[Doc][Serving]serving doc update version to 1.0.0 (#755)

serving doc update version to 1.0.0

Author: heliqi

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

@@ -51,10 +51,10 @@ models
 # GPU镜像
 docker pull 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
+docker pull 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:0.6.0-cpu-only-21.10 bash
+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
 ```
 
 ## 部署模型
@@ -67,7 +67,7 @@ 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:0.6.0-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 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/text/uie/serving/README.md

@@ -34,10 +34,10 @@ models
 # GPU镜像
 docker pull 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
+docker pull 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 /uie_serving 目录
-docker run  -it --net=host --name fastdeploy_server --shm-size="1g" -v `pwd`/:/uie_serving paddlepaddle/fastdeploy:0.6.0-gpu-cuda11.4-trt8.4-21.10 bash
+docker run  -it --net=host --name fastdeploy_server --shm-size="1g" -v `pwd`/:/uie_serving 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=/uie_serving/models --backend-config=python,shm-default-byte-size=10485760

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

@@ -28,10 +28,10 @@ mv ResNet50_vd_infer/inference.pdiparams models/runtime/1/model.pdiparams
 # GPU镜像
 docker pull 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
+docker pull 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:0.6.0-gpu-cuda11.4-trt8.4-21.10  bash
+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
 
 # 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/yolov5/serving/README.md

@@ -22,10 +22,10 @@ mv yolov5s.onnx models/runtime/1/model.onnx
 # GPU镜像
 docker pull 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
+docker pull 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:0.6.0-gpu-cuda11.4-trt8.4-21.10  bash
+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
 
 # 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

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

@@ -9,11 +9,11 @@ wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s.onnx
 # Save the model under models/infer/1 and rename it as model.onnx
 mv yolov5s.onnx models/infer/1/
 
-# Pull fastdeploy image
-docker pull paddlepaddle/fastdeploy:0.6.0-gpu-cuda11.4-trt8.4-21.10
+# Pull fastdeploy image, x.y.z is FastDeploy version, example 1.0.0.
+docker pull paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10
 
 # Run the docker. The docker name is fd_serving, and the current directory is mounted as the docker's /yolov5_serving directory
-nvidia-docker run -it --net=host --name fd_serving -v `pwd`/:/yolov5_serving paddlepaddle/fastdeploy:0.6.0-gpu-cuda11.4-trt8.4-21.10  bash
+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
 
 # Start the service (Without setting the CUDA_VISIBLE_DEVICES environment variable, it will have scheduling privileges for all GPU cards)
 CUDA_VISIBLE_DEVICES=0 fastdeployserver --model-repository=models --backend-config=python,shm-default-byte-size=10485760

examples/vision/ocr/PP-OCRv3/serving/README.md

@@ -1,5 +1,9 @@
 # PP-OCR服务化部署示例
 
+在服务化部署前，需确认
+
+- 1. 服务化镜像的软硬件环境要求和镜像拉取命令请参考[FastDeploy服务化部署](../../../../../serving/README_CN.md)
+
 ## 介绍
 本文介绍了使用FastDeploy搭建OCR文字识别服务的方法.
 
@@ -48,9 +52,9 @@ mv ppocr_keys_v1.txt models/rec_postprocess/1/
 
 wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/doc/imgs/12.jpg
 
-
-docker pull paddlepaddle/fastdeploy:0.6.0-gpu-cuda11.4-trt8.4-21.10
-docker run -dit --net=host --name fastdeploy --shm-size="1g" -v $PWD:/ocr_serving paddlepaddle/fastdeploy:0.6.0-gpu-cuda11.4-trt8.4-21.10 bash
+# x.y.z为镜像版本号，需参照serving文档替换为数字
+docker pull paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10
+docker run -dit --net=host --name fastdeploy --shm-size="1g" -v $PWD:/ocr_serving paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10 bash
 docker exec -it -u root fastdeploy bash
 ```
 

serving/README_CN.md

@@ -17,13 +17,13 @@ FastDeploy基于[Triton Inference Server](https://github.com/triton-inference-se
 #### CPU镜像
 CPU镜像仅支持Paddle/ONNX模型在CPU上进行服务化部署，支持的推理后端包括OpenVINO、Paddle Inference和ONNX Runtime
 ``` shell
-docker pull paddlepaddle/fastdeploy:0.6.0-cpu-only-21.10
+docker pull paddlepaddle/fastdeploy:1.0.0-cpu-only-21.10
 ```
 
 #### GPU镜像
 GPU镜像支持Paddle/ONNX模型在GPU/CPU上进行服务化部署，支持的推理后端包括OpenVINO、TensorRT、Paddle Inference和ONNX Runtime
 ```
-docker pull paddlepaddle/fastdeploy:0.6.0-gpu-cuda11.4-trt8.4-21.10
+docker pull paddlepaddle/fastdeploy:1.0.0-gpu-cuda11.4-trt8.4-21.10
 ```
 
