Merge branch 'develop' into pddet

python/examples/bert/README.md

@@ -15,12 +15,18 @@ pip install paddlehub
 
 run 
 ```
-python prepare_model.py 20
+python prepare_model.py 128
 ```
 
-the 20 in the command above means max_seq_len in BERT model, which is the length of sample after preprocessing.
-the config file and model file for server side are saved in the folder bert_seq20_model.
-the config file generated for client side is saved in the folder bert_seq20_client.
+the 128 in the command above means max_seq_len in BERT model, which is the length of sample after preprocessing.
+the config file and model file for server side are saved in the folder bert_seq128_model.
+the config file generated for client side is saved in the folder bert_seq128_client.
+
+You can also download the above model from BOS(max_seq_len=128). After decompression, the config file and model file for server side are stored in the bert_chinese_L-12_H-768_A-12_model folder, and the config file generated for client side is stored in the bert_chinese_L-12_H-768_A-12_client folder:
+```shell
+wget https://paddle-serving.bj.bcebos.com/paddle_hub_models/text/SemanticModel/bert_chinese_L-12_H-768_A-12.tar.gz
+tar -xzf bert_chinese_L-12_H-768_A-12.tar.gz
+```
 
 ### Getting Dict and Sample Dataset
 
@@ -32,11 +38,11 @@ this script will download Chinese Dictionary File vocab.txt and Chinese Sample D
 ### RPC Inference Service
 Run
 ```
-python -m paddle_serving_server.serve --model bert_seq20_model/ --port 9292  #cpu inference service
+python -m paddle_serving_server.serve --model bert_seq128_model/ --port 9292  #cpu inference service
 ```
 Or
 ```
-python -m paddle_serving_server_gpu.serve --model bert_seq20_model/ --port 9292 --gpu_ids 0 #launch gpu inference service at GPU 0
+python -m paddle_serving_server_gpu.serve --model bert_seq128_model/ --port 9292 --gpu_ids 0 #launch gpu inference service at GPU 0
 ```
 
 ### RPC Inference
@@ -47,7 +53,7 @@ pip install paddle_serving_app
 ```
 Run
 ```
-head data-c.txt | python bert_client.py --model bert_seq20_client/serving_client_conf.prototxt
+head data-c.txt | python bert_client.py --model bert_seq128_client/serving_client_conf.prototxt
 ```
 
 the client reads data from data-c.txt and send prediction request, the prediction is given by word vector. (Due to massive data in the word vector, we do not print it).
@@ -58,7 +64,7 @@ the client reads data from data-c.txt and send prediction request, the predictio
 ```
 set environmental variable to specify which gpus are used, the command above means gpu 0 and gpu 1 is used.
 ```
- python bert_web_service.py bert_seq20_model/ 9292 #launch gpu inference service
+ python bert_web_service.py bert_seq128_model/ 9292 #launch gpu inference service
 ```
 ### HTTP Inference 
 
@@ -75,7 +81,7 @@ GPU：GPU V100 * 1
 CUDA/cudnn Version：CUDA 9.2，cudnn 7.1.4
 
 
-In the test, 10 thousand samples in the sample data are copied into 100 thousand samples. Each client thread sends a sample of the number of threads. The batch size is 1, the max_seq_len is 20, and the time unit is seconds.
+In the test, 10 thousand samples in the sample data are copied into 100 thousand samples. Each client thread sends a sample of the number of threads. The batch size is 1, the max_seq_len is 20(not 128 as described above), and the time unit is seconds.
 
