Caffe研究实践 一 ------环境搭建

链接：
http://www.68idc.cn/help/opersys/qt/20160513615668.html

和 TensorFlow 对应的是 Theano ， Torch ； Caffe专精于图像处理 ，Caffe方便，更快入门上手； 在通用的DL task上，Caffe不如Theano。 开发环境搭建： 一、 没有GPU learning@learning -virtual -machine :~$ lspci | grep -i nvidia learning@learning -vi

和TensorFlow对应的是Theano，Torch；
Caffe专精于图像处理，Caffe方便，更快入门上手；
在通用的DL task上，Caffe不如Theano。

开发环境搭建：

一、没有GPU

learning@learning-virtual-machine:~$ lspci | grep -i nvidia learning@learning-virtual-machine:~$ 

二、ubuntu版本

learning@learning-virtual-machine:~$ uname -m && cat /etc/*releasex86_64DISTRIB_ID=UbuntuDISTRIB_RELEASE=15.10DISTRIB_CODENAME=wilyDISTRIB_DESCRIPTION="Ubuntu 15.10"NAME="Ubuntu"VERSION="15.10 (Wily Werewolf)"ID=ubuntuID_LIKE=debianPRETTY_NAME="Ubuntu 15.10"VERSION_ID="15.10"HOME_URL="http://www.ubuntu.com/"SUPPORT_URL="http://help.ubuntu.com/"BUG_REPORT_URL="http://bugs.launchpad.net/ubuntu/"learning@learning-virtual-machine:~$ 

三、gcc

learning@learning-virtual-machine:~$ gcc --version  gcc.real (Ubuntu 5.2.1-22ubuntu2) 5.2.1 20151010Copyright (C) 2015 Free Software Foundation, Inc.This is free software; see the source for copying conditions.  There is NOwarranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.learning@learning-virtual-machine:~$ 

四、安装依赖库

learning@learning-virtual-machine:~$ sudo apt-get install libprotobuf-dev libleveldb-dev libsnappy-dev libopencv-dev libhdf5-serial-dev protobuf-compiler[sudo] password for learning: Reading package lists... DoneBuilding dependency tree      

sudo apt-get install --no-install-recommends libboost-all-dev

sudo apt-get install libatlas-base-dev

五、安装python

六、安装Opencv

安装Opencv
http://blog.csdn.net/forest_world/article/details/51372703Ubuntu

七、安装依赖库
learning@learning-virtual-machine:~$ sudo apt-get install libgflags-dev libgoogle-glog-dev liblmdb-dev
[sudo] password for learning:
Reading package lists… Done

八、下载Caffe

learning@learning-virtual-machine:~$ git clone git://github.com/BVLC/caffe.gitCloning into 'caffe'...remote: Counting objects: 34637, done.Receiving objects: 100% (34637/34637), 47.81 MiB | 81.00 KiB/s, done.remote: Total 34637 (delta 0), reused 0 (delta 0), pack-reused 34636Resolving deltas: 100% (23287/23287), done.Checking connectivity... done.

九、修改

Makefile 修改：
LIBRARIES += glog gflags protobuf boost_system boost_filesystem m hdf5_serial_hl hdf5_serial opencv_core opencv_highgui opencv_imgproc opencv_imgcodecs

这一块代码不需要修改

修改处：
caffe/examples/cpp_classification/classification.cpp文件

十、编译

learning@learning-virtual-machine:~/caffe$ cp Makefile.config.example Makefile.configlearning@learning-virtual-machine:~/caffe$ lscaffe.cloc       data      INSTALL.md               matlab     srccmake            docker    LICENSE                  models     toolsCMakeLists.txt   docs      Makefile                 pythonCONTRIBUTING.md  examples  Makefile.config          README.mdCONTRIBUTORS.md  include   Makefile.config.example  scriptslearning@learning-virtual-machine:~/caffe$ 

learning@learning-virtual-machine:~/caffe$ gedit Makefile.config

learning@learning-virtual-machine:~/caffe$ make all
出现问题：

learning@learning-virtual-machine:~/caffe$ make allPROTOC src/caffe/proto/caffe.protoCXX .build_release/src/caffe/proto/caffe.pb.ccCXX src/caffe/data_transformer.cppCXX src/caffe/common.cppCXX src/caffe/internal_thread.cppCXX src/caffe/blob.cppCXX src/caffe/data_reader.cppCXX src/caffe/parallel.cppCXX src/caffe/util/hdf5.cppIn file included from src/caffe/util/hdf5.cpp:1:0:./include/caffe/util/hdf5.hpp:6:18: fatal error: hdf5.h: No such file or directorycompilation terminated.Makefile:572: recipe for target '.build_release/src/caffe/util/hdf5.o' failedmake: *** [.build_release/src/caffe/util/hdf5.o] Error 1learning@learning-virtual-machine:~/caffe$ 

