xzvf resnet_v2_50_imagenet.tar.gz
+```
+
+## RPC Service
+
+### Start Service
+
+```
+python -m paddle_serving_server_gpu.serve --model resnet_v2_50_imagenet_model --gpu_ids 0 --port 9393
+```
+
+### Client Prediction
+
+```
+python resnet50_v2_tutorial.py
+```

python/examples/resnet_v2_50/README_CN.md

+# 图像分类
+
+## 获取模型
+
+```
+python -m paddle_serving_app.package --get_model resnet_v2_50_imagenet
+tar -xzvf resnet_v2_50_imagenet.tar.gz
+```
+
+## RPC 服务
+
+### 启动服务端
+
+```
+python -m paddle_serving_server_gpu.serve --model resnet_v2_50_imagenet_model --gpu_ids 0 --port 9393
+```
+
+### 客户端预测
+
+```
+python resnet50_v2_tutorial.py
+```

python/examples/senta/get_data.sh

 wget https://paddle-serving.bj.bcebos.com/paddle_hub_models/text/SentimentAnalysis/senta_bilstm.tar.gz --no-check-certificate
 tar -xzvf senta_bilstm.tar.gz
 wget https://paddle-serving.bj.bcebos.com/paddle_hub_models/text/LexicalAnalysis/lac.tar.gz --no-check-certificate
-tar -xzvf lac_model.tar.gz
+tar -xzvf lac.tar.gz
 wget https://paddle-serving.bj.bcebos.com/reader/lac/lac_dict.tar.gz  --no-check-certificate
 tar -xzvf lac_dict.tar.gz
 wget https://paddle-serving.bj.bcebos.com/reader/senta/vocab.txt --no-check-certificate

python/examples/unet_for_image_seg/README.md

+# Image Segmentation
+
+## Get Model
+
+```
+python -m paddle_serving_app.package --get_model unet
+tar -xzvf unet.tar.gz
+```
+
+## RPC Service
+
+### Start Service
+
+```
+python -m paddle_serving_server_gpu.serve --model unet_model --gpu_ids 0 --port 9494
+```
+
+### Client Prediction
+
+```
+python seg_client.py
+```

python/examples/unet_for_image_seg/README_CN.md

+# 图像分割
+
+## 获取模型
+
+```
+python -m paddle_serving_app.package --get_model unet
+tar -xzvf unet.tar.gz
+```
+
+## RPC 服务
+
+### 启动服务端
+
+```
+python -m paddle_serving_server_gpu.serve --model unet_model --gpu_ids 0 --port 9494
+```
+
+### 客户端预测
+
+```
+python seg_client.py
+```

python/paddle_serving_app/README.md

@@ -12,7 +12,7 @@ pip install paddle_serving_app
 ## Get model list
 
 ```shell
-python -m paddle_serving_app.package --model_list
+python -m paddle_serving_app.package --list_model
 ```
 
 ## Download pre-training model

python/paddle_serving_app/README_CN.md

@@ -11,7 +11,7 @@ pip install paddle_serving_app
 ## 获取模型列表
 
 ```shell
-python -m paddle_serving_app.package --model_list
+python -m paddle_serving_app.package --list_model
 ```
 
 ## 下载预训练模型

python/paddle_serving_app/reader/image_reader.py

@@ -296,7 +296,10 @@ class File2Image(object):
         pass
 
     def __call__(self, img_path):
-        fin = open(img_path)
+        if py_version == 2:
+            fin = open(img_path)
+        else:
+            fin = open(img_path, "rb")
         sample = fin.read()
         data = np.fromstring(sample, np.uint8)
         img = cv2.imdecode(data, cv2.IMREAD_COLOR)

python/paddle_serving_client/__init__.py

@@ -61,13 +61,18 @@ class SDKConfig(object):
         self.tag_list = []
         self.cluster_list = []
         self.variant_weight_list = []
+        self.rpc_timeout_ms = 20000
+        self.load_balance_strategy = "la"
 
     def add_server_variant(self, tag, cluster, variant_weight):
         self.tag_list.append(tag)
         self.cluster_list.append(cluster)
         self.variant_weight_list.append(variant_weight)
 