 When the number of client threads is 4, the prediction speed can reach 432 samples per second.
 Because a single GPU can only perform serial calculations internally, increasing the number of client threads can only reduce the idle time of the GPU. Therefore, after the number of threads reaches 4, the increase in the number of threads does not improve the prediction speed.

python/examples/bert/README_CN.md

@@ -13,11 +13,17 @@ pip install paddlehub
 ```
 执行
 ```
-python prepare_model.py 20
+python prepare_model.py 128
+```
+参数128表示BERT模型中的max_seq_len，即预处理后的样本长度。
+生成server端配置文件与模型文件，存放在bert_seq128_model文件夹。
+生成client端配置文件，存放在bert_seq128_client文件夹。
+
+您也可以从bos上直接下载上述模型（max_seq_len=128），解压后server端配置文件与模型文件存放在bert_chinese_L-12_H-768_A-12_model文件夹，client端配置文件存放在bert_chinese_L-12_H-768_A-12_client文件夹：
+```shell
+wget https://paddle-serving.bj.bcebos.com/paddle_hub_models/text/SemanticModel/bert_chinese_L-12_H-768_A-12.tar.gz
+tar -xzf bert_chinese_L-12_H-768_A-12.tar.gz
 ```
-参数20表示BERT模型中的max_seq_len，即预处理后的样本长度。
-生成server端配置文件与模型文件，存放在bert_seq20_model文件夹
-生成client端配置文件，存放在bert_seq20_client文件夹
 
 ### 获取词典和样例数据
 
@@ -29,11 +35,11 @@ sh get_data.sh
 ### 启动RPC预测服务
 执行
 ```
-python -m paddle_serving_server.serve --model bert_seq20_model/ --port 9292  #启动cpu预测服务
+python -m paddle_serving_server.serve --model bert_seq128_model/ --port 9292  #启动cpu预测服务
 ```
 或者
 ```
-python -m paddle_serving_server_gpu.serve --model bert_seq20_model/ --port 9292 --gpu_ids 0 #在gpu 0上启动gpu预测服务
+python -m paddle_serving_server_gpu.serve --model bert_seq128_model/ --port 9292 --gpu_ids 0 #在gpu 0上启动gpu预测服务
 ```
 
 ### 执行预测
@@ -44,7 +50,7 @@ pip install paddle_serving_app
 ```
 执行
 ```
-head data-c.txt | python bert_client.py --model bert_seq20_client/serving_client_conf.prototxt
+head data-c.txt | python bert_client.py --model bert_seq128_client/serving_client_conf.prototxt
 ```
 启动client读取data-c.txt中的数据进行预测，预测结果为文本的向量表示（由于数据较多，脚本中没有将输出进行打印），server端的地址在脚本中修改。
 
