Ubuntu 16.04安装tensorflow，theano，keras和caffe，针对CPU only

一，tensorflow安装

1 首先安装pip

sudo apt-get install python-pip python-dev

2 pip安装tensorflow

sudo pip install --upgrade https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.8.0-cp27-none-linux_x86_64.whl

二，theano和keras安装

1 安装环境所需要的基础

sudo apt update

sudo apt upgrade

sudo apt install -y python-dev python-pip python-nose gcc g++ git gfortran vim

sudo apt install -y libopenblas-dev liblapack-dev libatlas-base-dev

sudo pip install -U --pre pip setuptools wheel

sudo pip install -U --pre numpy scipy matplotlib scikit-learn scikit-image

sudo pip install -U --pre theano

sudo pip install -U --pre keras

2 进入python命令环境，输入import keras会出错，改一下backend

输入：gedit ~/.keras/keras.json

将tensorflow改为theano

输入：gedit ~/.theanorc

写入：

[global]
openmp=True 
device = cpu 
floatX = float32  
allow_input_downcast=True  
[blas]
ldflags= -lopenblas 

三， 安装caffe

1 安装caffe基础要求

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 libhdf5-serial-dev

sudo apt-get install python-dev

sudo apt-get install libgflags-dev libgoogle-glog-dev liblmdb-dev

2 git下载caffe

git clone https://github.com/BVLC/caffe.git

3 配置caffe下的python
cd caffe
cd python
for req in $(cat requirements.txt); do pip install $req; done
如果安装出错，使用sudo安装：
for req in $(cat requirements.txt); do sudo pip install $req; done
4 配置caffe
在caffe文件路径下
cp Makefile.config.example Makefile.config
gedit Makefile.config
修改如下：
# Whatever else you find you need goes here.
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

###python的numpy重新装一下，要不然会出错。

sudo apt-get install python-numpy

5 运行检测

make pycaffe
make all
make test
make runtest

6 配置python caffe环境

export PYTHONPATH=/path/to/caffe/python:$PYTHONPATH