解决：
Makefile.config
INCLUDE_DIRS
/usr/include/hdf5/serial/
Makefile
LIBRARIES
hdf5_hl and hdf5 改为 hdf5_serial_hl ，hdf5_serial

出现问题：

LD -o .build_release/lib/libcaffe.so.1.0.0-rc3CXX tools/finetune_net.cppCXX/LD -o .build_release/tools/finetune_net.binCXX tools/net_speed_benchmark.cppCXX/LD -o .build_release/tools/net_speed_benchmark.binCXX tools/compute_image_mean.cppCXX/LD -o .build_release/tools/compute_image_mean.bin.build_release/lib/libcaffe.so: undefined reference to `cv::imread(cv::String const&, int)'.build_release/lib/libcaffe.so: undefined reference to `cv::imencode(cv::String const&, cv::_InputArray const&, std::vector<unsigned char, std::allocator<unsigned char> >&, std::vector<int, std::allocator<int> > const&)'.build_release/lib/libcaffe.so: undefined reference to `cv::imdecode(cv::_InputArray const&, int)'collect2: error: ld returned 1 exit statusMakefile:616: recipe for target '.build_release/tools/compute_image_mean.bin' failedmake: *** [.build_release/tools/compute_image_mean.bin] Error 1

解决方法：
Makefile
修改：
LIBRARIES += glog gflags protobuf boost_system boost_filesystem m hdf5_serial_hl hdf5_serial opencv_core opencv_highgui opencv_imgproc opencv_imgcodecs

编译成功：

make test

make runtest

[----------] 2 tests from BatchReindexLayerTest/0, where TypeParam = caffe::CPUDevice<float>[ RUN      ] BatchReindexLayerTest/0.TestForward[       OK ] BatchReindexLayerTest/0.TestForward (0 ms)[ RUN      ] BatchReindexLayerTest/0.TestGradient[       OK ] BatchReindexLayerTest/0.TestGradient (373 ms)[----------] 2 tests from BatchReindexLayerTest/0 (374 ms total)[----------] Global test environment tear-down[==========] 1058 tests from 146 test cases ran. (134225 ms total)[  PASSED  ] 1058 tests.learning@learning-virtual-machine:~/caffe$ 

十一、配置pycaffe

sudo apt-get install python-numpy python-scipy python-matplotlib python-sklearn python-skimage python-h5py python-protobuf python-leveldb python-networkx python-nose python-pandas python-gflags Cython ipython

sudo apt-get install protobuf-c-compiler protobuf-compiler

learning@learning-virtual-machine:~/caffe$ make pycaffe

learning@learning-virtual-machine:~/caffe$ make pycaffeCXX/LD -o python/caffe/_caffe.so python/caffe/_caffe.cpptouch python/caffe/proto/__init__.pyPROTOC (python) src/caffe/proto/caffe.protolearning@learning-virtual-machine:~/caffe$ 

sudo gedit /etc/profile
末尾添加： export PYTHONPATH=/path/to/caffe/python:$PYTHONPATH
用完整路径
source /etc/profile

learning@learning-virtual-machine:~/caffe$ python
Python 2.7.10 (default, Oct 14 2015, 16:09:02)
[GCC 5.2.1 20151010] on linux2
Type “help”, “copyright”, “credits” or “license” for more information.
.>>>

出现问题：

.>>> import caffeTraceback (most recent call last): File "<stdin>", line 1, in <module>ImportError: No module named caffe

解决方法：
sudo gedit /etc/profile
export PYTHONPATH=$PYTHONPATH:/home/learning/caffe/python
source /etc/profile

补充:baidu解释
Python（英国发音：/?pa?θ?n/ 美国发音：/?pa?θɑ?n/）, 是一种面向对象、解释型计算机程序设计语言，由Guido van Rossum于1989年发明，第一个公开发行版发行于1991年。
Python是纯粹的自由软件， 源代码和解释器CPython遵循 GPL(GNU General Public License)协议[1] 。
Python语法简洁清晰，特色之一是强制用空白符(white space)作为语句缩进。
Python具有丰富和强大的库。它常被昵称为胶水语言，能够把用其他语言制作的各种模块（尤其是C/C++）很轻松地联结在一起。常见的一种应用情形是，使用Python快速生成程序的原型（有时甚至是程序的最终界面），然后对其中[2] 有特别要求的部分，用更合适的语言改写，比如3D游戏中的图形渲染模块，性能要求特别高，就可以用C/C++重写，而后封装为Python可以调用的扩展类库。需要注意的是在您使用扩展类库时可能需要考虑平台问题，某些可能不提供跨平台的实现。

参考资料：Ubuntu14.04 安装Caffe
http://blog.csdn.net/u011762313/article/details/47262549