@@ -54,7 +60,7 @@ head data-c.txt | python bert_client.py --model bert_seq20_client/serving_client
 ```
 通过环境变量指定gpu预测服务使用的gpu，示例中指定索引为0和1的两块gpu
 ```
- python bert_web_service.py bert_seq20_model/ 9292 #启动gpu预测服务
+ python bert_web_service.py bert_seq128_model/ 9292 #启动gpu预测服务
 ```
 ### 执行预测
 
@@ -70,7 +76,7 @@ curl -H "Content-Type:application/json" -X POST -d '{"words": "hello", "fetch":[
 
 环境：CUDA 9.2，cudnn 7.1.4
 
-测试中将样例数据中的1W个样本复制为10W个样本，每个client线程发送线程数分之一个样本，batch size为1，max_seq_len为20，时间单位为秒.
+测试中将样例数据中的1W个样本复制为10W个样本，每个client线程发送线程数分之一个样本，batch size为1，max_seq_len为20（而不是上面的128），时间单位为秒.
 
 在client线程数为4时，预测速度可以达到432样本每秒。
 由于单张GPU内部只能串行计算，client线程增多只能减少GPU的空闲时间，因此在线程数达到4之后，线程数增多对预测速度没有提升。

python/examples/bert/bert_client.py

@@ -29,7 +29,7 @@ from paddle_serving_app import ChineseBertReader
 
 args = benchmark_args()
 
-reader = ChineseBertReader({"max_seq_len": 20})
+reader = ChineseBertReader({"max_seq_len": 128})
 fetch = ["pooled_output"]
 endpoint_list = ["127.0.0.1:9292"]
 client = Client()

python/examples/bert/bert_web_service.py

@@ -21,7 +21,7 @@ import os
 
 class BertService(WebService):
     def load(self):
-        self.reader = BertReader(vocab_file="vocab.txt", max_seq_len=20)
+        self.reader = BertReader(vocab_file="vocab.txt", max_seq_len=128)
 
     def preprocess(self, feed={}, fetch=[]):
         feed_res = self.reader.process(feed["words"].encode("utf-8"))

python/paddle_serving_client/__init__.py

@@ -158,8 +158,7 @@ class Client(object):
                 )
         else:
             if self.predictor_sdk_ is None:
-                timestamp = time.time()
-                self.add_variant('default_tag_{}'.format(timestamp), endpoints,
+                self.add_variant('default_tag_{}'.format(id(self)), endpoints,
                                  100)
             else:
                 print(

python/paddle_serving_server/serve.py

@@ -19,6 +19,7 @@ Usage:
 """
 import argparse
 from .web_service import WebService
+from flask import Flask, request
 
 
 def parse_args():  # pylint: disable=doc-string-missing
@@ -88,3 +89,20 @@ if __name__ == "__main__":
         service.prepare_server(
             workdir=args.workdir, port=args.port, device=args.device)
         service.run_server()
+
+        app_instance = Flask(__name__)
+
+        @app_instance.before_first_request
+        def init():
+            service._launch_web_service()
+
+        service_name = "/" + service.name + "/prediction"
+
+        @app_instance.route(service_name, methods=["POST"])
+        def run():
+            return service.get_prediction(request)
+
+        app_instance.run(host="0.0.0.0",
+                         port=service.port,
+                         threaded=False,
+                         processes=4)

python/paddle_serving_server/web_service.py

@@ -50,44 +50,33 @@ class WebService(object):
         self.device = device
 
     def _launch_web_service(self):
-        app_instance = Flask(__name__)
-        client_service = Client()
-        client_service.load_client_config(
+        self.client_service = Client()
+        self.client_service.load_client_config(
             "{}/serving_server_conf.prototxt".format(self.model_config))
-        client_service.connect(["0.0.0.0:{}".format(self.port + 1)])
-        service_name = "/" + self.name + "/prediction"
+        self.client_service.connect(["0.0.0.0:{}".format(self.port + 1)])
 
-        @app_instance.route(service_name, methods=['POST'])
-        def get_prediction():
-            if not request.json:
-                abort(400)
-            if "fetch" not in request.json:
-                abort(400)
-            try:
-                feed, fetch = self.preprocess(request.json,
-                                              request.json["fetch"])
-                if isinstance(feed, list):
-                    fetch_map_batch = client_service.predict(
-                        feed_batch=feed, fetch=fetch)
-                    fetch_map_batch = self.postprocess(
-                        feed=request.json,
-                        fetch=fetch,
-                        fetch_map=fetch_map_batch)
-                    result = {"result": fetch_map_batch}
-                elif isinstance(feed, dict):
-                    if "fetch" in feed:
-                        del feed["fetch"]
-                    fetch_map = client_service.predict(feed=feed, fetch=fetch)
