Merge branch 'develop' into add_0.7

83967751 · Thomas Young · GitHub · 7df3401f · ce441d92 · 83967751
19 changed file
--- a/doc/DOCKER_IMAGES.md
+++ b/doc/DOCKER_IMAGES.md
@@ -37,7 +37,7 @@ If you want to customize your Serving based on source code, use the version with
 |              GPU (cuda10.1-cudnn7-tensorRT6-gcc54) development               | Ubuntu16 | latest-cuda10.1-cudnn7-gcc54-devel(not ready) | [Dockerfile.cuda10.1-cudnn7-gcc54.devel](../tools/Dockerfile.cuda10.1-cudnn7-gcc54.devel) |
 |              GPU (cuda10.1-cudnn7-tensorRT6) development               | Ubuntu16 | latest-cuda10.1-cudnn7-devel | [Dockerfile.cuda10.1-cudnn7.devel](../tools/Dockerfile.cuda10.1-cudnn7.devel) |
 |              GPU (cuda10.2-cudnn8-tensorRT7) development               | Ubuntu16 | latest-cuda10.2-cudnn8-devel | [Dockerfile.cuda10.2-cudnn8.devel](../tools/Dockerfile.cuda10.2-cudnn8.devel) |
-|              GPU (cuda11-cudnn8-tensorRT7) development               | Ubuntu18 | latest-cuda11-cudnn8-devel | [Dockerfile.cuda11-cudnn8.devel](../tools/Dockerfile.cuda11-cudnn8.devel) |
+|              GPU (cuda11.2-cudnn8-tensorRT7) development               | Ubuntu18 | latest-cuda11.2-cudnn8-devel | [Dockerfile.cuda11.2-cudnn8.devel](../tools/Dockerfile.cuda11.2-cudnn8.devel) |

 **Java Client:**
 ```

--- a/doc/HTTP_SERVICE_CN.md
+++ b/doc/HTTP_SERVICE_CN.md
@@ -48,7 +48,7 @@ python3.6 -m paddle_serving_server.serve --model uci_housing_model --thread 10 -

 Python的HttpClient使用示例见[`python/examples/fit_a_line/test_httpclient.py`](../python/examples/fit_a_line/test_httpclient.py)，接口详见[`python/paddle_serving_client/httpclient.py`](../python/paddle_serving_client/httpclient.py)。

-Java的HttpClient使用示例见[`java/examples/src/main/java/PaddleServingClientExample.java`](../java/examples/src/main/java/PaddleServingClientExample.java)接口详见[`java/src/main/java/io/paddle/serving/client/HttpClient.java`](../java/src/main/java/io/paddle/serving/client/HttpClient.java)。
+Java的HttpClient使用示例见[`java/examples/src/main/java/PaddleServingClientExample.java`](../java/examples/src/main/java/PaddleServingClientExample.java)接口详见[`java/src/main/java/io/paddle/serving/client/Client.java`](../java/src/main/java/io/paddle/serving/client/Client.java)。

 如果不能满足您的需求，您也可以在此基础上添加一些功能。


--- a/doc/model_zoo.md
+++ b/doc/model_zoo.md
+# Model Zoo
+
+本页面展示了Paddle Serving目前支持的预训练模型以及下载链接
+若您想为Paddle Serving提供新的模型，可通过[pull requese](https://github.com/PaddlePaddle/Serving/pulls)提交PR
+
+*特别感谢[PadddlePaddle 全链条](https://www.paddlepaddle.org.cn/wholechain)以及[PaddleHub](https://www.paddlepaddle.org.cn/hub)为Paddle Serving提供的部分预训练模型*
+
+
+| Model | Type | Dataset | Size | Download | Sample Input| Model mode |
+| --- | --- | --- | --- | --- | --- | --- |
+| ResNet_V2_50 | PaddleClas | ImageNet | 90.78 MB | [.tar.gz](https://paddle-serving.bj.bcebos.com/paddle_hub_models/image/ImageClassification/resnet_v2_50_imagenet.tar.gz) | [daisy.jpg](../examples/PaddleClas/resnet_v2_50/daisy.jpg) |Eager|
+| MobileNet_v2 | PaddleClas | ImageNet | 8.06 MB | [.tar.gz](https://paddle-serving.bj.bcebos.com/paddle_hub_models/image/ImageClassification/mobilenet_v2_imagenet.tar.gz) | [daisy.jpg](../examples/PaddleClas/mobilenet/daisy.jpg) |Eager|
+| Bert | PaddleNLP | zhwiki | 361.96 MB | [.tar.gz](https://paddle-serving.bj.bcebos.com/paddle_hub_models/text/SemanticModel/bert_chinese_L-12_H-768_A-12.tar.gz) | [data-c.txt](../examples/PaddleNLP/data-c.txt) |Eager|
+| Senta | PaddleNLP | Baidu | 578.37 MB | [.tar.gz](https://paddle-serving.bj.bcebos.com/paddle_hub_models/text/SentimentAnalysis/senta_bilstm.tar.gz) |  |Eager|
+| Squeezenet 1_1 | Image Classification | ImageNet | 4.4 MB | [.mar](https://torchserve.pytorch.org/mar_files/squeezenet1_1.mar) | [kitten.jpg](../examples/image_classifier/kitten.jpg) |Eager|
