裝了好幾遍GPU版本的，出現了各種錯誤，所以簡單裝一個CPU版本先用，記錄一下各種錯誤。

安裝依賴包

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
sudo apt-get install python-dev
sudo apt-get install libatlas-base-dev
sudo apt-get install libgflags-dev libgoogle-glog-dev liblmdb-dev
sudo apt-get install python-opencv
 

如果安裝過程中出現無法定位軟體包

sudo apt-get update

下載caffe

git clone git://github.com/BVLC/caffe.git

cd caffe
cp Makefile.config.example Makefile.config


修改 Makefile.config   
gedit Makefile.config     

去掉CPU_ONLY :=1的註釋 
註釋掉CUDA有關的行： 
#CUDA_DIR := /usr/local/cuda 
#CUDA_DIR := /usr 
#CUDA_ARCH := .... 
#TEST_GPUID := 0 
去掉WITH_PYTHON_LAYER := 1的註釋

修改這一行：
# Whatever else you find you need goes here.
INCLUDE_DIRS := $(PYTHON_INCLUDE) /usr/local/include /usr/include/hdf5/serial
LIBRARY_DIRS := $(PYTHON_LIB) /usr/local/lib /usr/lib  /usr/lib/x86_64-linux-gnu /usr/lib/x86_64-linux-gnu/hdf5/serial


修改 Makefile   
gedit Makefile    

opencv_core opencv_highgui opencv_imgproc opencv_imgcodecs     
加入 opencv_imgcodecs  


 

再修改檔案時，如果開啟的檔案是空白的，可能是路徑不對，修改路徑後重新開啟。

修改   caffe/examples/cpp_classification/classification.cpp檔案

加入

#include <opencv2/imgproc/types_c.h>
#include <opencv2/objdetect/objdetect_c.h>

修改完成後編譯

make all 
make test
make runtest

沒有錯誤就是編譯成功

接下來編譯pycaffe

make pycaffe

編譯完成後測試是否可用

cd python
python

#如果出現
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
>>>