add desc of pip mirror source && fix docker images tag

README.md

@@ -3,7 +3,7 @@
 <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">
@@ -41,6 +41,8 @@ pip install paddle-serving-client
 pip install paddle-serving-server
 ```
 
+You may need to use a domestic mirror source (in China, you can use the Tsinghua mirror source) to speed up the download.
+
 <h2 align="center">Quick Start Example</h2>
 
 ### Boston House Price Prediction model
@@ -146,7 +148,7 @@ python image_classification_service_demo.py resnet50_serving_model
 <img src='https://paddle-serving.bj.bcebos.com/imagenet-example/daisy.jpg' width = "200" height = "200">
     <br>
 <p>
-    
+
 ``` shell
 curl -H "Content-Type:application/json" -X POST -d '{"url": "https://paddle-serving.bj.bcebos.com/imagenet-example/daisy.jpg", "fetch": ["score"]}' http://127.0.0.1:9292/image/prediction
 ```

README_CN.md

@@ -3,7 +3,7 @@
 <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">
@@ -42,6 +42,8 @@ pip install paddle-serving-client
 pip install paddle-serving-server
 ```
 
+您可能需要使用国内镜像源（例如清华源）来加速下载。
+
 <h2 align="center">快速启动示例</h2>
 
 <h3 align="center">波士顿房价预测</h3>
@@ -151,7 +153,7 @@ python image_classification_service_demo.py resnet50_serving_model
 <img src='https://paddle-serving.bj.bcebos.com/imagenet-example/daisy.jpg' width = "200" height = "200">
     <br>
 <p>
-    
+
 ``` shell
 curl -H "Content-Type:application/json" -X POST -d '{"url": "https://paddle-serving.bj.bcebos.com/imagenet-example/daisy.jpg", "fetch": ["score"]}' http://127.0.0.1:9292/image/prediction
 ```

doc/ABTEST_IN_PADDLE_SERVING.md

@@ -38,7 +38,7 @@ Here, we [use docker](https://github.com/PaddlePaddle/Serving/blob/develop/doc/R
 First, start the BOW server, which enables the `8000` port:
 
 ``` shell
-docker run -dit -v $PWD/imdb_bow_model:/model -p 8000:8000 --name bow-server hub.baidubce.com/paddlepaddle/serving:0.1.3
+docker run -dit -v $PWD/imdb_bow_model:/model -p 8000:8000 --name bow-server hub.baidubce.com/paddlepaddle/serving:0.2.0
 docker exec -it bow-server bash
 pip install paddle-serving-server
 python -m paddle_serving_server.serve --model model --port 8000 >std.log 2>err.log &
@@ -48,7 +48,7 @@ exit
 Similarly, start the LSTM server, which enables the `9000` port:
 
 ```bash
-docker run -dit -v $PWD/imdb_lstm_model:/model -p 9000:9000 --name lstm-server hub.baidubce.com/paddlepaddle/serving:0.1.3
+docker run -dit -v $PWD/imdb_lstm_model:/model -p 9000:9000 --name lstm-server hub.baidubce.com/paddlepaddle/serving:0.2.0
 docker exec -it lstm-server bash
 pip install paddle-serving-server
 python -m paddle_serving_server.serve --model model --port 9000 >std.log 2>err.log &

doc/ABTEST_IN_PADDLE_SERVING_CN.md

@@ -38,9 +38,9 @@ with open('test_data/part-0') as fin:
 首先启动BOW Server，该服务启用`8000`端口：
 
 ```bash
-docker run -dit -v $PWD/imdb_bow_model:/model -p 8000:8000 --name bow-server hub.baidubce.com/paddlepaddle/serving:0.1.3
+docker run -dit -v $PWD/imdb_bow_model:/model -p 8000:8000 --name bow-server hub.baidubce.com/paddlepaddle/serving:0.2.0
 docker exec -it bow-server bash
-pip install paddle-serving-server
+pip install paddle-serving-server -i https://pypi.tuna.tsinghua.edu.cn/simple
 python -m paddle_serving_server.serve --model model --port 8000 >std.log 2>err.log &
 exit
 ```
@@ -48,9 +48,9 @@ exit
 同理启动LSTM Server，该服务启用`9000`端口：
 
 ```bash
-docker run -dit -v $PWD/imdb_lstm_model:/model -p 9000:9000 --name lstm-server hub.baidubce.com/paddlepaddle/serving:0.1.3
+docker run -dit -v $PWD/imdb_lstm_model:/model -p 9000:9000 --name lstm-server hub.baidubce.com/paddlepaddle/serving:0.2.0
 docker exec -it lstm-server bash
-pip install paddle-serving-server
+pip install paddle-serving-server -i https://pypi.tuna.tsinghua.edu.cn/simple
 python -m paddle_serving_server.serve --model model --port 9000 >std.log 2>err.log &
 exit
 ```