+| MNIST digit classifier | Image Classification | MNIST | 4.3 MB | [.mar](https://torchserve.pytorch.org/mar_files/mnist_v2.mar) | [0.png](../examples/image_classifier/mnist/test_data/0.png) |Eager|
+| Resnet 152 |Image Classification | ImageNet | 214 MB | [.mar](https://torchserve.pytorch.org/mar_files/resnet-152-batch_v2.mar) | [kitten.jpg](../examples/image_classifier/kitten.jpg) |Eager|
+| Faster RCNN | Object Detection | COCO | 148 MB | [.mar](https://torchserve.pytorch.org/mar_files/fastrcnn.mar) | [persons.jpg](../examples/object_detector/persons.jpg) |Eager|
+| MASK RCNN | Object Detection | COCO | 158 MB | [.mar](https://torchserve.pytorch.org/mar_files/maskrcnn.mar) | [persons.jpg](../examples/object_detector/persons.jpg) |Eager|
+| Text classifier | Text Classification | AG_NEWS | 169 MB | [.mar](https://torchserve.pytorch.org/mar_files/my_text_classifier_v4.mar) | [sample_text.txt](../examples/text_classification/sample_text.txt) |Eager|
+| FCN ResNet 101 | Image Segmentation | COCO | 193 MB | [.mar](https://torchserve.pytorch.org/mar_files/fcn_resnet_101.mar) | [persons.jpg](../examples/image_segmenter/persons.jpg) |Eager|
+| DeepLabV3 ResNet 101 | Image Segmentation | COCO | 217 MB | [.mar](https://torchserve.pytorch.org/mar_files/deeplabv3_resnet_101_eager.mar) | [persons.jpg](https://github.com/pytorch/serve/blob/master/examples/image_segmenter/persons.jpg) |Eager|
+| AlexNet Scripted | Image Classification | ImageNet | 216 MB | [.mar](https://torchserve.pytorch.org/mar_files/alexnet_scripted.mar) | [kitten.jpg](../examples/image_classifier/kitten.jpg) |Torchscripted |
+| Densenet161 Scripted| Image Classification | ImageNet | 105 MB | [.mar](https://torchserve.pytorch.org/mar_files/densenet161_scripted.mar) | [kitten.jpg](../examples/image_classifier/kitten.jpg) |Torchscripted |
+| Resnet18 Scripted| Image Classification | ImageNet | 42 MB | [.mar](https://torchserve.pytorch.org/mar_files/resnet-18_scripted.mar) | [kitten.jpg](../examples/image_classifier/kitten.jpg) |Torchscripted |
+| VGG16 Scripted| Image Classification | ImageNet | 489 MB | [.mar](https://torchserve.pytorch.org/mar_files/vgg16_scripted.mar) | [kitten.jpg](../examples/image_classifier/kitten.jpg) |Torchscripted |
+| Squeezenet 1_1 Scripted | Image Classification | ImageNet | 4.4 MB | [.mar](https://torchserve.pytorch.org/mar_files/squeezenet1_1_scripted.mar) | [kitten.jpg](../examples/image_classifier/kitten.jpg) |Torchscripted |
+| MNIST digit classifier Scripted | Image Classification | MNIST | 4.3 MB | [.mar](https://torchserve.pytorch.org/mar_files/mnist_scripted_v2.mar) | [0.png](../examples/image_classifier/mnist/test_data/0.png) |Torchscripted |
+| Resnet 152 Scripted |Image Classification | ImageNet | 215 MB | [.mar](https://torchserve.pytorch.org/mar_files/resnet-152-scripted_v2.mar) | [kitten.jpg](../examples/image_classifier/kitten.jpg) |Torchscripted |
+| Text classifier Scripted | Text Classification | AG_NEWS | 169 MB | [.mar](https://torchserve.pytorch.org/mar_files/my_text_classifier_scripted_v3.mar) | [sample_text.txt](../examples/text_classification/sample_text.txt) |Torchscripted |
+| FCN ResNet 101 Scripted | Image Segmentation | COCO | 193 MB | [.mar](https://torchserve.pytorch.org/mar_files/fcn_resnet_101_scripted.mar) | [persons.jpg](../examples/image_segmenter/persons.jpg) |Torchscripted |
+| DeepLabV3 ResNet 101 Scripted | Image Segmentation | COCO | 217 MB | [.mar](https://torchserve.pytorch.org/mar_files/deeplabv3_resnet_101_scripted.mar) | [persons.jpg](https://github.com/pytorch/serve/blob/master/examples/image_segmenter/persons.jpg) |Torchscripted |
+
+Refer [example](../examples) for more details on above models.
