2.2 深度学习环境配置分部详解

OS: Linux: Ubuntu 14.04

安装：

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

1. 安装numpy, scipy, theano：
   pip install numpy scipy theano
   sudo pip install numpy scipy theano (1:03:32)

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 scipy
sudo pip install Theano

1. 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

1. 安装scikit-neuralnetwork

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

1. 测试

sudo pip install nose
nosetests -v sknn.tests

需要安装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
sudo apt-get install libjpeg8-dev
sudo apt-get install libfreetype6-dev

1. 视觉化显示：

   python examples/plot_mlp.py –params activation

2. 在MNIST上测试

   python examples/bench_mnist.py (sknn|lasagne)