-    def gen_desc(self):
+    def set_load_banlance_strategy(self, strategy):
+        self.load_balance_strategy = strategy
+
+    def gen_desc(self, rpc_timeout_ms):
         predictor_desc = sdk.Predictor()
         predictor_desc.name = "general_model"
         predictor_desc.service_name = \
@@ -86,7 +91,7 @@ class SDKConfig(object):
         self.sdk_desc.predictors.extend([predictor_desc])
         self.sdk_desc.default_variant_conf.tag = "default"
         self.sdk_desc.default_variant_conf.connection_conf.connect_timeout_ms = 2000
-        self.sdk_desc.default_variant_conf.connection_conf.rpc_timeout_ms = 20000
+        self.sdk_desc.default_variant_conf.connection_conf.rpc_timeout_ms = rpc_timeout_ms
         self.sdk_desc.default_variant_conf.connection_conf.connect_retry_count = 2
         self.sdk_desc.default_variant_conf.connection_conf.max_connection_per_host = 100
         self.sdk_desc.default_variant_conf.connection_conf.hedge_request_timeout_ms = -1
@@ -119,6 +124,7 @@ class Client(object):
         self.profile_ = _Profiler()
         self.all_numpy_input = True
         self.has_numpy_input = False
+        self.rpc_timeout_ms = 20000
 
     def load_client_config(self, path):
         from .serving_client import PredictorClient
@@ -171,6 +177,12 @@ class Client(object):
         self.predictor_sdk_.add_server_variant(tag, cluster,
                                                str(variant_weight))
 
+    def set_rpc_timeout_ms(self, rpc_timeout):
+        if not isinstance(rpc_timeout, int):
+            raise ValueError("rpc_timeout must be int type.")
+        else:
+            self.rpc_timeout_ms = rpc_timeout
+
     def connect(self, endpoints=None):
         # check whether current endpoint is available
         # init from client config
@@ -188,7 +200,7 @@ class Client(object):
                 print(
                     "parameter endpoints({}) will not take effect, because you use the add_variant function.".
                     format(endpoints))
-        sdk_desc = self.predictor_sdk_.gen_desc()
+        sdk_desc = self.predictor_sdk_.gen_desc(self.rpc_timeout_ms)
         self.client_handle_.create_predictor_by_desc(sdk_desc.SerializeToString(
         ))
 

python/paddle_serving_server/__init__.py

@@ -23,6 +23,7 @@ import paddle_serving_server as paddle_serving_server
 from .version import serving_server_version
 from contextlib import closing
 import collections
+import fcntl
 
 
 class OpMaker(object):
@@ -322,6 +323,10 @@ class Server(object):
         bin_url = "https://paddle-serving.bj.bcebos.com/bin/" + tar_name
         self.server_path = os.path.join(self.module_path, floder_name)
 
+        #acquire lock
+        version_file = open("{}/version.py".format(self.module_path), "r")
+        fcntl.flock(version_file, fcntl.LOCK_EX)
+
         if not os.path.exists(self.server_path):
             print('Frist time run, downloading PaddleServing components ...')
             r = os.system('wget ' + bin_url + ' --no-check-certificate')
@@ -345,6 +350,8 @@ class Server(object):
                         foemat(self.module_path))
                 finally:
                     os.remove(tar_name)
+        #release lock
+        version_file.close()
         os.chdir(self.cur_path)
         self.bin_path = self.server_path + "/serving"
 

python/paddle_serving_server_gpu/__init__.py

@@ -25,6 +25,7 @@ from .version import serving_server_version
 from contextlib import closing
 import argparse
 import collections
+import fcntl
 
 
 def serve_args():
@@ -347,6 +348,11 @@ class Server(object):
 
         download_flag = "{}/{}.is_download".format(self.module_path,
                                                    folder_name)
+
+        #acquire lock
+        version_file = open("{}/version.py".format(self.module_path), "r")
+        fcntl.flock(version_file, fcntl.LOCK_EX)
+
         if os.path.exists(download_flag):
             os.chdir(self.cur_path)
             self.bin_path = self.server_path + "/serving"
@@ -377,6 +383,8 @@ class Server(object):
                         format(self.module_path))
                 finally:
                     os.remove(tar_name)
+        #release lock
+        version_file.cloes()
         os.chdir(self.cur_path)
         self.bin_path = self.server_path + "/serving"