SlipGURU Dipartimento di Informatica e Scienze dell'Informazione Università Degli Studi di Genova

Examples

All examples listed here can be found in the examples directory, either in the paddle source distribution or in the installation. To find out the exact path of the installation, you can (for instance) issue the following commands from the interpreter:

$ python
Python 2.6.5 (r265:79063, Apr 16 2010, 13:57:41)
[GCC 4.4.3] on linux2
Type "help", "copyright", "credits" or "license" for more information.
>>> import paddle
>>> print paddle.__path__
['/usr/local/lib/python2.6/dist-packages/paddle-1.0.0-py2.6.egg/paddle']

this means that the examples will be in the directory /usr/local/lib/python2.6/dist-packages/paddle-1.0.0-py2.6.egg/paddle/examples.

Experiments from [Basso10]

Some of the examples are the scripts used for the experiments presented in [Basso10], that is:

  • the two synthetic experiments of section 4.1, experiment_synthetic.py;
  • the experiment on the Berkeley Segmentation Dataset (BSD, available here), section 4.2, experiment_BSD.py;
  • the experiment on the MNIST dataset (download the dataset as a single file from here), section 4.2, experiment_MNIST.py.

All experiments can be run simply as:

$ python path_to_examples/experiment_XXXX.py [arguments if any]

The classification experiment of section 4.3 has not been included since it does involve third-parties software and its implementation is slightly more involved than a plain script.

Table Of Contents