--- a/python/examples/detection/README.md
+++ b/python/examples/detection/README.md
@@ -4,11 +4,11 @@

 ### Introduction

-PaddleDetection flying paddle target detection development kit is designed to help developers complete the whole development process of detection model formation, training, optimization and deployment faster and better. For details, see [Github](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph)
+PaddleDetection flying paddle target detection development kit is designed to help developers complete the whole development process of detection model formation, training, optimization and deployment faster and better. For details, see [Github](https://github.com/PaddlePaddle/PaddleDetection/tree/master)

 This article mainly introduces the deployment of Paddle Detection's dynamic graph model on Serving.

-Paddle Detection provides a large number of [Model Zoo](https://github.com/PaddlePaddle/PaddleDetection/blob/master/dygraph/docs/MODEL_ZOO_cn.md), these model libraries can be used in Paddle Serving with export tools Model. For the export tutorial, please refer to [Paddle Detection Export Model Tutorial (Simplified Chinese)](https://github.com/PaddlePaddle/PaddleDetection/blob/master/dygraph/deploy/EXPORT_MODEL.md).
+Paddle Detection provides a large number of [Model Zoo](https://github.com/PaddlePaddle/PaddleDetection/blob/master/docs/MODEL_ZOO_cn.md), these model libraries can be used in Paddle Serving with export tools Model. For the export tutorial, please refer to [Paddle Detection Export Model Tutorial (Simplified Chinese)](https://github.com/PaddlePaddle/PaddleDetection/blob/master/deploy/EXPORT_MODEL.md).

 ### Serving example
 Several examples of PaddleDetection models used in Serving are given in this folder

--- a/python/examples/detection/README_CN.md
+++ b/python/examples/detection/README_CN.md
@@ -4,13 +4,13 @@

 ### 简介

-PaddleDetection飞桨目标检测开发套件，旨在帮助开发者更快更好地完成检测模型的组建、训练、优化及部署等全开发流程。详情参见[Github](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph)
+PaddleDetection飞桨目标检测开发套件，旨在帮助开发者更快更好地完成检测模型的组建、训练、优化及部署等全开发流程。详情参见[Github](https://github.com/PaddlePaddle/PaddleDetection/tree/master)

 本文主要是介绍Paddle Detection的动态图模型在Serving上的部署。

 ### 导出模型

-Paddle Detection提供了大量的[模型库](https://github.com/PaddlePaddle/PaddleDetection/blob/master/dygraph/docs/MODEL_ZOO_cn.md), 这些模型库配合导出工具都可以得到可以用于Paddle Serving的模型。导出教程参见[Paddle Detection模型导出教程](https://github.com/PaddlePaddle/PaddleDetection/blob/master/dygraph/deploy/EXPORT_MODEL.md)。
+Paddle Detection提供了大量的[模型库](https://github.com/PaddlePaddle/PaddleDetection/blob/master/docs/MODEL_ZOO_cn.md), 这些模型库配合导出工具都可以得到可以用于Paddle Serving的模型。导出教程参见[Paddle Detection模型导出教程](https://github.com/PaddlePaddle/PaddleDetection/blob/master/deploy/EXPORT_MODEL.md)。

 ### Serving示例
 本文件夹下给出了多个PaddleDetection模型用于Serving的范例

--- a/python/examples/pipeline/PaddleDetection/faster_rcnn/config.yml
+++ b/python/examples/pipeline/PaddleDetection/faster_rcnn/config.yml
 dag:
+  #op资源类型, True, 为线程模型；False，为进程模型
  is_thread_op: false
+  #使用性能分析, True，生成Timeline性能数据，对性能有一定影响；False为不使用
  tracer:
    interval_s: 30
+#http端口, rpc_port和http_port不允许同时为空。当rpc_port可用且http_port为空时，不自动生成http_port
 http_port: 18082
 op:
  faster_rcnn:
+    #并发数，is_thread_op=True时，为线程并发；否则为进程并发
    concurrency: 2
