Ubuntu 14 Caffe安装（无GPU）

前提

已经安装好Anaconda、opencv2.4.8以及dlib

正文

• 安装依赖库（一）：

$ sudo apt-get install libprotobuf-dev libleveldb-dev libsnappy-dev libopencv-dev libhdf5-serial-dev protobuf-compiler
$ sudo apt-get install --no-install-recommends libboost-all-dev

• 安装BLAS：

$ sudo apt-get install libatlas-base-dev

可以安装OpenBLAS 或 MKL，以提升CPU性能，但是要修改caffe中Makefile文件…

• 安装依赖库（二）：

$ sudo apt-get install libgflags-dev libgoogle-glog-dev liblmdb-dev

• 下载Caffe

$ cd ~
$ git clone git://github.com/BVLC/caffe.git

• 编译Caffe

$ cd ~/caffe
$ cp Makefile.config.example Makefile.config

• 修改Makefile.config文件：去掉CPU_ONLY:= 1的注释

$ make all
$ make test
$ make runtest

存在问题解决

安装glog/gflags/lmdb

• 安装glog

wget https://google-glog.googlecode.com/files/glog-0.3.3.tar.gz
tar zxvf glog-0.3.3.tar.gz
cd glog-0.3.3
./configure
make
sudo make install

• 安装gflags

wget https://github.com/schuhschuh/gflags/archive/master.zip
unzip master.zip
cd gflags-master
mkdir build && cd build
export CXXFLAGS="-fPIC" && cmake .. && make VERBOSE=1
make
sudo make install

• 安装lmdb

git clone https://github.com/LMDB/lmdb
cd lmdb/libraries/liblmdb
make
sudo make install

• 安装glog
  glog安装由于无google访问权限，需离线下载安装就好

make  sudo make install

• 安装lmdb
  runtest报错：../../build/examples/lenet/convert_mnist_data.bin: error while loading shared libraries: libglog.so.0: cannot open shared object file: No such file or directory
  解决，在runtest之前修改路径如下：
  export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/lib

配置pycaffe

• 安装依赖库：

$ 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

• 编译

$ cd ~/caffe
$ make pycaffe

• 添加~/caffe/Python到$PYTHONPATH：

$ sudo gedit /etc/profile

• 末尾添加：

export PYTHONPATH=/实际path/caffe/python:$PYTHONPATH
$ source /etc/profile

• 测试是否可以引用：

$ python
Python 2.7.6 (default, Jun 22 2015, 17:58:13)
[GCC 4.8.2] on linux2
Type "help", "copyright", "credits" or "license" for more information.
>>> import caffe