Linux上安装深度学习环境

OS: Linux: Ubuntu 14.04

安装：

1. Pip (Python 2.7.9或以上自带pip）： sudo apt-get install python-pip

2. 尝试安装scikit-neuralnetwork: 需要 numpy scipy theano

    sudo pip install scikit-neuralnetwork
    错误：SystemError: cannot compile "python.h". Perhaps you need to install python-dev|python-devel
    
    解决方法：
    sudo apt-get update
    sudo apt-get upgrade gcc
    sudo apt-get install python2.7-dev 
   

3. 安装numpy, scipy, theano：

    sudo pip install numpy scipy Theano 
    
    错误：numpy.distutils.system_info.NotFoundError: no lapack/blas resources found
   
    解决方法：sudo apt-get install libblas-dev liblapack-dev libatlas-base-dev gfortran
    
    sudo pip install numpy==1.12 scipy==0.17.1 Theano==0.8 
   

4. 安装Pylearn2

    sudo pip install -e git+https://github.com/lisa-lab/pylearn2.git#egg=Package
   
    需要git
   
    sudo apt-get install git
   

5. 安装scikit-neuralnetwork

    git clone https://github.com/aigamedev/scikit-neuralnetwork.git
    cd scikit-neuralnetwork;
    sudo python setup.py develop
   

6. 测试

    sudo pip install nose
    nosetests -v sknn.tests
   
   
    需要安装:
    安装pandas：sudo pip install pandas；
    matplotlib: sudo pip install matplotlib
   
    错误：The following package could not be built: freetype, png
   
    解决方法：
    sudo apt-get install libpng-dev libjpeg8-dev libfreetype6-dev
   
    python3要使用matplotlib还要装下面两条：
    sudo apt install python3-tk
    sudo apt install tk-dev
   

7. 视觉化显示：

    python examples/plot_mlp.py --params activation
   

8. 在MNIST上测试

    python examples/bench_mnist.py (sknn|lasagne)