-
    local_service_conf:
+      #client类型，包括brpc, grpc和local_predictor.local_predictor不启动Serving服务，进程内预测
      client_type: local_predictor
+      # device_type, 0=cpu, 1=gpu, 2=tensorRT, 3=arm cpu, 4=kunlun xpu
      device_type: 1
+      #计算硬件ID，当devices为""或不写时为CPU预测；当devices为"0", "0,1,2"时为GPU预测，表示使用的GPU卡
      devices: '2'
+      #Fetch结果列表，以bert_seq128_model中fetch_var的alias_name为准, 如果没有设置则全部返回
      fetch_list:
      - save_infer_model/scale_0.tmp_1
+      #模型路径
      model_config: serving_server/
+#rpc端口, rpc_port和http_port不允许同时为空。当rpc_port为空且http_port不为空时，会自动将rpc_port设置为http_port+1
 rpc_port: 9998
+#worker_num, 最大并发数。当build_dag_each_worker=True时, 框架会创建worker_num个进程，每个进程内构建grpcSever和DAG
+#当build_dag_each_worker=False时，框架会设置主线程grpc线程池的max_workers=worker_num
 worker_num: 20
--- a/python/examples/pipeline/PaddleDetection/ppyolo_mbv3/README_CN.md
+++ b/python/examples/pipeline/PaddleDetection/ppyolo_mbv3/README_CN.md
+# PPYOLO model on Pipeline Paddle Serving
+
+(简体中文|[English](./README_CN.md))
+
+### 获取模型
+```
+wget --no-check-certificate https://paddle-serving.bj.bcebos.com/pddet_demo/2.0/ppyolo_mbv3_large_coco.tar
+```
+
+### 启动服务
+```
+tar xf ppyolo_mbv3_large_coco.tar
+python3 web_service.py
+```
+
+### 执行预测
+```
+python3 pipeline_http_client.py
+```
--- a/python/examples/pipeline/PaddleDetection/ppyolo_mbv3/config.yml
+++ b/python/examples/pipeline/PaddleDetection/ppyolo_mbv3/config.yml
 dag:
+  #op资源类型, True, 为线程模型；False，为进程模型
  is_thread_op: false
+  #使用性能分析, True，生成Timeline性能数据，对性能有一定影响；False为不使用
  tracer:
    interval_s: 30
+#http端口, rpc_port和http_port不允许同时为空。当rpc_port可用且http_port为空时，不自动生成http_port
 http_port: 18082
 op:
  ppyolo_mbv3:
+    #并发数，is_thread_op=True时，为线程并发；否则为进程并发
    concurrency: 10

    local_service_conf:
+      #client类型，包括brpc, grpc和local_predictor.local_predictor不启动Serving服务，进程内预测
      client_type: local_predictor
+      # device_type, 0=cpu, 1=gpu, 2=tensorRT, 3=arm cpu, 4=kunlun xpu
      device_type: 1
+      #计算硬件ID，当devices为""或不写时为CPU预测；当devices为"0", "0,1,2"时为GPU预测，表示使用的GPU卡
      devices: '2'
+      #Fetch结果列表，以bert_seq128_model中fetch_var的alias_name为准, 如果没有设置则全部返回
      fetch_list:
      - save_infer_model/scale_0.tmp_1
+      #模型路径
      model_config: serving_server/
+#rpc端口, rpc_port和http_port不允许同时为空。当rpc_port为空且http_port不为空时，会自动将rpc_port设置为http_port+1
 rpc_port: 9998
+#worker_num, 最大并发数。当build_dag_each_worker=True时, 框架会创建worker_num个进程，每个进程内构建grpcSever和DAG
+#当build_dag_each_worker=False时，框架会设置主线程grpc线程池的max_workers=worker_num
 worker_num: 20
--- a/python/examples/pipeline/PaddleDetection/yolov3/README_CN.md
+++ b/python/examples/pipeline/PaddleDetection/yolov3/README_CN.md
+# YOLOv3 model on Pipeline Paddle Serving
+
+(简体中文|[English](./README.md))
+
+### 获取模型
+```
+wget --no-check-certificate https://paddle-serving.bj.bcebos.com/pddet_demo/2.0/yolov3_darknet53_270e_coco.tar
+```
+
+### 启动 WebService
+```
+tar xf yolov3_darknet53_270e_coco.tar
+python3 web_service.py
+```
+
+### 执行预测
+```
+python3 pipeline_http_client.py
+```
--- a/python/examples/pipeline/PaddleDetection/yolov3/config.yml
+++ b/python/examples/pipeline/PaddleDetection/yolov3/config.yml
 dag:
+  #op资源类型, True, 为线程模型；False，为进程模型
  is_thread_op: false
+  #使用性能分析, True，生成Timeline性能数据，对性能有一定影响；False为不使用
  tracer:
    interval_s: 30
+#http端口, rpc_port和http_port不允许同时为空。当rpc_port可用且http_port为空时，不自动生成http_port
 http_port: 18082
 op:
  yolov3:
+    #并发数，is_thread_op=True时，为线程并发；否则为进程并发
    concurrency: 10
-
    local_service_conf:
+      #client类型，包括brpc, grpc和local_predictor.local_predictor不启动Serving服务，进程内预测
      client_type: local_predictor
+      # device_type, 0=cpu, 1=gpu, 2=tensorRT, 3=arm cpu, 4=kunlun xpu
      device_type: 1
+      #计算硬件ID，当devices为""或不写时为CPU预测；当devices为"0", "0,1,2"时为GPU预测，表示使用的GPU卡
      devices: '2'
+      #Fetch结果列表，以bert_seq128_model中fetch_var的alias_name为准, 如果没有设置则全部返回
      fetch_list:
      - save_infer_model/scale_0.tmp_1
+      #模型路径
      model_config: serving_server/
+#rpc端口, rpc_port和http_port不允许同时为空。当rpc_port为空且http_port不为空时，会自动将rpc_port设置为http_port+1
 rpc_port: 9998
+#worker_num, 最大并发数。当build_dag_each_worker=True时, 框架会创建worker_num个进程，每个进程内构建grpcSever和DAG
+#当build_dag_each_worker=False时，框架会设置主线程grpc线程池的max_workers=worker_num
 worker_num: 20
--- a/python/examples/pipeline/bert/config.yml
+++ b/python/examples/pipeline/bert/config.yml
+#worker_num, 最大并发数。当build_dag_each_worker=True时, 框架会创建worker_num个进程，每个进程内构建grpcSever和DAG
+##当build_dag_each_worker=False时，框架会设置主线程grpc线程池的max_workers=worker_num
 worker_num: 20
+#build_dag_each_worker, False，框架在进程内创建一条DAG；True，框架会每个进程内创建多个独立的DAG
+build_dag_each_worker: false
+
 dag:
+  #op资源类型, True, 为线程模型；False，为进程模型
  is_thread_op: false
+  #使用性能分析, True，生成Timeline性能数据，对性能有一定影响；False为不使用
  tracer:
    interval_s: 10
+#http端口, rpc_port和http_port不允许同时为空。当rpc_port可用且http_port为空时，不自动生成http_port
 http_port: 18082
+#rpc端口, rpc_port和http_port不允许同时为空。当rpc_port为空且http_port不为空时，会自动将rpc_port设置为http_port+1
 rpc_port: 9998
 op:
  bert:
+    #并发数，is_thread_op=True时，为线程并发；否则为进程并发
    concurrency: 2
-
+    #当op配置没有server_endpoints时，从local_service_conf读取本地服务配置
    local_service_conf:
+      #client类型，包括brpc, grpc和local_predictor.local_predictor不启动Serving服务，进程内预测
      client_type: local_predictor
+      # device_type, 0=cpu, 1=gpu, 2=tensorRT, 3=arm cpu, 4=kunlun xpu
      device_type: 1
+      #计算硬件ID，当devices为""或不写时为CPU预测；当devices为"0", "0,1,2"时为GPU预测，表示使用的GPU卡
      devices: '2'
+      #Fetch结果列表，以bert_seq128_model中fetch_var的alias_name为准, 如果没有设置则全部返回
      fetch_list:
+      #bert模型路径
      model_config: bert_seq128_model/
--- a/python/examples/pipeline/ocr/config.yml
+++ b/python/examples/pipeline/ocr/config.yml
@@ -38,6 +38,9 @@ op:

            #Fetch结果列表，以client_config中fetch_var的alias_name为准
            fetch_list: ["concat_1.tmp_0"]
+            
+            # device_type, 0=cpu, 1=gpu, 2=tensorRT, 3=arm cpu, 4=kunlun xpu
+            device_type: 0

            #计算硬件ID，当devices为""或不写时为CPU预测；当devices为"0", "0,1,2"时为GPU预测，表示使用的GPU卡
            devices: ""
@@ -71,6 +74,8 @@ op:

            #Fetch结果列表，以client_config中fetch_var的alias_name为准
            fetch_list: ["ctc_greedy_decoder_0.tmp_0", "softmax_0.tmp_0"] 
+            # device_type, 0=cpu, 1=gpu, 2=tensorRT, 3=arm cpu, 4=kunlun xpu
+            device_type: 0

            #计算硬件ID，当devices为""或不写时为CPU预测；当devices为"0", "0,1,2"时为GPU预测，表示使用的GPU卡
            devices: ""

--- a/python/paddle_serving_app/README.md
+++ b/python/paddle_serving_app/README.md
@@ -67,7 +67,7 @@ Preprocessing for Chinese word segmentation task.