doc/IMDB_GO_CLIENT_CN.md

@@ -11,7 +11,7 @@
 ```shell
 go get github.com/PaddlePaddle/Serving/go/serving_client
 go get github.com/PaddlePaddle/Serving/go/proto
-pip install paddle-serving-server
+pip install paddle-serving-server -i https://pypi.tuna.tsinghua.edu.cn/simple
 ```
 ### 下载文本分类模型
 

doc/RUN_IN_DOCKER.md

@@ -15,7 +15,7 @@ You can get images in two ways:
 1. Pull image directly
 
    ```bash
-   docker pull hub.baidubce.com/paddlepaddle/serving:0.1.3
+   docker pull hub.baidubce.com/paddlepaddle/serving:0.2.0
    ```
 
 2. Building image based on dockerfile
@@ -23,13 +23,13 @@ You can get images in two ways:
    Create a new folder and copy [Dockerfile](../tools/Dockerfile) to this folder, and run the following command:
 
    ```bash
-   docker build -t hub.baidubce.com/paddlepaddle/serving:0.1.3 .
+   docker build -t hub.baidubce.com/paddlepaddle/serving:0.2.0 .
    ```
 
 ### Create container
 
 ```bash
-docker run -p 9292:9292 --name test -dit hub.baidubce.com/paddlepaddle/serving:0.1.3
+docker run -p 9292:9292 --name test -dit hub.baidubce.com/paddlepaddle/serving:0.2.0
 docker exec -it test bash
 ```
 
@@ -37,12 +37,18 @@ The `-p` option is to map the `9292` port of the container to the `9292` port of
 
 ### Install PaddleServing
 
-In order to make the image smaller, the PaddleServing package is not installed in the image. You can run the following command to install it
+In order to make the image smaller, the PaddleServing package is not installed in the image. You can run the following command to install it:
 
 ```bash
 pip install paddle-serving-server
 ```
 
+You may need to use a domestic mirror source (in China, you can use the Tsinghua mirror source of the following example) to speed up the download:
+
+```shell
+pip install paddle-serving-server -i https://pypi.tuna.tsinghua.edu.cn/simple
+```
+
 ### Test example
 
 Before running the GPU version of the Server side code, you need to set the `CUDA_VISIBLE_DEVICES` environment variable to specify which GPUs the prediction service uses. The following example specifies two GPUs with indexes 0 and 1:
@@ -107,7 +113,7 @@ You can also get images in two ways:
 1. Pull image directly
 
    ```bash
-   nvidia-docker pull hub.baidubce.com/paddlepaddle/serving:0.1.3-gpu
+   nvidia-docker pull hub.baidubce.com/paddlepaddle/serving:0.2.0-gpu
    ```
 
 2. Building image based on dockerfile
@@ -115,13 +121,13 @@ You can also get images in two ways:
    Create a new folder and copy [Dockerfile.gpu](../tools/Dockerfile.gpu) to this folder, and run the following command:
 
    ```bash
-   nvidia-docker build -t hub.baidubce.com/paddlepaddle/serving:0.1.3-gpu .
+   nvidia-docker build -t hub.baidubce.com/paddlepaddle/serving:0.2.0-gpu .
    ```
 
 ### Create container
 
 ```bash
-nvidia-docker run -p 9292:9292 --name test -dit hub.baidubce.com/paddlepaddle/serving:0.1.3-gpu
+nvidia-docker run -p 9292:9292 --name test -dit hub.baidubce.com/paddlepaddle/serving:0.2.0-gpu
 nvidia-docker exec -it test bash
 ```
 
