推荐系统与硬件组合:Ubuntu14.04+cuda 7.5
安装caffe:Git clone https://github.com/BVLC/caffe
安装caffe依赖包:http://caffe.berkeleyvision.org/
->Installation instructions
->Ubuntu installation
->sudo apt-get install libprotobuf-dev libleveldb-dev libsnappy-devlibopencv-dev libhdf5-serial-dev protobuf-compiler
->sudo apt-get install --no-install-recommends libboost-all-dev
->sudo apt-get install libgflags-dev libgoogle-glog-dev liblmdb-dev
Cython>=0.19.2
numpy>=1.7.1
scipy>=0.13.2
scikit-image>=0.9.3
matplotlib>=1.3.1
ipython>=3.0.0
h5py>=2.2.0
leveldb>=0.191
networkx>=1.8.1
nose>=1.3.0
pandas>=0.12.0
python-dateutil>=1.4,<2
protobuf>=2.5.0
python-gflags>=2.0
pyyaml>=3.10
Pillow>=2.3.0
six>=1.1.0
Cd caffeàless python/requirements.txt
Sudo apt-getinstall …各依赖包
Eg: sudo apt-getinstall cython python-numpy python-scipy python-scikits-learn python-matplotlibipython python-h5py python-leveldb python-networkx python-nose python-pandaspython-dateutil python-protobuf python-gflags python-yaml python-six
Makefile配置文件的配置
1、复制Caffe文件夹下的Makefile的配置文件Makefile.config-example:cp Makefile.config-exampleMakefile.config
>>vimMakefile.config对该文件进行配置修改
USE_LEVELDB
USE_LMDB 此两个是caffe的训练知识,因为caffe的训练数据需要从数据库里读出来,此数据库由LEVELDB和LMDB来做。
>>make或make -j*(表示有几个线程在编译caffe,这样比较快)
2、进行~/caffe/build文件夹用cmake进行编译即输入>>cmake.. (失败修改vim ../cmake/Dependencies.cmake后需要rm CMakeCache.txt,再重新cmake ..)
>>make或make -j*(表示有几个线程在编译caffe,这样比较快)
./build/examples/cpp_classification/classification.bin
models/bvlc_reference_caffenet/deploy.prototxt //模型网络结构的定义
models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel //网络中的权值
data/ilsvrc12/imagenet_mean.binaryproto //图像预处理,图像去均值化(归一化)
data/ilsvrc12/synset_words.txt //每个类的类名
examples/images/cat.jpg //输入图像