    - words（st ）：Original text input.
    - crf_decode（np.array）：CRF code predicted by model.

-  [example](../examples/lac/lac_web_service.py)
+  [example](../examples/lac/lac_http_client.py)

 - class SentaReader


--- a/python/paddle_serving_app/README_CN.md
+++ b/python/paddle_serving_app/README_CN.md
@@ -60,7 +60,7 @@ paddle_serving_app针对CV和NLP领域的模型任务，提供了多种常见的
    - words（str）：原始文本
    - crf_decode（np.array）：模型预测结果中的CRF编码

-  [参考示例](../examples/lac/lac_web_service.py)
+  [参考示例](../examples/lac/lac_http_client.py)

 - class SentaReader


--- a/tools/Dockerfile.cuda10.1-cudnn7.devel
+++ b/tools/Dockerfile.cuda10.1-cudnn7.devel
@@ -83,7 +83,7 @@ RUN ln -sf /usr/local/bin/python3.6 /usr/local/bin/python3 && ln -sf /usr/local/
 RUN rm -r /root/python_build

 # Install Go and glide
-RUN wget -qO- https://dl.google.com/go/go1.14.linux-amd64.tar.gz | \
+RUN wget -qO- https://paddle-ci.cdn.bcebos.com/go1.17.2.linux-amd64.tar.gz | \
    tar -xz -C /usr/local && \
    mkdir /root/go && \
    mkdir /root/go/bin && \

--- a/tools/Dockerfile.cuda10.2-cudnn7.devel
+++ b/tools/Dockerfile.cuda10.2-cudnn7.devel
@@ -83,7 +83,7 @@ RUN ln -sf /usr/local/bin/python3.6 /usr/local/bin/python3 && ln -sf /usr/local/
 RUN rm -r /root/python_build

 # Install Go and glide
-RUN wget -qO- https://dl.google.com/go/go1.14.linux-amd64.tar.gz | \
+RUN wget -qO- https://paddle-ci.cdn.bcebos.com/go1.17.2.linux-amd64.tar.gz | \
    tar -xz -C /usr/local && \
    mkdir /root/go && \
    mkdir /root/go/bin && \

--- a/tools/Dockerfile.cuda10.2-cudnn8.devel
+++ b/tools/Dockerfile.cuda10.2-cudnn8.devel
@@ -83,7 +83,7 @@ RUN ln -sf /usr/local/bin/python3.6 /usr/local/bin/python3 && ln -sf /usr/local/
 RUN rm -r /root/python_build

 # Install Go and glide
-RUN wget -qO- https://dl.google.com/go/go1.14.linux-amd64.tar.gz | \
+RUN wget -qO- https://paddle-ci.cdn.bcebos.com/go1.17.2.linux-amd64.tar.gz | \
    tar -xz -C /usr/local && \
    mkdir /root/go && \
    mkdir /root/go/bin && \

--- a/tools/Dockerfile.cuda11.2-cudnn8.devel
+++ b/tools/Dockerfile.cuda11.2-cudnn8.devel
+# A image for building paddle binaries
+# Use cuda devel base image for both cpu and gpu environment
+# When you modify it, please be aware of cudnn-runtime version
+FROM nvidia/cuda:11.2.0-cudnn8-devel-ubuntu16.04
+MAINTAINER PaddlePaddle Authors <paddle-dev@baidu.com>
+
+# ENV variables
+ARG WITH_GPU
+ARG WITH_AVX
+
+ENV WITH_GPU=${WITH_GPU:-ON}
+ENV WITH_AVX=${WITH_AVX:-ON}
+
+ENV HOME /root
+# Add bash enhancements
+COPY tools/dockerfiles/root/ /root/
+
+# Prepare packages for Python
+RUN apt-get update && \
+    apt-get install -y make build-essential libssl-dev zlib1g-dev libbz2-dev \
+    libreadline-dev libsqlite3-dev wget curl llvm libncurses5-dev libncursesw5-dev \
+    xz-utils tk-dev libffi-dev liblzma-dev
+
+RUN apt-get update && \
+    apt-get install -y --allow-downgrades --allow-change-held-packages \
+    patchelf git python-pip python-dev python-opencv openssh-server bison \
+    wget unzip unrar tar xz-utils bzip2 gzip coreutils ntp \
+    curl sed grep graphviz libjpeg-dev zlib1g-dev  \
+    python-matplotlib unzip \
+    automake locales clang-format swig  \
+    liblapack-dev liblapacke-dev libcurl4-openssl-dev \
+    net-tools libtool module-init-tools vim && \
+    apt-get clean -y
+
+RUN ln -s /usr/lib/x86_64-linux-gnu/libssl.so /usr/lib/libssl.so.10 && \
