linux下安装kears

 

2. 安装python基础开发包
   # 系统升级 
    sudo apt update 
    sudo apt upgrade

    sudo apt install -y python-dev python-pip python-nose gcc g++ git gfortran vim
3.安装运算加速库
    sudo apt install -y libopenblas-dev liblapack-dev libatlas-base-dev
4.安装相关开发包
    安装pip ,  sudo pip install -U --pre pip setuptools wheel
    安装numpy,scipy, matplotlib,scklearn包 ， sudo pip install -U --pre numpy scipy matplotlib scikit-learn scikit-image
    安装theano， sudo pip install -U --pre theano
    安装keras，sudo pip install -U --pre keras 
    安装tensorflow，sudo pip install --upgrade https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.8.0-cp27-none-linux_x86_64.whl
   

5.keras环境设置
   1）修改默认keras后端 在终端中输入:

      gedit ~/.keras/keras.json

         2）配置theano文件 在终端中输入:

       gedit ~/.theanorc
6.本人采用的是cpu加速，故在theanorc中输入
   [global] 
    openmp=True 
    device = cpu 
    floatX = float32 
    allow_input_downcast=True
    [blas] ldflags= -lopenblas