-                    result = self.postprocess(
-                        feed=request.json, fetch=fetch, fetch_map=fetch_map)
-            except ValueError:
-                result = {"result": "Request Value Error"}
-            return result
-
-        app_instance.run(host="0.0.0.0",
-                         port=self.port,
-                         threaded=False,
-                         processes=1)
+    def get_prediction(self, request):
+        if not request.json:
+            abort(400)
+        if "fetch" not in request.json:
+            abort(400)
+        try:
+            feed, fetch = self.preprocess(request.json, request.json["fetch"])
+            if isinstance(feed, list):
+                fetch_map_batch = self.client_service.predict(
+                    feed_batch=feed, fetch=fetch)
+                fetch_map_batch = self.postprocess(
+                    feed=request.json, fetch=fetch, fetch_map=fetch_map_batch)
+                result = {"result": fetch_map_batch}
+            elif isinstance(feed, dict):
+                if "fetch" in feed:
+                    del feed["fetch"]
+                fetch_map = self.client_service.predict(feed=feed, fetch=fetch)
+                result = self.postprocess(
+                    feed=request.json, fetch=fetch, fetch_map=fetch_map)
+        except ValueError:
+            result = {"result": "Request Value Error"}
+        return result
 
     def run_server(self):
         import socket
@@ -96,11 +85,7 @@ class WebService(object):
         print("http://{}:{}/{}/prediction".format(localIP, self.port,
                                                   self.name))
         p_rpc = Process(target=self._launch_rpc_service)
-        p_web = Process(target=self._launch_web_service)
         p_rpc.start()
-        p_web.start()
-        p_web.join()
-        p_rpc.join()
 
     def preprocess(self, feed={}, fetch=[]):
         return feed, fetch

python/paddle_serving_server_gpu/__init__.py

@@ -306,6 +306,9 @@ class Server(object):
         self.check_local_bin()
         if not self.use_local_bin:
             self.download_bin()
+            # wait for other process to download server bin
+            while not os.path.exists(self.server_path):
+                time.sleep(1)
         else:
             print("Use local bin : {}".format(self.bin_path))
         command = "{} " \
@@ -337,8 +340,5 @@ class Server(object):
                       self.gpuid,)
         print("Going to Run Comand")
         print(command)
-        # wait for other process to download server bin
-        while not os.path.exists(self.server_path):
-            time.sleep(1)
 
         os.system(command)

python/paddle_serving_server_gpu/serve.py

@@ -21,6 +21,7 @@ import argparse
 import os
 from multiprocessing import Pool, Process
 from paddle_serving_server_gpu import serve_args
+from flask import Flask, request
 
 
 def start_gpu_card_model(index, gpuid, args):  # pylint: disable=doc-string-missing
@@ -114,3 +115,20 @@ if __name__ == "__main__":
         web_service.prepare_server(
             workdir=args.workdir, port=args.port, device=args.device)
         web_service.run_server()
+
+        app_instance = Flask(__name__)
+
+        @app_instance.before_first_request
+        def init():
+            web_service._launch_web_service()
+
+        service_name = "/" + web_service.name + "/prediction"
+
+        @app_instance.route(service_name, methods=["POST"])
+        def run():
+            return web_service.get_prediction(request)
+
+        app_instance.run(host="0.0.0.0",
+                         port=web_service.port,
+                         threaded=False,
+                         processes=4)

python/paddle_serving_server_gpu/web_service.py

@@ -11,17 +11,16 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-#!flask/bin/python
-# pylint: disable=doc-string-missing
 
 from flask import Flask, request, abort
-from multiprocessing import Pool, Process, Queue
 from paddle_serving_server_gpu import OpMaker, OpSeqMaker, Server
 import paddle_serving_server_gpu as serving
+from multiprocessing import Pool, Process, Queue
 from paddle_serving_client import Client
-from .serve import start_multi_card
-import time
-import random
+from paddle_serving_server_gpu.serve import start_multi_card
+
+import sys
+import numpy as np
 
 
 class WebService(object):
@@ -29,7 +28,6 @@ class WebService(object):
         self.name = name
