[Caffe]linux installed Caffe (without cuda) and Mnist EXAMPLE

Yesterday on the Mac toss a day is not installed successfully, at night on the Mac mounted a paralleldesktop virtual machine, and then installed Linux, 10 minutes to install, I was drunk =. =

The main process is slightly documented:

1. Installing Blas

sudo Install Libatlas-base-dev

2. Install dependencies

sudo apt-get install Libprotobuf-dev libleveldb-dev libsnappy-dev libopencv-dev libboost-all-dev Libhdf5-serial-dev Protobuf-compiler Liblmdb-dev

3. Installing Glog

This to FQ, I put on my Baidu cloud.

tar zxvf glog-0.3. 3. Tar . GZCD glog-0.3. 3 . /Configuremakesudomakeinstall

4. Installing gflags

 wget  https:// github.com/schuhschuh/gflags/archive/master.zip  unzip  Master.zip  cd gflags -master  mkdir  build && CD Buildexport cxxflags  = " -fpic  "  && CMake. && make  verbose=make  sudo  make  install  

This step requires CMake, if not installed, can be installed with sudo apt-get install CMake .

5. Installing Lmdb

git clone git://gitorious.org/mdb/mdb.gitcd mdb/libraries/liblmdbmakesudo  makeinstall

If you don't have git installed, install it with sudo apt-get install git .

6. Download Caffe

git clone git://github.com/bvlc/caffe.git

7. Installing Caffe

CP Makefile.config.example Makefile.config

Because there is no GPU here, you need to set cpu_only:= 1 in the Makefile.config file to remove the comment.

and then compile

 Make  All  Make Test  make Runtest

After installation we can try to run a lenet on the mnist.

1. Get Mnist Data first

CD Caffe. /data/mnist/get_mnist. SH

2. Then create the lenet, be sure to run the following command at the root of the Caffe, otherwise the "Build/examples/mnist/convert_mnist_data.bin:not found" error will be reported, see here. If there is no GPU, remember to set the Solver_mode in Caffe/examples/mnist/lenet_solver.prototxt to SOLVER_MODE:CPU.

./examples/mnist/train_lenet. SH

Accuracy can reach 0.9912

Reference

[1]http://blog.csdn.net/fengbingchun/article/details/45535741

[2]http://caffe.berkeleyvision.org/install_apt.html

[Caffe]linux installed Caffe (without cuda) and Mnist EXAMPLE