@@ -135,6 +141,12 @@ In order to make the image smaller, the PaddleServing package is not installed i
 pip install paddle-serving-server-gpu
 ```
 
+You may need to use a domestic mirror source (in China, you can use the Tsinghua mirror source of the following example) to speed up the download:
+
+```shell
+pip install paddle-serving-server -i https://pypi.tuna.tsinghua.edu.cn/simple
+```
+
 ### Test example
 
 When running the GPU Server, you need to set the GPUs used by the prediction service through the `--gpu_ids` option, and the CPU is used by default. An error will be reported when the value of `--gpu_ids` exceeds the environment variable `CUDA_VISIBLE_DEVICES`. The following example specifies to use a GPU with index 0:

doc/RUN_IN_DOCKER_CN.md

@@ -15,7 +15,7 @@ Docker（GPU版本需要在GPU机器上安装nvidia-docker）
 1. 直接拉取镜像
 
    ```bash
-   docker pull hub.baidubce.com/paddlepaddle/serving:0.1.3
+   docker pull hub.baidubce.com/paddlepaddle/serving:0.2.0
    ```
 
 2. 基于Dockerfile构建镜像
@@ -23,13 +23,13 @@ Docker（GPU版本需要在GPU机器上安装nvidia-docker）
    建立新目录，复制[Dockerfile](../tools/Dockerfile)内容到该目录下Dockerfile文件。执行
 
    ```bash
-   docker build -t hub.baidubce.com/paddlepaddle/serving:0.1.3 .
+   docker build -t hub.baidubce.com/paddlepaddle/serving:0.2.0 .
    ```
 
 ### 创建容器并进入
 
 ```bash
-docker run -p 9292:9292 --name test -dit hub.baidubce.com/paddlepaddle/serving:0.1.3
+docker run -p 9292:9292 --name test -dit hub.baidubce.com/paddlepaddle/serving:0.2.0
 docker exec -it test bash
 ```
 
@@ -37,12 +37,18 @@ docker exec -it test bash
 
 ### 安装PaddleServing
 
-为了减小镜像的体积，镜像中没有安装Serving包，要执行下面命令进行安装
+为了减小镜像的体积，镜像中没有安装Serving包，要执行下面命令进行安装。
 
 ```bash
 pip install paddle-serving-server
 ```
 
+您可能需要使用国内镜像源（例如清华源）来加速下载。
+
+```shell
+pip install paddle-serving-server -i https://pypi.tuna.tsinghua.edu.cn/simple
+```
+
 ### 测试example
 
 通过下面命令获取训练好的Boston房价预估模型：
@@ -99,7 +105,7 @@ GPU版本与CPU版本基本一致，只有部分接口命名的差别（GPU版
 1. 直接拉取镜像
 
    ```bash
-   nvidia-docker pull hub.baidubce.com/paddlepaddle/serving:0.1.3-gpu
+   nvidia-docker pull hub.baidubce.com/paddlepaddle/serving:0.2.0-gpu
    ```
 
 2. 基于Dockerfile构建镜像
@@ -107,13 +113,13 @@ GPU版本与CPU版本基本一致，只有部分接口命名的差别（GPU版
    建立新目录，复制[Dockerfile.gpu](../tools/Dockerfile.gpu)内容到该目录下Dockerfile文件。执行
 
    ```bash
-   nvidia-docker build -t hub.baidubce.com/paddlepaddle/serving:0.1.3-gpu .
+   nvidia-docker build -t hub.baidubce.com/paddlepaddle/serving:0.2.0-gpu .
    ```
 
 ### 创建容器并进入
 
 ```bash
-nvidia-docker run -p 9292:9292 --name test -dit hub.baidubce.com/paddlepaddle/serving:0.1.3-gpu
+nvidia-docker run -p 9292:9292 --name test -dit hub.baidubce.com/paddlepaddle/serving:0.2.0-gpu
 nvidia-docker exec -it test bash
 ```
 
@@ -121,12 +127,18 @@ nvidia-docker exec -it test bash
 
 ### 安装PaddleServing
 
-为了减小镜像的体积，镜像中没有安装Serving包，要执行下面命令进行安装
+为了减小镜像的体积，镜像中没有安装Serving包，要执行下面命令进行安装。
 
 ```bash
 pip install paddle-serving-server-gpu
 ```
 
+您可能需要使用国内镜像源（例如清华源）来加速下载。
+
+```shell
+pip install paddle-serving-server -i https://pypi.tuna.tsinghua.edu.cn/simple
+```
+
 ### 测试example
 
 在运行GPU版Server时需要通过`--gpu_ids`选项设置预测服务使用的GPU，缺省状态默认使用CPU。当设置的`--gpu_ids`超出环境变量`CUDA_VISIBLE_DEVICES`时会报错。下面的示例为指定使用索引为0的GPU：