         self.gpus = []
         self.rpc_service_list = []
-        self.input_queues = []
 
     def load_model_config(self, model_config):
         self.model_config = model_config
@@ -66,12 +64,6 @@ class WebService(object):
         return server
 
     def _launch_rpc_service(self, service_idx):
-        if service_idx == 0:
-            self.rpc_service_list[service_idx].check_local_bin()
-            if not self.rpc_service_list[service_idx].use_local_bin:
-                self.rpc_service_list[service_idx].download_bin()
-        else:
-            time.sleep(3)
         self.rpc_service_list[service_idx].run_server()
 
     def prepare_server(self, workdir="", port=9393, device="gpu", gpuid=0):
@@ -93,87 +85,30 @@ class WebService(object):
                         gpuid,
                         thread_num=10))
 
-    def producers(self, inputqueue, endpoint):
-        client = Client()
-        client.load_client_config("{}/serving_server_conf.prototxt".format(
+    def _launch_web_service(self):
+        gpu_num = len(self.gpus)
+        self.client = Client()
+        self.client.load_client_config("{}/serving_server_conf.prototxt".format(
             self.model_config))
-        client.connect([endpoint])
-        while True:
-            request_json = inputqueue.get()
-            try:
-                feed, fetch = self.preprocess(request_json,
-                                              request_json["fetch"])
-                if isinstance(feed, list):
-                    fetch_map_batch = client.predict(
-                        feed_batch=feed, fetch=fetch)
-                    fetch_map_batch = self.postprocess(
-                        feed=request_json,
-                        fetch=fetch,
-                        fetch_map=fetch_map_batch)
-                    result = {"result": fetch_map_batch}
-                elif isinstance(feed, dict):
-                    if "fetch" in feed:
-                        del feed["fetch"]
-                    fetch_map = client.predict(feed=feed, fetch=fetch)
-                    result = self.postprocess(
-                        feed=request_json, fetch=fetch, fetch_map=fetch_map)
-                self.output_queue.put(result)
-            except ValueError:
-                self.output_queue.put(-1)
-
-    def _launch_web_service(self, gpu_num):
-        app_instance = Flask(__name__)
-        service_name = "/" + self.name + "/prediction"
-
-        self.input_queues = []
-        self.output_queue = Queue()
-        for i in range(gpu_num):
-            self.input_queues.append(Queue())
-
-        producer_list = []
-        for i, input_q in enumerate(self.input_queues):
-            producer_processes = Process(
-                target=self.producers,
-                args=(
-                    input_q,
-                    "0.0.0.0:{}".format(self.port + 1 + i), ))
-            producer_list.append(producer_processes)
-
-        for p in producer_list:
-            p.start()
-
-        client = Client()
-        client.load_client_config("{}/serving_server_conf.prototxt".format(
-            self.model_config))
-        client.connect(["0.0.0.0:{}".format(self.port + 1)])
-
-        self.idx = 0
-
-        @app_instance.route(service_name, methods=['POST'])
-        def get_prediction():
-            if not request.json:
-                abort(400)
-            if "fetch" not in request.json:
-                abort(400)
-
-            self.input_queues[self.idx].put(request.json)
-
-            #self.input_queues[0].put(request.json)
-            self.idx += 1
-            if self.idx >= len(self.gpus):
-                self.idx = 0
-            result = self.output_queue.get()
-            if not isinstance(result, dict) and result == -1:
-                result = {"result": "Request Value Error"}
-            return result
-
-        app_instance.run(host="0.0.0.0",
-                         port=self.port,
-                         threaded=False,
-                         processes=1)
-
-        for p in producer_list:
-            p.join()
+        endpoints = ""
+        if gpu_num > 0:
+            for i in range(gpu_num):
+                endpoints += "127.0.0.1:{},".format(self.port + i + 1)
+        else:
+            endpoints = "127.0.0.1:{}".format(self.port + 1)
+        self.client.connect([endpoints])
+
+    def get_prediction(self, request):
+        if not request.json:
