yhtang/FunFact
Tensor decomposition with arbitrary expressions: inner, outer, elementwise operators; nonlinear transformations; and more.
This tool helps researchers and engineers break down complex, multi-dimensional datasets (tensors) into simpler components. You provide your raw data and a mathematical formula describing how you think it's structured, and it outputs the underlying factors. It's designed for quantitative scientists and specialized engineers who work with high-dimensional data in fields like quantum computing or large-scale data analysis.
No commits in the last 6 months. Available on PyPI.
Use this if you need to perform custom tensor decomposition or factorization to uncover hidden structures in your multi-dimensional data, especially when standard methods don't fit your specific model.
Not ideal if you're looking for a straightforward, off-the-shelf data analysis tool without needing to define custom mathematical expressions.
Stars
59
Forks
4
Language
Python
License
—
Category
Last pushed
Sep 15, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yhtang/FunFact"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pymc-devs/pytensor
PyTensor allows you to define, optimize, and efficiently evaluate mathematical expressions...
arogozhnikov/einops
Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)
lava-nc/lava-dl
Deep Learning library for Lava
tensorly/tensorly
TensorLy: Tensor Learning in Python.
tensorpack/tensorpack
A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility