mini-vec2vec 0.1.1

Python implementation of the mini-vec2vec paper

mini-vec2vec

This is a python package implementation of the mini-vec2vec: Scaling Universal Geometry Alignment with Linear Transformations paper.

This is not the official python implementation that is used in the paper, that code can be found here. All credit goes to guy-dar, this just takes his work but puts it into a package.

Install

pip install mini-vec2vec

Contribute

Create a venv and install the dev dependencies. (I have used UV to create this package)

python3 -m venv .venv
source .venv/bin/activate
pip install uv
uv sync
uvx pre-commit install

Testing

uv pip install -e .
uv run pytest

---

TODO:

• Docs (zensical)
• Code Improvements:
  • Make some of the hard coded values variables
• Performance Improvements:
  • Use float32 numpy arrays
  • Use from scipy.optimize import linear_sum_assignment rather than QAP or reduce number of QAP loops
  • MiniBatchKMeans instead of Kmeans
  • Concatenate rather than vstack
• Add in original Vec2Vec method