+            abort(400)
+        if "fetch" not in request.json:
+            abort(400)
+        feed, fetch = self.preprocess(request.json, request.json["fetch"])
+        fetch_map_batch = self.client.predict(feed=feed, fetch=fetch)
+        fetch_map_batch = self.postprocess(
+            feed=request.json, fetch=fetch, fetch_map=fetch_map_batch)
+        result = {"result": fetch_map_batch}
+        return result
 
     def run_server(self):
         import socket
@@ -188,13 +123,6 @@ class WebService(object):
         for p in server_pros:
             p.start()
 
-        p_web = Process(
-            target=self._launch_web_service, args=(len(self.gpus), ))
-        p_web.start()
-        p_web.join()
-        for p in server_pros:
-            p.join()
-
     def preprocess(self, feed={}, fetch=[]):
         return feed, fetch
 

tools/Dockerfile

@@ -3,6 +3,9 @@ FROM centos:7.3.1611
 RUN yum -y install wget && \
     yum -y install epel-release && yum -y install patchelf && \
     yum -y install gcc make python-devel && \
+    yum -y install libSM-1.2.2-2.el7.x86_64 --setopt=protected_multilib=false && \
+    yum -y install libXrender-0.9.10-1.el7.x86_64 --setopt=protected_multilib=false && \
+    yum -y install libXext-1.3.3-3.el7.x86_64 --setopt=protected_multilib=false && \
     yum -y install python3 python3-devel && \
     yum clean all && \
     curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py && \

tools/Dockerfile.ci

@@ -2,6 +2,9 @@ FROM centos:7.3.1611
 RUN yum -y install wget >/dev/null \
     && yum -y install gcc gcc-c++ make glibc-static which >/dev/null \
     && yum -y install git openssl-devel curl-devel bzip2-devel python-devel >/dev/null \
+    && yum -y install libSM-1.2.2-2.el7.x86_64 --setopt=protected_multilib=false \
+    && yum -y install libXrender-0.9.10-1.el7.x86_64 --setopt=protected_multilib=false \
+    && yum -y install libXext-1.3.3-3.el7.x86_64 --setopt=protected_multilib=false \
     && wget https://cmake.org/files/v3.2/cmake-3.2.0-Linux-x86_64.tar.gz >/dev/null \
     && tar xzf cmake-3.2.0-Linux-x86_64.tar.gz \
     && mv cmake-3.2.0-Linux-x86_64 /usr/local/cmake3.2.0 \

tools/serving_build.sh

@@ -164,6 +164,7 @@ function python_test_fit_a_line() {
             fi
             ;;
         GPU)
+            export CUDA_VISIBLE_DEVICES=0
             # test rpc
             check_cmd "python -m paddle_serving_server_gpu.serve --model uci_housing_model --port 9393 --thread 4 --gpu_ids 0 > /dev/null &"
             sleep 5 # wait for the server to start
@@ -226,7 +227,7 @@ function python_run_criteo_ctr_with_cube() {
                 exit 1
             fi
             echo "criteo_ctr_with_cube inference auc test success"
-            ps -ef | grep "paddle_serving_server" | grep -v grep | awk '{print $2}' | xargs kill
+            kill_server_process
             ps -ef | grep "cube" | grep -v grep | awk '{print $2}' | xargs kill
             ;;
         GPU)
@@ -253,7 +254,7 @@ function python_run_criteo_ctr_with_cube() {
                 exit 1
             fi
             echo "criteo_ctr_with_cube inference auc test success"
-            ps -ef | grep "paddle_serving_server" | grep -v grep | awk '{print $2}' | xargs kill
+            kill_server_process
             ps -ef | grep "cube" | grep -v grep | awk '{print $2}' | xargs kill
             ;;
         *)
@@ -276,27 +277,48 @@ function python_test_bert() {
     case $TYPE in
         CPU)
             pip install paddlehub
-            python prepare_model.py 20
+            # Because download from paddlehub may timeout,
+            # download the model from bos(max_seq_len=128).
+            wget https://paddle-serving.bj.bcebos.com/paddle_hub_models/text/SemanticModel/bert_chinese_L-12_H-768_A-12.tar.gz
+            tar -xzf bert_chinese_L-12_H-768_A-12.tar.gz
             sh get_data.sh
-            check_cmd "python -m paddle_serving_server.serve --model bert_seq20_model/ --port 9292 &"
+            check_cmd "python -m paddle_serving_server.serve --model bert_chinese_L-12_H-768_A-12_model --port 9292 &"
             sleep 5
             pip install paddle_serving_app
-            check_cmd "head -n 10 data-c.txt | python bert_client.py --model bert_seq20_client/serving_client_conf.prototxt"
+            check_cmd "head -n 10 data-c.txt | python bert_client.py --model bert_chinese_L-12_H-768_A-12_client/serving_client_conf.prototxt"
