GitHub Windows版Caffe分支 Windows Caffe

安装环境

• Visual Studio 2015
  Visual Studio Professional 2015 (x86 and x64) - DVD (Chinese-Simplified)
• CMake 3.4 或更高
  cmake-3.9.1-win64-x64.msi
• Python 3.5 Anaconda x64
  Anaconda3-4.2.0-Windows-x86_64.exe
• CUDA 8.0
  CUDA下载
• cuDNN v5.1
  cuDNN 下载 需要注册
  需要使用Tensorflow最新版本需要安装cuDNN v6
• MATLAB
  需要使用Matconvnet，在CUDA8.0下，需要安装MATLAB2017a s8sh

cuDNN安装

1. 安装CUDA
2. 下载cuDNN并解压压缩包
3. 将解压后的文件夹cuda下的文件分别复制到CUDA安装目录

安装Caffe

1. D盘新建目录CaffeBuild
2. 打开cmd(命令提示符)切换到CaffeBuild目录

> d:
> cd CaffeBuild

3. 下载Caffe

D:\CaffeBuild> git clone https://github.com/BVLC/caffe.git
D:\CaffeBuild> cd caffe
D:\CaffeBuild> git checkout windows

4. 修改配置
   在D:\CaffeBuild\caffe\scripts下修改build_win.cmd文件，使用Sublime打开
   第8,9,14行

:: Default values
if DEFINED APPVEYOR (
    echo Setting Appveyor defaults
    if NOT DEFINED MSVC_VERSION set MSVC_VERSION=14
    if NOT DEFINED WITH_NINJA set WITH_NINJA=0
    if NOT DEFINED CPU_ONLY set CPU_ONLY=0
    if NOT DEFINED CUDA_ARCH_NAME set CUDA_ARCH_NAME=Auto
    if NOT DEFINED CMAKE_CONFIG set CMAKE_CONFIG=Release
    if NOT DEFINED USE_NCCL set USE_NCCL=0
    if NOT DEFINED CMAKE_BUILD_SHARED_LIBS set CMAKE_BUILD_SHARED_LIBS=0
    if NOT DEFINED PYTHON_VERSION set PYTHON_VERSION=3
    if NOT DEFINED BUILD_PYTHON set BUILD_PYTHON=1
    if NOT DEFINED BUILD_PYTHON_LAYER set BUILD_PYTHON_LAYER=1
    if NOT DEFINED BUILD_MATLAB set BUILD_MATLAB=1
    if NOT DEFINED PYTHON_EXE set PYTHON_EXE=python
    if NOT DEFINED RUN_TESTS set RUN_TESTS=1
    if NOT DEFINED RUN_LINT set RUN_LINT=1
    if NOT DEFINED RUN_INSTALL set RUN_INSTALL=1

第29行

:: Set python 3.5 with conda as the default python
    if !PYTHON_VERSION! EQU 3 (
        set CONDA_ROOT=D:\Anaconda3
    )

第74行

:: Change to 1 to use Ninja generator (builds much faster)
    if NOT DEFINED WITH_NINJA set WITH_NINJA=0

第87行

:: Change to 3 if using python 3.5 (only 2.7 and 3.5 are supported)
    if NOT DEFINED PYTHON_VERSION set PYTHON_VERSION=3

第91行

:: Change these options for your needs.
    if NOT DEFINED BUILD_PYTHON set BUILD_PYTHON=1
    if NOT DEFINED BUILD_PYTHON_LAYER set BUILD_PYTHON_LAYER=1
    if NOT DEFINED BUILD_MATLAB set BUILD_MATLAB=1

