Recommendation system and hardware combination: Ubuntu14.04+cuda 7.5 1, installation Cuda
Install Caffe:git clone Https://github.com/BVLC/caffe
Install the Caffe Dependency pack: http://caffe.berkeleyvision.org/
->installation Instructions
->ubuntu Installation
->sudo apt-get Install Libprotobuf-dev Libleveldb-dev Libsnappy-devlibopencv-dev Protobuf-compiler
->sudo apt-get Install--no-install-recommends Libboost-all-dev
->sudo apt-get Install Libgflags-dev libgoogle-glog-dev liblmdb-dev 2, installing Python dependency packs
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 ... Each dependent package
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-six
Makefile configuration file Configuration
1, copy the Makefile configuration file under the Caffe folder MAKEFILE.CONFIG-EXAMPLE:CP Makefile.config-examplemakefile.config
>>vimmakefile.config the file for configuration changes
Use_leveldb
Use_lmdb These two are Caffe training knowledge, because Caffe training data needs to be read from the database, this database is done by LEVELDB and Lmdb.
>>make or make-j* (indicates that several threads are compiling Caffe, which is faster)
2, the ~/caffe/build folder with CMake for the compilation is entered >>cmake. (Failure modifies vim. /cmake/dependencies.cmake need RM CMakeCache.txt, then cmake again.
>>make or make-j* (indicates that several threads are compiling Caffe, which is faster) 3, testing
./build/examples/cpp_classification/classification.bin
Definition of Models/bvlc_reference_caffenet/deploy.prototxt//model network structure
Weights in the Models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel//network
Data/ilsvrc12/imagenet_mean.binaryproto//image preprocessing, image to mean (normalized)
Data/ilsvrc12/synset_words.txt//class name of each class
Examples/images/cat.jpg//Input image