             kill_server_process
-            ps -ef | grep "paddle_serving_server" | grep -v grep | awk '{print $2}' | xargs kill
-            ps -ef | grep "serving" | grep -v grep | awk '{print $2}' | xargs kill
+            # python prepare_model.py 20
+            # sh get_data.sh
+            # check_cmd "python -m paddle_serving_server.serve --model bert_seq20_model/ --port 9292 &"
+            # sleep 5
+            # pip install paddle_serving_app
+            # check_cmd "head -n 10 data-c.txt | python bert_client.py --model bert_seq20_client/serving_client_conf.prototxt"
+            # kill_server_process
+            # ps -ef | grep "paddle_serving_server" | grep -v grep | awk '{print $2}' | xargs kill
+            # ps -ef | grep "serving" | grep -v grep | awk '{print $2}' | xargs kill
             echo "bert RPC inference pass" 
             ;;
         GPU)
+            export CUDA_VISIBLE_DEVICES=0
             pip install paddlehub
-            python prepare_model.py 20
+            # Because download from paddlehub may timeout,
+            # download the model from bos(max_seq_len=128).
+            wget https://paddle-serving.bj.bcebos.com/paddle_hub_models/text/SemanticModel/bert_chinese_L-12_H-768_A-12.tar.gz
+            tar -xzf bert_chinese_L-12_H-768_A-12.tar.gz
             sh get_data.sh
-            check_cmd "python -m paddle_serving_server_gpu.serve --model bert_seq20_model/ --port 9292 --gpu_ids 0 &"
+            check_cmd "python -m paddle_serving_server_gpu.serve --model bert_chinese_L-12_H-768_A-12_model --port 9292 --gpu_ids 0 &"
             sleep 5
             pip install paddle_serving_app
-            check_cmd "head -n 10 data-c.txt | python bert_client.py --model bert_seq20_client/serving_client_conf.prototxt"
+            check_cmd "head -n 10 data-c.txt | python bert_client.py --model bert_chinese_L-12_H-768_A-12_client/serving_client_conf.prototxt"
             kill_server_process
-            ps -ef | grep "paddle_serving_server" | grep -v grep | awk '{print $2}' | xargs kill
+            # python prepare_model.py 20
+            # sh get_data.sh
+            # check_cmd "python -m paddle_serving_server_gpu.serve --model bert_seq20_model/ --port 9292 --gpu_ids 0 &"
+            # sleep 5
+            # pip install paddle_serving_app
+            # check_cmd "head -n 10 data-c.txt | python bert_client.py --model bert_seq20_client/serving_client_conf.prototxt"
+            # kill_server_process
+            # ps -ef | grep "paddle_serving_server" | grep -v grep | awk '{print $2}' | xargs kill
             echo "bert RPC inference pass"
             ;;
         *)
@@ -325,9 +347,10 @@ function python_test_imdb() {
             check_cmd "python text_classify_service.py imdb_cnn_model/workdir/9292 imdb.vocab &"
             sleep 5
             check_cmd "curl -H "Content-Type:application/json" -X POST -d '{"words": "i am very sad | 0", "fetch":["prediction"]}' http://127.0.0.1:9292/imdb/prediction"
+            kill_server_process
             ps -ef | grep "paddle_serving_server" | grep -v grep | awk '{print $2}' | xargs kill
             ps -ef | grep "text_classify_service.py" | grep -v grep | awk '{print $2}' | xargs kill
-            echo "imdb CPU HTTP inference pass"           
+            echo "imdb CPU HTTP inference pass"
             ;;
         GPU)
             echo "imdb ignore GPU test"
@@ -356,6 +379,7 @@ function python_test_lac() {
             check_cmd "python lac_web_service.py jieba_server_model/ lac_workdir 9292 &"
             sleep 5
             check_cmd "curl -H "Content-Type:application/json" -X POST -d '{"words": "我爱北京天安门", "fetch":["word_seg"]}' http://127.0.0.1:9292/lac/prediction"
+            kill_server_process
             ps -ef | grep "paddle_serving_server" | grep -v grep | awk '{print $2}' | xargs kill
             ps -ef | grep "lac_web_service" | grep -v grep | awk '{print $2}' | xargs kill
             echo "lac CPU HTTP inference pass"
@@ -377,7 +401,7 @@ function python_run_test() {
     python_test_fit_a_line $TYPE # pwd: /Serving/python/examples
     python_run_criteo_ctr_with_cube $TYPE # pwd: /Serving/python/examples
     python_test_bert $TYPE # pwd: /Serving/python/examples
-    python_test_imdb $TYPE 
+    python_test_imdb $TYPE # pwd: /Serving/python/examples 
     python_test_lac $TYPE    
     echo "test python $TYPE part finished as expected."
     cd ../.. # pwd: /Serving