第167行添加

:: Configure using cmake and using the caffe-builder dependencies
:: Add -DCUDNN_ROOT=C:/Projects/caffe/cudnn-8.0-windows10-x64-v5.1/cuda ^
:: below to use cuDNN
cmake -G"!CMAKE_GENERATOR!" ^
      -DBLAS=Open ^
      -DCMAKE_BUILD_TYPE:STRING=%CMAKE_CONFIG% ^
      -DBUILD_SHARED_LIBS:BOOL=%CMAKE_BUILD_SHARED_LIBS% ^
      -DBUILD_python:BOOL=%BUILD_PYTHON% ^
      -DBUILD_python_layer:BOOL=%BUILD_PYTHON_LAYER% ^
      -DBUILD_matlab:BOOL=%BUILD_MATLAB% ^
      -DCUDNN_ROOT=C:\Program Files\NVIDIA GPU Computiong Toolkit\CUDA\v8.0 ^
      -DCPU_ONLY:BOOL=%CPU_ONLY% ^
      -DCOPY_PREREQUISITES:BOOL=1 ^
      -DINSTALL_PREREQUISITES:BOOL=1 ^
      -DUSE_NCCL:BOOL=!USE_NCCL! ^
      -DCUDA_ARCH_NAME:STRING=%CUDA_ARCH_NAME% ^
      "%~dp0\.."

5. 执行脚本

D:\CaffeBuild\caffe> scripts\build_win.cmd

耐心等待，希望别报错：）

下载依赖包可能因为网络原因会失败
网盘下载并放到下面这个目录下，其中users后面的路径改成你电脑的用户名
C:\Users\shuai\.caffe\dependencies\download
这个依赖包只适合这个环境，其他环境需要搞定网络后重新运行脚本

#报错
'"C:\Program Files (x86)\Microsoft Visual Studio 14.0\Common7\Tools\..\..\VC\vcvarsall.bat"' 不是内部或外部命令，也不是 可运行的程序
或批处理文件。
-- The C compiler identification is unknown
-- The CXX compiler identification is unknown
CMake Error at CMakeLists.txt:18 (project):
  No CMAKE_C_COMPILER could be found.

 CMake Error at CMakeLists.txt:18 (project):
  No CMAKE_CXX_COMPILER could be found.

-- Configuring incomplete, errors occurred!
See also "E:/CaffeBuild/caffe/build/CMakeFiles/CMakeOutput.log".
See also "E:/CaffeBuild/caffe/build/CMakeFiles/CMakeError.log".
ERROR: Configure failed

解决方法：打开VS2015安装程序，选择修改，勾选编程语言下的Visual C++

勾选Visual C++

装了两次都出现下面这个错误

#报错
CMake Error at cmake/Utils.cmake:69 (string):   
string sub-command STRIP requires two arguments.

解决方法：修改caffe\cmake下Utils.cmake，第69行加引号

# Function merging lists of compiler flags to single string.
# Usage:
#   caffe_merge_flag_lists(out_variable <list1> [<list2>] [<list3>] ...)
function(caffe_merge_flag_lists out_var)
  set(__result "")
  foreach(__list ${ARGN})
    foreach(__flag ${${__list}})
      string(STRIP ${__flag} __flag)
      set(__result "${__result} ${__flag}")
    endforeach()
  endforeach()
  string(STRIP "${__result}" __result)
  set(${out_var} ${__result} PARENT_SCOPE)
endfunction()

如果安装成功则在caffe\build\tools\Release下有可执行文件

Python接口

打开Anaconda下的Anaconda Prompt

conda config --add channels conda-forge
conda config --add channels willyd

conda install --yes cmake ninja numpy scipy protobuf==3.1.0 six scikit-image pyyaml pydotplus graphviz

E:\CaffeBuild\caffe\python下caffe文件夹复制到E:\Anaconda3\Lib\site-packages下

在cmd中输入python，执行import caffe，若没有报错，则Python接口成功配置

MATLAB接口

在E:\caffeBuild\caffe\matlab目录下MATLAB中运行>> caffe.run_tests()
把E:\CaffeBuild\caffe\matlab\+caffe\private\Release下的caffe_mexw64复制到E:\CaffeBuild\caffe\matlab\+caffe\private下
修改matlab+caffe\Net.m第72行

function delete (self)
    if self.isvalid
        caffe_('delete_net', self.hNet_self);
    end
end

下载模型，cmd在caffe根目录下执行

python scripts\download_model_binary.py models\bvlc_reference_caffenet

打开MATLAB，打开E:\CaffeBuild\caffe\matlab\demo\classification_demo.m
命令行窗口执行

im = imread('E:\CaffeBuild\caffe\examples\images\cat.jpg');

执行classification_demo.m
在MATLAB命令窗口执行help caffe，如果不报错，则MATLAB接口配置成功