sashakolpakov/dire-jax
DImensionality REduction in JAX
This tool helps data scientists and machine learning engineers simplify complex datasets for better visualization and analysis. You input high-dimensional data, and it outputs a lower-dimensional representation that preserves the overall structure of your data. This makes it easier to spot patterns and clusters that might be hidden in raw, high-dimensional forms.
Available on PyPI.
Use this if you need to reduce the complexity of large datasets for visualization, exploratory data analysis, or as a preprocessing step for machine learning models, especially when preserving global data structure is important.
Not ideal if you primarily work with extremely large datasets (millions of data points) on standard CPU setups without GPU acceleration, or if you need to strictly preserve local neighborhood relationships above all else.
Stars
26
Forks
4
Language
Python
License
Apache-2.0
Category
Last pushed
Nov 21, 2025
Commits (30d)
0
Dependencies
9
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/sashakolpakov/dire-jax"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
cosmosgl/graph
GPU-accelerated force graph layout and rendering
Clay-foundation/model
The Clay Foundation Model - An open source AI model and interface for Earth
nomic-ai/nomic
Nomic Developer API SDK
omoindrot/tensorflow-triplet-loss
Implementation of triplet loss in TensorFlow
poloclub/wizmap
Explore and interpret large embeddings in your browser with interactive visualization! 📍