update 1.8.1 lib link

deploy/cpp/CMakeLists.txt

@@ -97,7 +97,7 @@ if (WIN32)
   include_directories("${PADDLE_DIR}/paddle/include")
   link_directories("${PADDLE_DIR}/paddle/fluid/inference")
   find_package(OpenCV REQUIRED PATHS ${OPENCV_DIR}/build/ NO_DEFAULT_PATH)
-  unset(OpenCV_DIR CACHE)
+  unset(OPENCV_DIR CACHE)
 else ()
   find_package(OpenCV REQUIRED PATHS ${OPENCV_DIR}/share/OpenCV NO_DEFAULT_PATH)
   include_directories("${PADDLE_DIR}/paddle/include")

docs/tutorials/deploy/deploy_server/deploy_cpp/deploy_cpp_win_vs2019.md

@@ -29,16 +29,16 @@ git clone https://github.com/PaddlePaddle/PaddleX.git
 
 PaddlePaddle C++ 预测库针对不同的`CPU`，`CUDA`，以及是否支持TensorRT，提供了不同的预编译版本，目前PaddleX依赖于Paddle1.7版本，以下提供了多个不同版本的Paddle预测库:
 
-|  版本说明   | 预测库(1.7.2版本)  | 编译器 | 构建工具| cuDNN | CUDA
+|  版本说明   | 预测库(1.8.1版本)  | 编译器 | 构建工具| cuDNN | CUDA
 |  ----  |  ----  |  ----  |  ----  | ---- | ---- |
-| cpu_avx_mkl  | [fluid_inference.zip](https://paddle-wheel.bj.bcebos.com/1.7.2/win-infer/mkl/cpu/fluid_inference_install_dir.zip) | MSVC 2015 update 3 | CMake v3.16.0 |
-| cpu_avx_openblas  | [fluid_inference.zip](https://paddle-wheel.bj.bcebos.com/1.7.2/win-infer/open/cpu/fluid_inference_install_dir.zip) | MSVC 2015 update 3 | CMake v3.16.0 |
-| cuda9.0_cudnn7_avx_mkl  | [fluid_inference.zip](https://paddle-wheel.bj.bcebos.com/1.7.2/win-infer/mkl/post97/fluid_inference_install_dir.zip) | MSVC 2015 update 3 | CMake v3.16.0 | 7.4.1 | 9.0 |
-| cuda9.0_cudnn7_avx_openblas  | [fluid_inference.zip](https://paddle-wheel.bj.bcebos.com/1.7.2/win-infer/open/post97/fluid_inference_install_dir.zip) | MSVC 2015 update 3 | CMake v3.16.0 | 7.4.1 | 9.0 |
-| cuda10.0_cudnn7_avx_mkl  | [fluid_inference.zip](https://paddle-wheel.bj.bcebos.com/1.7.2/win-infer/mkl/post107/fluid_inference_install_dir.zip) | MSVC 2015 update 3 | CMake v3.16.0 | 7.5.0 | 9.0 |
+| cpu_avx_mkl  | [fluid_inference.zip](https://paddle-wheel.bj.bcebos.com/1.8.1/win-infer/mkl/cpu/fluid_inference_install_dir.zip) | MSVC 2015 update 3 | CMake v3.16.0 |
+| cpu_avx_openblas  | [fluid_inference.zip](https://paddle-wheel.bj.bcebos.com/1.8.1/win-infer/open/cpu/fluid_inference_install_dir.zip) | MSVC 2015 update 3 | CMake v3.16.0 |
+| cuda9.0_cudnn7_avx_mkl  | [fluid_inference.zip](https://paddle-wheel.bj.bcebos.com/1.8.1/win-infer/mkl/post97/fluid_inference_install_dir.zip) | MSVC 2015 update 3 | CMake v3.16.0 | 7.4.1 | 9.0 |
+| cuda9.0_cudnn7_avx_openblas  | [fluid_inference.zip](https://paddle-wheel.bj.bcebos.com/1.8.1/win-infer/open/post97/fluid_inference_install_dir.zip) | MSVC 2015 update 3 | CMake v3.16.0 | 7.4.1 | 9.0 |
+| cuda10.0_cudnn7_avx_mkl  | [fluid_inference.zip](https://paddle-wheel.bj.bcebos.com/1.8.1/win-infer/mkl/post107/fluid_inference_install_dir.zip) | MSVC 2015 update 3 | CMake v3.16.0 | 7.5.0 | 9.0 |
 
 
-更多和更新的版本，请根据实际情况下载:  [C++预测库下载列表](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/advanced_guide/inference_deployment/inference/build_and_install_lib_cn.html#id1)
+更多和更新的版本，请根据实际情况下载:  [C++预测库下载列表](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/advanced_guide/inference_deployment/inference/windows_cpp_inference.html)
 
 解压后`D:\projects\fluid_inference*\`目录下主要包含的内容为：
 ```
@@ -107,7 +107,7 @@ yaml-cpp.zip文件下载后无需解压，在cmake/yaml.cmake中将`URL https://
 ### Step5: 预测及可视化
 
 
-**在加载模型前，请检查你的模型目录中文件应该包括`model.yml`、`__model__`和`__params__`三个文件。如若不满足这个条件，请参考[模型导出为Inference文档](../deploy_python.html#inference)将模型导出为部署格式。**   
+**在加载模型前，请检查你的模型目录中文件应该包括`model.yml`、`__model__`和`__params__`三个文件。如若不满足这个条件，请参考[模型导出为Inference文档](../deploy_python.html#inference)将模型导出为部署格式。**  
 
 **注意：由于PaddleX代码的持续更新，版本低于1.0.0的模型（模型版本可查看model.yml文件中的version字段）暂时无法直接用于预测部署，参考[模型版本升级](../../upgrade_version.md)对模型版本进行升级。**