[Serving]modify docker images name (PaddlePaddle#992)

* modify docker images name

* Update Dockerfile_cpu

Author: heliqi

examples/text/ernie-3.0/serving/README.md

@@ -51,16 +51,16 @@ models
 ```bash
 # x.y.z represent image versions. Please refer to the serving document to replace them with numbers
 # GPU Image
-docker pull paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10
+docker pull registry.baidubce.com/paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10
 # CPU Image
-docker pull paddlepaddle/fastdeploy:x.y.z-cpu-only-21.10
+docker pull registry.baidubce.com/paddlepaddle/fastdeploy:x.y.z-cpu-only-21.10
 
 # Running
-docker run  -it --net=host --name fastdeploy_server --shm-size="1g" -v /path/serving/models:/models paddlepaddle/fastdeploy:x.y.z-cpu-only-21.10 bash
+docker run  -it --net=host --name fastdeploy_server --shm-size="1g" -v /path/serving/models:/models registry.baidubce.com/paddlepaddle/fastdeploy:x.y.z-cpu-only-21.10 bash
 ```
 
 ## Deployment Models
-The serving directory contains the configuration to start the pipeline service and the code to send the prediction request, including 
+The serving directory contains the configuration to start the pipeline service and the code to send the prediction request, including
 
 ```
 models                    # 服务化启动需要的模型仓库，包含模型和服务配置文件
@@ -70,7 +70,7 @@ token_cls_rpc_client.py   # 序列标注任务发送pipeline预测请求的脚
 
 *Attention*:Attention: When starting the service, each python backend process of Server requests 64M memory by default, and the docker started by default cannot start more than one python backend node. There are two solutions:
 
-- 1.Set the `shm-size` parameter when starting the container, for example, `docker run  -it --net=host --name fastdeploy_server --shm-size="1g" -v /path/serving/models:/models paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10 bash`
+- 1.Set the `shm-size` parameter when starting the container, for example, `docker run  -it --net=host --name fastdeploy_server --shm-size="1g" -v /path/serving/models:/models registry.baidubce.com/paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10 bash`
 - 2.Set the `shm-default-byte-size` parameter of python backend when starting the service. Set the default memory of python backend to 10M： `tritonserver --model-repository=/models --backend-config=python,shm-default-byte-size=10485760`
 
 ### Classification Task

examples/text/ernie-3.0/serving/README_CN.md

@@ -51,12 +51,12 @@ models
 ```bash
 # x.y.z为镜像版本号，需参照serving文档替换为数字
 # GPU镜像
-docker pull paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10
+docker pull registry.baidubce.com/paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10
 # CPU镜像
-docker pull paddlepaddle/fastdeploy:x.y.z-cpu-only-21.10
+docker pull registry.baidubce.com/paddlepaddle/fastdeploy:x.y.z-cpu-only-21.10
 
 # 运行
-docker run  -it --net=host --name fastdeploy_server --shm-size="1g" -v /path/serving/models:/models paddlepaddle/fastdeploy:x.y.z-cpu-only-21.10 bash
+docker run  -it --net=host --name fastdeploy_server --shm-size="1g" -v /path/serving/models:/models registry.baidubce.com/paddlepaddle/fastdeploy:x.y.z-cpu-only-21.10 bash
 ```
 
 ## 部署模型
@@ -69,7 +69,7 @@ token_cls_rpc_client.py   # 序列标注任务发送pipeline预测请求的脚
 ```
 
 *注意*:启动服务时，Server的每个python后端进程默认申请`64M`内存，默认启动的docker无法启动多个python后端节点。有两个解决方案：
-- 1.启动容器时设置`shm-size`参数, 比如:`docker run  -it --net=host --name fastdeploy_server --shm-size="1g" -v /path/serving/models:/models paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10 bash`
+- 1.启动容器时设置`shm-size`参数, 比如:`docker run  -it --net=host --name fastdeploy_server --shm-size="1g" -v /path/serving/models:/models registry.baidubce.com/paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10 bash`
 - 2.启动服务时设置python后端的`shm-default-byte-size`参数, 设置python后端的默认内存为10M： `tritonserver --model-repository=/models --backend-config=python,shm-default-byte-size=10485760`
 
 ### 分类任务

examples/vision/classification/paddleclas/serving/README.md

@@ -26,12 +26,12 @@ mv ResNet50_vd_infer/inference.pdiparams models/runtime/1/model.pdiparams
 
 # 拉取fastdeploy镜像(x.y.z为镜像版本号，需参照serving文档替换为数字)
 # GPU镜像
-docker pull paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10
+docker pull registry.baidubce.com/paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10
 # CPU镜像
-docker pull paddlepaddle/fastdeploy:x.y.z-cpu-only-21.10
+docker pull registry.baidubce.com/paddlepaddle/fastdeploy:x.y.z-cpu-only-21.10
 
 # 运行容器.容器名字为 fd_serving, 并挂载当前目录为容器的 /serving 目录
-nvidia-docker run -it --net=host --name fd_serving -v `pwd`/:/serving paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10  bash
+nvidia-docker run -it --net=host --name fd_serving -v `pwd`/:/serving registry.baidubce.com/paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10  bash
 
 # 启动服务(不设置CUDA_VISIBLE_DEVICES环境变量，会拥有所有GPU卡的调度权限)
 CUDA_VISIBLE_DEVICES=0 fastdeployserver --model-repository=/serving/models --backend-config=python,shm-default-byte-size=10485760

examples/vision/detection/paddledetection/serving/README.md

@@ -37,13 +37,13 @@ cp models/runtime/ppyoloe_runtime_config.pbtxt models/runtime/config.pbtxt
 
