From a380686c31542b00ba93b30b12c8da073b22a2ab Mon Sep 17 00:00:00 2001 From: zhouwei25 <52485244+zhouwei25@users.noreply.github.com> Date: Mon, 28 Oct 2019 14:04:52 +0800 Subject: [PATCH] fix inference lib package on windows (#1554) Update download link of inference lib package on windows. * fix the DOC of Windows compile , install and inference lib * fix inference lib package on windows --- .../deploy/inference/windows_cpp_inference.md | 18 ++++----- .../inference/windows_cpp_inference_en.md | 39 +++++++++---------- 2 files changed, 26 insertions(+), 31 deletions(-) diff --git a/doc/fluid/advanced_usage/deploy/inference/windows_cpp_inference.md b/doc/fluid/advanced_usage/deploy/inference/windows_cpp_inference.md index 5d9039611..30ca11144 100755 --- a/doc/fluid/advanced_usage/deploy/inference/windows_cpp_inference.md +++ b/doc/fluid/advanced_usage/deploy/inference/windows_cpp_inference.md @@ -5,13 +5,13 @@ 直接下载安装 ------------- - | 版本说明 | 预测库(1.6.0版本) | |:---------|:-------------------| -| cpu_avx_mkl | [fluid_inference.zip](https://paddle-inference-lib.bj.bcebos.com/1.5.2-win/cpu_mkl_avx/fluid_inference_install_dir.zip) | -| cuda8.0_cudnn7_avx_mkl | [fluid_inference.zip](https://paddle-inference-lib.bj.bcebos.com/1.5.2-win/gpu_mkl_avx_8.0/fluid_inference_install_dir.zip) | -| cuda9.0_cudnn7_avx_mkl | [fluid_inference.zip](https://paddle-inference-lib.bj.bcebos.com/1.5.2-win/gpu_mkl_avx_9.0/fluid_inference_install_dir.zip) | -| cuda10.0_cudnn7_avx_mkl | [fluid_inference.zip](https://paddle-inference-lib.bj.bcebos.com/1.5.2-win/gpu_mkl_avx_10.0/fluid_inference_install_dir.zip) | +| cpu_avx_mkl | [fluid_inference.zip](https://paddle-wheel.bj.bcebos.com/1.6.0/win-infer/mkl/cpu/fluid_inference_install_dir.zip) | +| cpu_avx_openblas | [fluid_inference.zip](https://paddle-wheel.bj.bcebos.com/1.6.0/win-infer/open/cpu/fluid_inference_install_dir.zip) | +| cuda9.0_cudnn7_avx_openblas | [fluid_inference.zip](https://paddle-wheel.bj.bcebos.com/1.6.0/win-infer/open/post97/fluid_inference_install_dir.zip) | +| cuda9.0_cudnn7_avx_mkl | [fluid_inference.zip](https://paddle-wheel.bj.bcebos.com/1.6.0/win-infer/mkl/post97/fluid_inference_install_dir.zip) | +| cuda10.0_cudnn7_avx_mkl | [fluid_inference.zip](https://paddle-wheel.bj.bcebos.com/1.6.0/win-infer/mkl/post107/fluid_inference_install_dir.zip) | 从源码编译预测库 -------------- @@ -43,11 +43,11 @@ Windows下安装与编译预测库步骤：(在Windows命令提示符下执行 cd build - cmake .. -G "Visual Studio 14 2015 Win64" -DCMAKE_BUILD_TYPE=Release -DWITH_MKL=OFF -DWITH_GPU=OFF -DON_INFER=ON -DWITH_PYTHON=OFF + cmake .. -G "Visual Studio 14 2015" -A x64 -DCMAKE_BUILD_TYPE=Release -DWITH_MKL=OFF -DWITH_GPU=OFF -DON_INFER=ON -DWITH_PYTHON=OFF # -DWITH_GPU`为是否使用GPU的配置选项，-DWITH_MKL 为是否使用Intel MKL(数学核心库)的配置选项，请按需配置。 # Windows默认使用 /MT 模式进行编译，如果想使用 /MD 模式，请使用以下命令。如不清楚两者的区别，请使用上面的命令 - cmake .. -G "Visual Studio 14 2015 Win64" -DCMAKE_BUILD_TYPE=Release -DWITH_MKL=OFF -DWITH_GPU=OFF -DON_INFER=ON -DWITH_PYTHON=OFF -DMSVC_STATIC_CRT=OFF + cmake .. -G "Visual Studio 14 2015" -A x64 -DCMAKE_BUILD_TYPE=Release -DWITH_MKL=OFF -DWITH_GPU=OFF -DON_INFER=ON -DWITH_PYTHON=OFF -DMSVC_STATIC_CRT=OFF ``` 3. 