 用户也可根据自身需求，参考如下文档自行编译镜像

serving/README_EN.md

@@ -20,15 +20,15 @@ FastDeploy builds an end-to-end serving deployment based on [Triton Inference Se
 CPU images only support Paddle/ONNX models for serving deployment on CPUs, and supported inference backends include OpenVINO, Paddle Inference, and ONNX Runtime
 
 ```shell
-docker pull paddlepaddle/fastdeploy:0.6.0-cpu-only-21.10
+docker pull paddlepaddle/fastdeploy:1.0.0-cpu-only-21.10
 ```
 
 #### GPU Image
 
 GPU images support Paddle/ONNX models for serving deployment on GPU and CPU, and supported inference backends including OpenVINO, TensorRT, Paddle Inference, and ONNX Runtime
 
 ```
-docker pull paddlepaddle/fastdeploy:0.6.0-gpu-cuda11.4-trt8.4-21.10
+docker pull paddlepaddle/fastdeploy:1.0.0-gpu-cuda11.4-trt8.4-21.10
 ```
 
 Users can also compile the image by themselves according to their own needs, referring to the following documents:

serving/docs/EN/compile-en.md

@@ -12,8 +12,9 @@ cd serving
 bash scripts/build.sh
 
 # Exit to the FastDeploy home directory and create the image
+# x.y.z is FastDeploy version, example: 1.0.0
 cd ../
-docker build -t paddlepaddle/fastdeploy:0.6.0-gpu-cuda11.4-trt8.4-21.10 -f serving/Dockerfile .
+docker build -t paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10 -f serving/Dockerfile .
 ```
 
 ## CPU Image
@@ -25,8 +26,9 @@ cd serving
 bash scripts/build.sh OFF
 
 # Exit to the FastDeploy home directory and create the image
+# x.y.z is FastDeploy version, example: 1.0.0
 cd ../
-docker build -t paddlepaddle/fastdeploy:0.6.0-cpu-only-21.10 -f serving/Dockerfile_cpu .
+docker build -t paddlepaddle/fastdeploy:x.y.z-cpu-only-21.10 -f serving/Dockerfile_cpu .
 ```
 
 ## IPU Image
@@ -37,6 +39,7 @@ cd serving
 bash scripts/build_fd_ipu.sh
 
 # Exit to the FastDeploy home directory and create the image
+# x.y.z is FastDeploy version, example: 1.0.0
 cd ../
-docker build -t paddlepaddle/fastdeploy:0.6.0-ipu-only-21.10 -f serving/Dockerfile_ipu .
+docker build -t paddlepaddle/fastdeploy:x.y.z-ipu-only-21.10 -f serving/Dockerfile_ipu .
 ```

serving/docs/zh_CN/compile.md

@@ -12,8 +12,9 @@ cd serving
 bash scripts/build.sh
 
 # 退出到FastDeploy主目录，制作镜像
+# x.y.z为FastDeploy版本号，可根据情况自己确定。比如: 1.0.0
 cd ../
-docker build -t paddlepaddle/fastdeploy:0.6.0-gpu-cuda11.4-trt8.4-21.10 -f serving/Dockerfile .
+docker build -t paddlepaddle/fastdeploy:x.y.z-gpu-cuda11.4-trt8.4-21.10 -f serving/Dockerfile .
 ```
 
 ## 制作CPU镜像
@@ -24,8 +25,9 @@ cd serving
 bash scripts/build.sh OFF
 
 # 退出到FastDeploy主目录，制作镜像
+# x.y.z为FastDeploy版本号，可根据情况自己确定。比如: 1.0.0
 cd ../
-docker build -t paddlepaddle/fastdeploy:0.6.0-cpu-only-21.10 -f serving/Dockerfile_cpu .
+docker build -t paddlepaddle/fastdeploy:x.y.z-cpu-only-21.10 -f serving/Dockerfile_cpu .
 ```
 
 ## 制作IPU镜像
@@ -36,6 +38,7 @@ cd serving
 bash scripts/build_fd_ipu.sh
 
 # 退出到FastDeploy主目录，制作镜像
+# x.y.z为FastDeploy版本号，可根据情况自己确定。比如: 1.0.0
 cd ../
-docker build -t paddlepaddle/fastdeploy:0.6.0-ipu-only-21.10 -f serving/Dockerfile_ipu .
+docker build -t paddlepaddle/fastdeploy:x.y.z-ipu-only-21.10 -f serving/Dockerfile_ipu .
 ```