Transformer based embeddings for Wasserstein Distances
Project description
WassersteinWormhole for Python3
Embedding point-clouds by presering Wasserstein distancse with the Wormhole.
This implementation is written in Python3 and relies on FLAX, JAX, JAX-OTT.
To install JAX, simply run the command:
pip install --upgrade "jax[cuda11_pip]" -f https://storage.googleapis.com/jax-releases/jax_cuda_releases.html
And to install WassersteinWormhole along with the rest of the requirements:
pip install WassersteinWormhole
And running the Womrhole on your own set of point-clouds is as simple as:
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Close
Hashes for wassersteinwormhole-0.1.1.tar.gz
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 7bedcad7073974bda6f7e0a24727ded019482b0d9d359ee478da6716be9397f6 |
|
| MD5 | 871f7ddb23cae76354a76a73f2b0a518 |
|
| BLAKE2b-256 | 46186a271e72d91c2b49c14b06c28706a276acbb1ae66673c7c181cb598486c4 |
Close
Hashes for wassersteinwormhole-0.1.1-py3-none-any.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 71ece6d91df4a1e1a5f96aedd32b444e7009333fdfe16f7fbd7f39b817abfab3 |
|
| MD5 | 67ccba8a3efbf16c6d5ee1a925c22898 |
|
| BLAKE2b-256 | c41da74e9cb081fac94f0042afdc2ba157090dc1b6c7b562be91c6f22d43fed6 |
