PADDLE Documentation

Release:1.0.2 Date:February 28, 2011 Homepage:http://slipguru.disi.unige.it/Research/PADDLE Download:http://slipguru.disi.unige.it/Research/PADDLE/PADDLE-latest.tar.gz

PADDLE is a Python package for learning dictionaries with frame-like properties, as well as achieving sparse coding of the training data. In particular, it provides algorithms for

• learning a dictionary together with a dual of itself, and
• learning a dictionary close to a tigth-frame.

PADDLE’s license is free for both commercial and non-commercial use, under the BSD terms.

• Quickstart guide to PADDLE
  • Installation
  • A Quick Example
  • Where to go from here
• Command-line Applications
  • oneimage.py
• PADDLE algorithm (paddle.dual)
  • Main Functions
  • Inner Optimizations
• PADDLE-TF algorithm (paddle.tight)
  • Main Functions
  • Inner Optimizations
• Common and low-level functions (paddle.common)
  • Evalutation of dictionaries
  • Misc
• Data-handling functions (paddle.data)
• Examples
  • Experiments from [Basso10]

Index

References

[Basso10]

C. Basso, M. Santoro, S. Villa and A. Verri. “Learning Frames for Sparse Coding” Technical Report, DISI-TR-10-06, Università di Genova, 2010. [pdf]

Acknowledgments

We would like to thank Salvatore Masecchia and Annalisa Barla, authors of the L1L2Py package, who allowed us to use the L1L2Py website stylesheets.