+    ln -s /usr/lib/x86_64-linux-gnu/libcrypto.so /usr/lib/libcrypto.so.10
+
+RUN wget https://github.com/koalaman/shellcheck/releases/download/v0.7.1/shellcheck-v0.7.1.linux.x86_64.tar.xz -O shellcheck-v0.7.1.linux.x86_64.tar.xz && \
+    tar -xf shellcheck-v0.7.1.linux.x86_64.tar.xz && cp  shellcheck-v0.7.1/shellcheck /usr/bin/shellcheck && \
+    rm -rf shellcheck-v0.7.1.linux.x86_64.tar.xz shellcheck-v0.7.1
+
+# Downgrade gcc&&g++
+WORKDIR /usr/bin 
+      COPY tools/dockerfiles/build_scripts /build_scripts 
+      RUN bash /build_scripts/install_gcc.sh gcc82 && rm -rf /build_scripts 
+      RUN cp gcc gcc.bak && cp g++ g++.bak && rm gcc && rm g++ 
+      RUN ln -s /usr/local/gcc-8.2/bin/gcc /usr/local/bin/gcc 
+      RUN ln -s /usr/local/gcc-8.2/bin/g++ /usr/local/bin/g++ 
+      RUN ln -s /usr/local/gcc-8.2/bin/gcc /usr/bin/gcc 
+      RUN ln -s /usr/local/gcc-8.2/bin/g++ /usr/bin/g++ 
+      ENV PATH=/usr/local/gcc-8.2/bin:$PATH 
+
+# install cmake
+WORKDIR /home
+RUN wget -q https://cmake.org/files/v3.16/cmake-3.16.0-Linux-x86_64.tar.gz && tar -zxvf cmake-3.16.0-Linux-x86_64.tar.gz && rm cmake-3.16.0-Linux-x86_64.tar.gz
+ENV PATH=/home/cmake-3.16.0-Linux-x86_64/bin:$PATH
+
+# Install Python3.6
+RUN mkdir -p /root/python_build/ && wget -q https://www.sqlite.org/2018/sqlite-autoconf-3250300.tar.gz && \
+    tar -zxf sqlite-autoconf-3250300.tar.gz && cd sqlite-autoconf-3250300 && \
+    ./configure -prefix=/usr/local && make -j8 && make install && cd ../ && rm sqlite-autoconf-3250300.tar.gz
+
+RUN wget -q https://www.python.org/ftp/python/3.6.0/Python-3.6.0.tgz && \
+    tar -xzf Python-3.6.0.tgz && cd Python-3.6.0 && \
+    CFLAGS="-Wformat" ./configure --prefix=/usr/local/ --enable-shared > /dev/null && \
+    make -j8 > /dev/null && make altinstall > /dev/null && ldconfig && cd .. && rm -rf Python-3.6.0*
+
+# Install Python3.7
+RUN wget -q https://www.python.org/ftp/python/3.7.0/Python-3.7.0.tgz && \
+    tar -xzf Python-3.7.0.tgz && cd Python-3.7.0 && \
+    CFLAGS="-Wformat" ./configure --prefix=/usr/local/ --enable-shared > /dev/null && \
+    make -j8 > /dev/null && make altinstall > /dev/null && ldconfig && cd .. && rm -rf Python-3.7.0*
+
+# Install Python3.8
+RUN wget -q https://www.python.org/ftp/python/3.8.0/Python-3.8.0.tgz && \
+    tar -xzf Python-3.8.0.tgz && cd Python-3.8.0 && \
+    CFLAGS="-Wformat" ./configure --prefix=/usr/local/ --enable-shared > /dev/null && \
+    make -j8 > /dev/null && make altinstall > /dev/null && ldconfig && cd .. && rm -rf Python-3.8.0*
+
+ENV LD_LIBRARY_PATH=/usr/local/lib:${LD_LIBRARY_PATH}
+RUN ln -sf /usr/local/bin/python3.6 /usr/local/bin/python3 && ln -sf /usr/local/bin/python3.6 /usr/bin/python3 && ln -sf /usr/local/bin/pip3.6 /usr/local/bin/pip3 && ln -sf /usr/local/bin/pip3.6 /usr/bin/pip3
+
+RUN rm -r /root/python_build
+
+# Install Go and glide
+RUN wget -qO- https://paddle-ci.cdn.bcebos.com/go1.17.2.linux-amd64.tar.gz | \
+    tar -xz -C /usr/local && \
+    mkdir /root/go && \
+    mkdir /root/go/bin && \
+    mkdir /root/go/src && \
+    echo "GOROOT=/usr/local/go" >> /root/.bashrc && \
+    echo "GOPATH=/root/go" >> /root/.bashrc && \
+    echo "PATH=/usr/local/go/bin:/root/go/bin:$PATH" >> /root/.bashrc
+ENV GOROOT=/usr/local/go GOPATH=/root/go
+# should not be in the same line with GOROOT definition, otherwise docker build could not find GOROOT.