使用Blend for Visual Studio 2015 打开 `paddle.sln` 文件，选择平台为`x64`，配置为`Release`，编译inference_lib_dist项目。 @@ -82,8 +82,6 @@ Windows下安装与编译预测库步骤：(在Windows命令提示符下执行 │   ├── mkldnn │   ├── mklml │   ├── protobuf - │   ├── snappy - │   ├── snappystream │   ├── xxhash │   └── zlib └── version.txt @@ -130,7 +128,7 @@ version.txt 中记录了该预测库的版本信息，包括Git Commit ID、使 进入 Paddle/paddle/fluid/inference/api/demo_ci 目录，新建build目录并进入，然后使用cmake生成vs2015的solution文件。 指令为： -`cmake .. -G "Visual Studio 14 2015 Win64" -DWITH_GPU=OFF -DWITH_MKL=ON -DWITH_STATIC_LIB=ON -DCMAKE_BUILD_TYPE=Release -DDEMO_NAME=simple_on_word2vec -DPADDLE_LIB=path_to_the_paddle_lib` +`cmake .. -G "Visual Studio 14 2015" -A x64 -DWITH_GPU=OFF -DWITH_MKL=ON -DWITH_STATIC_LIB=ON -DCMAKE_BUILD_TYPE=Release -DDEMO_NAME=simple_on_word2vec -DPADDLE_LIB=path_to_the_paddle_lib` 注： diff --git a/doc/fluid/advanced_usage/deploy/inference/windows_cpp_inference_en.md b/doc/fluid/advanced_usage/deploy/inference/windows_cpp_inference_en.md index 6ec1d03ee..f6ae5fd18 100755 --- a/doc/fluid/advanced_usage/deploy/inference/windows_cpp_inference_en.md +++ b/doc/fluid/advanced_usage/deploy/inference/windows_cpp_inference_en.md @@ -1,31 +1,30 @@ -Model Inference on Windows + +Install and Compile C++ Inference Library on Windows =========================== -Pre-Built Inference Libraries +Direct Download and Install ------------- -| Version | Inference Libraries(v1.6.0) | +| Version | Inference Libraries(v1.6.0) | |:---------|:-------------------| -| cpu_avx_mkl | [fluid_inference.zip](https://paddle-inference-lib.bj.bcebos.com/1.5.1-win/cpu_mkl_avx/fluid_inference_install_dir.zip) | -| cpu_avx_openblas | [fluid_inference.zip](https://paddle-inference-lib.bj.bcebos.com/1.5.1-win/cpu_open_avx/fluid_inference_install_dir.zip) | -| cuda8.0_cudnn7_avx_mkl | [fluid_inference.zip](https://paddle-inference-lib.bj.bcebos.com/1.5.1-win/gpu_mkl_avx_8.0/fluid_inference_install_dir.zip) | -| cuda8.0_cudnn7_avx_openblas | [fluid_inference.zip](https://paddle-inference-lib.bj.bcebos.com/1.5.1-win/gpu_open_avx_8.0/fluid_inference_install_dir.zip)| -| cuda9.0_cudnn7_avx_mkl | [fluid_inference.zip](https://paddle-inference-lib.bj.bcebos.com/1.5.1-win/gpu_mkl_avx_9.0/fluid_inference_install_dir.zip) | -| cuda9.0_cudnn7_avx_openblas | [fluid_inference.zip](https://paddle-inference-lib.bj.bcebos.com/1.5.1-win/gpu_open_avx_9.0/fluid_inference_install_dir.zip) | - +| cpu_avx_mkl | [fluid_inference.zip](https://paddle-wheel.bj.bcebos.com/1.6.0/win-infer/mkl/cpu/fluid_inference_install_dir.zip) | +| cpu_avx_openblas | [fluid_inference.zip](https://paddle-wheel.bj.bcebos.com/1.6.0/win-infer/open/cpu/fluid_inference_install_dir.zip) | +| cuda9.0_cudnn7_avx_openblas | [fluid_inference.zip](https://paddle-wheel.bj.bcebos.com/1.6.0/win-infer/open/post97/fluid_inference_install_dir.zip) | +| cuda9.0_cudnn7_avx_mkl | [fluid_inference.zip](https://paddle-wheel.bj.bcebos.com/1.6.0/win-infer/mkl/post97/fluid_inference_install_dir.zip) | +| cuda10.0_cudnn7_avx_mkl | [fluid_inference.zip](https://paddle-wheel.bj.bcebos.com/1.6.0/win-infer/mkl/post107/fluid_inference_install_dir.zip) | Build From Source Code -------------- -Important Compilation Flags: -|Option | Value | +Users can also compile C++ inference libraries from the PaddlePaddle core code by specifying the following compile options at compile time: + +|Option | Value | |:-------------|:-------------------| |CMAKE_BUILD_TYPE | Release | -|ON_INFER | ON (recommended) | -|WITH_GPU | ON/OFF | +|ON_INFER | ON(recommended) | +|WITH_GPU | ON/OFF | |WITH_MKL | ON/OFF | -|WITH_PYTHON | OFF | - +|WITH_PYTHON | OFF | **Paddle Windows Inference Library Compilation Steps** @@ -43,13 +42,13 @@ Important Compilation Flags: # change to the build directory cd build - cmake .. -G "Visual Studio 14 2015 Win64" -DCMAKE_BUILD_TYPE=Release -DWITH_MKL=OFF -DWITH_GPU=OFF -DON_INFER=ON -DWITH_PYTHON=OFF + cmake .. -G "Visual Studio 14 2015" -A x64 -DCMAKE_BUILD_TYPE=Release -DWITH_MKL=OFF -DWITH_GPU=OFF -DON_INFER=ON -DWITH_PYTHON=OFF # use -DWITH_GPU to control we are building CPU or GPU version # use -DWITH_MKL to select math library: Intel MKL or OpenBLAS # By default on Windows we use /MT for C Runtime Library, If you want to use /MD, please use the below command # If you have no ideas the differences between the two, use the above one - cmake .. -G "Visual Studio 14 2015 Win64" -DCMAKE_BUILD_TYPE=Release -DWITH_MKL=OFF -DWITH_GPU=OFF -DON_INFER=ON -DWITH_PYTHON=OFF -DMSVC_STATIC_CRT=OFF + cmake .. -G "Visual Studio 14 2015" -A x64 -DCMAKE_BUILD_TYPE=Release -DWITH_MKL=OFF -DWITH_GPU=OFF -DON_INFER=ON -DWITH_PYTHON=OFF -DMSVC_STATIC_CRT=OFF ``` 3. Open the `paddle.sln` using VisualStudio 2015，choose the`x64` for Solution Platforms，and `Release` for Solution Configurations，then build the `inference_lib_dist` project in the Solution Explorer(Rigth click the project and click Build) @@ -81,8 +80,6 @@ The inference library will be installed in `fluid_inference_install_dir`: │   ├── mkldnn │   ├── mklml │   ├── protobuf - │   ├── snappy - │   ├── snappystream │   ├── xxhash │   └── zlib └── version.txt @@ -130,7 +127,7 @@ Decompress Paddle, Release and fluid_install_dir compressed package. First enter into Paddle/paddle/fluid/inference/api/demo_ci, then create and enter into directory /build, finally use cmake to generate vs2015 solution file. Commands are as follows: -`cmake .. -G "Visual Studio 14 2015 Win64" -DWITH_GPU=OFF -DWITH_MKL=OFF -DWITH_STATIC_LIB=ON -DCMAKE_BUILD_TYPE=Release -DDEMO_NAME=simple_on_word2vec -DPADDLE_LIB=path_to_the_patddle\paddle_fluid.lib` +`cmake .. -G "Visual Studio 14 2015" -A x64 -DWITH_GPU=OFF -DWITH_MKL=OFF -DWITH_STATIC_LIB=ON -DCMAKE_BUILD_TYPE=Release -DDEMO_NAME=simple_on_word2vec -DPADDLE_LIB=path_to_the_patddle\paddle_fluid.lib` Note: -- GitLab