CoDeX contains learned data compression tools for JAX.

You can use this library to build your own ML models with end-to-end optimized data compression built in. It's useful to find storage-efficient representations of your data (images, features, examples, etc.) while only sacrificing a small fraction of model performance.

For a more in-depth introduction from a classical data compression perspective, consider our paper on nonlinear transform coding, or watch @jonycgn's talk on learned image compression. For an introduction to lossy data compression from a machine learning perspective, take a look at @yiboyang's review paper.

Please post all questions or comments on Discussions. Only file Issues for actual bugs or feature requests. On Discussions, you may get a faster answer, and you help other people find the question or answer more easily later.

To install CoDeX via pip, run the following command:

python -m pip install jax-codex

To test that the installation works correctly, you can run the unit tests with:

python -m pip install pytest chex tensorflow-probability
pytest --pyargs codex

Once the command finishes, you should see a message 13 passed in 2.76s or similar in the last line.

We recommend importing the library from your Python code as follows:

import codex as cdx

If you use this library for research purposes, please cite:

@software{codex_github,
  author = "Ballé, Johannes and Hwang, Sung Jin and Agustsson, Eirikur",
  title = "{CoDeX}: Learned Data Compression in {JAX}",
  url = "http://github.com/google/codex",
  version = "0.0.1",
  year = "2022",
}

In the above BibTeX entry, names are top contributors sorted by number of commits. Please adjust version number and year according to the version that was actually used.

Note that this is not an officially supported Google product.