Pylearn2的使用简介

环境: ubuntu 12.4

Pylearn2是基于theano上封装的深度学习包。 它实现一些常见的模型，具体请参考： http://deeplearning.net/software/pylearn2/library/index.html#libdoc，比theano在做实际的项目节约时间，只需要配置一些参数来实现模型的训练。 
下面来讲解实际的安装和使用：

1. 安装 Theano（Bleeding-edge install instruction）

    jerry@hq:~$sudo pip install --upgrade --no-deps git+git://github.com/Theano/Theano.git --user

2. 下载Pylearn2
      jerry@hq:~$ git clone git://github.com/lisa-lab/pylearn2.git 

3.  安装pylearn2
     jerry@hq:~$cd pylearn2
    jerry@hq:~$sudo python setup.py develop --user

4. 测试安装成功
    jerry@hq:~$python
    import pylearn2
    能加载包即安装ok

5. 设置PYTHON2_DATA_PATH, PYLEARN2_VIEWR_COMMAND
    vi ~/.bashrc
    添加 
    export PYLEARN2_DATA_PATH=/u01/lisa/data
     export PYLEARN2_VIEWER_COMMAND=/usr/bin/eog

如何运行一个示例

1. 下载数据 
   cd /u01/lisa/data/cifar10
    wget http://www.cs.utoronto.ca/~kriz/cifar-10-python.tar.gz
   tar xvf cifar-10-python.tar.gz

2. 修改make_dataset.py文件 ，指定路径/u01/lisa/data/ (由于本机上/空间不足，只能把数据放在其它路径上)
   jerry@hq:~$vi /home/jerry/pylearn2/pylearn2/scripts/tutorials/grbm_smd/make_dataset.py
  修改成这样：
   """
    path = pylearn2.__path__[0]
    train_example_path = os.path.join(path, 'scripts', 'tutorials', 'grbm_smd')
    train.use_design_loc(os.path.join(train_example_path, 'cifar10_preprocessed_train_design.npy'))
    train_pkl_path = os.path.join(train_example_path, 'cifar10_preprocessed_train.pkl')
    """
    train_pkl_path = os.path.join('/u01/lisa/data/', 'cifar10_preprocessed_train.pkl')
    serial.save(train_pkl_path, train)

3. 对下载数据进行数据预处理
   python /home/jerry/pylearn2/pylearn2/scripts/tutorials/grbm_smd/make_dataset.py
    处理完后在目录/u01/lisa/data下有一个文件 cifar10_preprocessed_train.pkl，大概652M左右

4. 对数据进行训练
   cd /u01/lisa/data
   python ~/pylearn2/pylearn2/scripts/train.py ~/pylearn2/pylearn2/scripts/tutorials/grbm_smd/cifar_grbm_smd.yaml

5. 查看结果
    python ~/pylearn2/pylearn2/scripts/show_weights.py ~/pylearn2/pylearn2/scripts/tutorials/grbm_smd/cifar_grbm_smd.pkl    

   python ~/pylearn2/pylearn2/scripts/plot_monitor.py ~/pylearn2/pylearn2/scripts/tutorials/grbm_smd/cifar_grbm_smd.pkl

   python ~/pylearn2/pylearn2/scripts/print_monitor.py ~/pylearn2/pylearn2/scripts/tutorials/grbm_smd/cifar_grbm_smd.pkl

    python ~/pylearn2/pylearn2/scripts/summarize_model.py ~/pylearn2/pylearn2/scripts/tutorials/grbm_smd/cifar_grbm_smd.pkl

6. 直接查看生成参数的文件 cifar_grbm_smd.pkl

加载模型文件
>>> from pylearn2.utils import serial
>>> model = serial.load('/home/jerry/pylearn2/pylearn2/scripts/tutorials/grbm_smd/cifar_grbm_smd.pkl')
查下文件结构
>>> dir(model)
获取权重参数
>>> model.get_weights()
获取参数名
>>> model.get_params()
获取参数值
>>> model.get_param_values()

来自 “ ITPUB博客 ” ，链接：http://blog.itpub.net/16582684/viewspace-1242503/，如需转载，请注明出处，否则将追究法律责任。

转载于:http://blog.itpub.net/16582684/viewspace-1242503/