Ubuntu 16.4下安装caffe
1.安装caffe所需要的依赖包
sudo apt-get install git
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 libatlas-base-dev
sudo apt-get install python-dev
sudo apt-get install libgflags-dev libgoogle-glog-dev liblmdb-dev
2.下载Caffe源码：
git clone https://github.com/bvlc/caffe.git
cd caffe/
mv Makefile.config.example Makefile.config
3.修改Makefile和Makefile.config两个文件
修改：Makefile.config：（95行左右）
INCLUDE_DIRS := /usr/include $(PYTHON_INCLUDE) /usr/local/include /usr/include/hdf5/serial/
LIBRARY_DIRS :=/usr/lib $(PYTHON_LIB) /usr/local/lib /usr/lib
打开CPU_ONLY := 1（入门建议先只用cpu训练，进阶再用gpu）
修改：Makefile：（181行左右）
LIBRARIES += glog gflags protobuf boost_system boost_filesystem m hdf5_serial_hl hdf5_serial
4.在caffe根目录：
make all -j4
5.运行手写识别过程:在caffe目录下
cd data/mnist
./get_mnist.sh(若没有权限，chmod +x ./get_mnist.sh 赋予权限) 下载数据
6.转换格式
./examples/mnist/create_mnist.sh
7.训练超参数
在/examples/mnist/lenet_solver.prototxt将mode改为cpu
再运行
./build/tools/caffe train --solver=examples/mnist/lenet_solver.prototxt $@
可以看到最后的结果达到0.9917
I0705 17:10:00.829900 17611 data_layer.cpp:73] Restarting data prefetching from start.
I0705 17:10:00.991636 17608 solver.cpp:398] Test net output #0: accuracy = 0.9917
I0705 17:10:00.991662 17608 solver.cpp:398] Test net output #1: loss = 0.0268429 (* 1 = 0.0268429 loss)
I0705 17:10:00.991664 17608 solver.cpp:316] Optimization Done.
I0705 17:10:00.991667 17608 caffe.cpp:259] Optimization Done.
