下面介绍在Ubuntu上不带CUDA的Caffe配置编译过程(这里没有安装matlab，python,opencv)：
1.安装BLAS：$ sudo apt-get install libatlas-base-dev
2.安装依赖项：$ sudo apt-get install libprotobuf-dev libleveldb-dev libsnappy-dev libopencv-dev libboost-all-dev libhdf5-serial-dev protobuf-compiler liblmdb-dev
$ sudo apt-get install libgflags-dev libgoogle-glog-dev liblmdb-dev
3.下载Caffe：$ Git clone git://github.com/BVLC/caffe.git
4.修改 caffe目录下的Makefile.config，Makefile
cd caffe ;
gedit Makefile.config;
在Makefile.config文件的第85行，添加 /usr/include/hdf5/serial/ 到 INCLUDE_DIRS，也就是把下面第一行代码改为第二行代码。
INCLUDE_DIRS := $(PYTHON_INCLUDE) /usr/local/include
INCLUDE_DIRS := $(PYTHON_INCLUDE) /usr/local/include /usr/include/hdf5/serial/
# Uncomment to support layers written in Python (will link against Python libs)
# WITH_PYTHON_LAYER := 1
# 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
gedit Makefile;
在Makefile文件的第173行，把 hdf5_hl 和hdf5修改为hdf5_serial_hl 和 hdf5_serial，也就是把下面第一行代码改为第二行代码。
LIBRARIES += glog gflags protobuf boost_system boost_filesystem m hdf5_hl hdf5
LIBRARIES += glog gflags protobuf boost_system boost_filesystem m hdf5_serial_hl hdf5_serial
INCLUDE_DIRS += $(BUILD_INCLUDE_DIR) ./src ./include
ifneq ($(CPU_ONLY), 1)
INCLUDE_DIRS += $(CUDA_INCLUDE_DIR)
LIBRARY_DIRS += $(CUDA_LIB_DIR)
LIBRARIES := cudart cublas curand
endif
LIBRARIES += glog gflags protobuf boost_system boost_filesystem m hdf5_serial_hl hdf5_serial
5.安装Caffe： $cd caffe
(1)、$ cp Makefile.config.example Makefile.config
(2)、修改Makefile.config文件：去掉注释, CPU_ONLY:= 1
(3)、$ make all
(4)、$ make test
(5)、$ make runtest
说明：1.make all步骤出现错误
./include/caffe/util/hdf5.hpp:6:18: fatal error: hdf5.h: No such file or directory
解决方法如步骤4
2.编译带CUDA支持的Caffe与上面的步骤完全一致，只要把CPU_ONLY:=1注释掉即可。