+ENV PATH=usr/local/go/bin:/root/go/bin:${PATH}
+
+# Install TensorRT
+# following TensorRT.tar.gz is not the default official one, we do two miny changes:
+# 1. Remove the unnecessary files to make the library small. TensorRT.tar.gz only contains include and lib now,
+#    and its size is only one-third of the official one.
+# 2. Manually add ~IPluginFactory() in IPluginFactory class of NvInfer.h, otherwise, it couldn't work in paddle.
+#    See https://github.com/PaddlePaddle/Paddle/issues/10129 for details.
+
+# Downgrade TensorRT 
+COPY tools/dockerfiles/build_scripts /build_scripts
+RUN bash /build_scripts/install_trt.sh cuda11.2 
+RUN rm -rf /build_scripts
+
+# git credential to skip password typing
+RUN git config --global credential.helper store
+
+# Fix locales to en_US.UTF-8
+RUN localedef -i en_US -f UTF-8 en_US.UTF-8
+
+RUN apt-get install libprotobuf-dev -y
+
+# Older versions of patchelf limited the size of the files being processed and were fixed in this pr.
+# https://github.com/NixOS/patchelf/commit/ba2695a8110abbc8cc6baf0eea819922ee5007fa
+# So install a newer version here.
+RUN wget -q https://paddle-ci.cdn.bcebos.com/patchelf_0.10-2_amd64.deb && \
+    dpkg -i patchelf_0.10-2_amd64.deb
+
+# Configure OpenSSH server. c.f. https://docs.docker.com/engine/examples/running_ssh_service
+RUN mkdir /var/run/sshd && echo 'root:root' | chpasswd && sed -ri 's/^PermitRootLogin\s+.*/PermitRootLogin yes/' /etc/ssh/sshd_config && sed -ri 's/UsePAM yes/#UsePAM yes/g' /etc/ssh/sshd_config
+CMD source ~/.bashrc
+
+# ccache 3.7.9
+RUN wget https://paddle-ci.gz.bcebos.com/ccache-3.7.9.tar.gz && \
+    tar xf ccache-3.7.9.tar.gz && mkdir /usr/local/ccache-3.7.9 && cd ccache-3.7.9 && \
+    ./configure -prefix=/usr/local/ccache-3.7.9 && \
+    make -j8 && make install && \
+    ln -s /usr/local/ccache-3.7.9/bin/ccache /usr/local/bin/ccache
+
+RUN python3.8 -m pip install --upgrade pip==21.1.1 requests && \
+    python3.7 -m pip install --upgrade pip==21.1.1 requests && \
+    python3.6 -m pip install --upgrade pip==21.1.1 requests 
+
+RUN wget https://paddle-serving.bj.bcebos.com/others/centos_ssl.tar && \
+    tar xf centos_ssl.tar && rm -rf centos_ssl.tar && \
+    mv libcrypto.so.1.0.2k /usr/lib/libcrypto.so.1.0.2k && mv libssl.so.1.0.2k /usr/lib/libssl.so.1.0.2k && \
+    ln -sf /usr/lib/libcrypto.so.1.0.2k /usr/lib/libcrypto.so.10 && \
+    ln -sf /usr/lib/libssl.so.1.0.2k /usr/lib/libssl.so.10 && \
+    ln -sf /usr/lib/libcrypto.so.10 /usr/lib/libcrypto.so && \
+    ln -sf /usr/lib/libssl.so.10 /usr/lib/libssl.so
+
+EXPOSE 22
--- a/tools/Dockerfile.devel
+++ b/tools/Dockerfile.devel
@@ -83,7 +83,7 @@ RUN ln -sf /usr/local/bin/python3.6 /usr/local/bin/python3 && ln -sf /usr/local/
 RUN rm -r /root/python_build

 # Install Go and glide
-RUN wget -qO- https://dl.google.com/go/go1.14.linux-amd64.tar.gz | \
+RUN wget -qO- https://paddle-ci.cdn.bcebos.com/go1.17.2.linux-amd64.tar.gz | \
    tar -xz -C /usr/local && \
    mkdir /root/go && \
    mkdir /root/go/bin && \