caffe-ssd

1.安装依赖

1 sudo apt-get install libprotobuf-dev libleveldb-dev libsnappy-dev libopencv-dev libhdf5-serial-dev protobuf-compiler
2 sudo apt-get install --no-install-recommends libboost-all-dev
3 sudo apt-get install libgflags-dev libgoogle-glog-dev liblmdb-dev
4 sudo apt-get install libatlas-base-dev
5 sudo apt-get install python-dev

sudo apt-get install libopenblas-dev

 sudo pip install protobuf
 sudo apt-get install liblapack3

2、下载caffe 

https://github.com/BVLC/caffe

3.编译Caffe 
（1）切换到Caffe所在目录

cp Makefile.config.example Makefile.config

（2）修改配置文件Makefile.config

• CPU_ONLY := 1
• 配置引用文件（解决新版本下，HDF5的路径问题）

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/hdf5/serial
BLAS := atlas

opencv问题：

1.$ pkg-config --modversion opencv查看是否安装

2. Makefile文件中，找到LIBRARIES（在PYTHON_LIBRARIES := boost_python python2.7 前一行）

LIBRARIES += glog gflags protobuf leveldb snappy lmdb boost_system hdf5_hl hdf5 m opencv_core opencv_highgui opencv_imgproc opencv_imgcodecs opencv_videoio

3.将Makefile.config中OPENCV_VERSION := 3取消注释;

cuda环境变量

sudo vim ~/.bashrc
export PATH=/usr/local/cuda-9.0/bin:$PATH
export LD_LIBRARY_PATH=/usr/local/cuda-9.0/lib64$LD_LIBRARY_PATH
source ~/.bashrc

（3）编译 Caffe

make all -j8
make test -j8
make runtest -j8

4.编译Python接口 
Caffe拥有pythonC++shell接口，在Caffe使用python特别方便，在实例中都有接口的说明。

sudo apt-get install python-pip

• 执行安装依赖

cd ~/caffe
sudo apt-get install gfortran
cd ./python
for req in $(cat requirements.txt); do pip install $req; done

安装完成以后，再次回到caffe根目录我们可以执行：

sudo pip install -r python/requirements.txt

就会看到，安装成功的，都会显示Requirement already satisfied, 没有安装成功的，会继续安装。

• 编译python接口

make pycaffe -j8

--结果显示ALL TESTS PASSED就安装好了！

• 运行python结构

$ python2.7
Python 2.7.12 (default, Jul  1 2016, 15:12:24) 
[GCC 5.4.0 20160609] on linux2
Type "help", "copyright", "credits" or "license" for more information.
>>> import caffe
>>> 

如果没有报错，说明caffe安装全部完成(注意：要进入caffe/python再执行python命令，否则import caffe会提示找不到caffe)！

5.在Mnist运行Lenet

• 获取数据源

./data/mnist/get_mnist.sh
./examples/mnist/create_mnist.sh

• 因为是CPU运行，所以修改在examples文件下的Mnist下的lenet_solver.prototxt中的solver_mode:CPU

solver_mode: CPU

• 训练模型

./examples/mnist/train_lenet.sh

添加python目录

vi ~/.bashrc
export PYTHONPATH=/home/username/caffe/python：$PYTHONPATH
source ~/.bashrc