 # 拉取fastdeploy镜像(x.y.z为镜像版本号，需替换成fastdeploy版本数字)
 # GPU镜像
-docker pull paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10
+docker pull registry.baidubce.com/paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10
 # CPU镜像
 docker pull paddlepaddle/fastdeploy:z.y.z-cpu-only-21.10
 
 
 # 运行容器.容器名字为 fd_serving, 并挂载当前目录为容器的 /serving 目录
-nvidia-docker run -it --net=host --name fd_serving --shm-size="1g"  -v `pwd`/:/serving paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10  bash
+nvidia-docker run -it --net=host --name fd_serving --shm-size="1g"  -v `pwd`/:/serving registry.baidubce.com/paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10  bash
 
 # 启动服务(不设置CUDA_VISIBLE_DEVICES环境变量，会拥有所有GPU卡的调度权限)
 CUDA_VISIBLE_DEVICES=0 fastdeployserver --model-repository=/serving/models

examples/vision/detection/yolov5/serving/README.md

@@ -20,12 +20,12 @@ mv yolov5s.onnx models/runtime/1/model.onnx
 
 # 拉取fastdeploy镜像(x.y.z为镜像版本号，需参照serving文档替换为数字)
 # GPU镜像
-docker pull paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10
+docker pull registry.baidubce.com/paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10
 # CPU镜像
-docker pull paddlepaddle/fastdeploy:x.y.z-cpu-only-21.10
+docker pull registry.baidubce.com/paddlepaddle/fastdeploy:x.y.z-cpu-only-21.10
 
 # 运行容器.容器名字为 fd_serving, 并挂载当前目录为容器的 /yolov5_serving 目录
-nvidia-docker run -it --net=host --name fd_serving -v `pwd`/:/yolov5_serving paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10  bash
+nvidia-docker run -it --net=host --name fd_serving -v `pwd`/:/yolov5_serving registry.baidubce.com/paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10  bash
 
 # 启动服务(不设置CUDA_VISIBLE_DEVICES环境变量，会拥有所有GPU卡的调度权限)
 CUDA_VISIBLE_DEVICES=0 fastdeployserver --model-repository=/yolov5_serving/models --backend-config=python,shm-default-byte-size=10485760

serving/Dockerfile

@@ -12,6 +12,9 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+ARG http_proxy
+ARG https_proxy
+
 FROM nvcr.io/nvidia/tritonserver:21.10-py3 as full
 FROM nvcr.io/nvidia/tritonserver:21.10-py3-min
 
@@ -24,7 +27,10 @@ COPY serving/TensorRT-8.4.1.5 /opt/TensorRT-8.4.1.5
 
 ENV TZ=Asia/Shanghai \
     DEBIAN_FRONTEND=noninteractive \
-    DCGM_VERSION=2.2.9
+    DCGM_VERSION=2.2.9 \
+    http_proxy=$http_proxy \
+    https_proxy=$http_proxy
+
 RUN apt-get update \
     && apt-key del 7fa2af80 \
     && wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/cuda-keyring_1.0-1_all.deb \
@@ -46,3 +52,6 @@ COPY build/fastdeploy_install /opt/fastdeploy/
 
 ENV LD_LIBRARY_PATH="/opt/TensorRT-8.4.1.5/lib/:/opt/fastdeploy/lib:/opt/fastdeploy/third_libs/install/onnxruntime/lib:/opt/fastdeploy/third_libs/install/paddle2onnx/lib:/opt/fastdeploy/third_libs/install/tensorrt/lib:/opt/fastdeploy/third_libs/install/paddle_inference/paddle/lib:/opt/fastdeploy/third_libs/install/paddle_inference/third_party/install/mkldnn/lib:/opt/fastdeploy/third_libs/install/paddle_inference/third_party/install/mklml/lib:/opt/fastdeploy/third_libs/install/openvino/runtime/lib:$LD_LIBRARY_PATH"
 ENV PATH="/opt/tritonserver/bin:$PATH"
+# unset proxy
+ENV http_proxy=
+ENV https_proxy=

serving/Dockerfile_cpu

@@ -12,10 +12,15 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+ARG http_proxy
+ARG https_proxy
+
 FROM paddlepaddle/fastdeploy:21.10-cpu-only-min
 
 ENV TZ=Asia/Shanghai \
-    DEBIAN_FRONTEND=noninteractive
+    DEBIAN_FRONTEND=noninteractive \
+    http_proxy=$http_proxy \
+    https_proxy=$http_proxy
 
 RUN apt-get update && apt-get install -y --no-install-recommends apt-utils libgomp1 ffmpeg libsm6 libxext6 \
     && python3 -m pip install -U pip \
@@ -30,3 +35,6 @@ COPY build/fastdeploy_install /opt/fastdeploy/
 
 RUN mv /opt/tritonserver/bin/tritonserver /opt/tritonserver/bin/fastdeployserver
 ENV LD_LIBRARY_PATH="/opt/fastdeploy/lib:/opt/fastdeploy/third_libs/install/onnxruntime/lib:/opt/fastdeploy/third_libs/install/paddle2onnx/lib:/opt/fastdeploy/third_libs/install/paddle_inference/paddle/lib:/opt/fastdeploy/third_libs/install/paddle_inference/third_party/install/mkldnn/lib:/opt/fastdeploy/third_libs/install/paddle_inference/third_party/install/mklml/lib:/opt/fastdeploy/third_libs/install/openvino/runtime/lib:$LD_LIBRARY_PATH"
+# unset proxy
+ENV http_proxy=
+ENV https_proxy=