aidos-lab/pytorch-topological
A topological machine learning framework based on PyTorch
This is a framework for researchers and machine learning practitioners who want to build advanced machine learning models that understand the 'shape' or connectivity within data. It helps you incorporate topological insights directly into neural networks. You provide your data, and it helps you construct models that output predictions or insights enhanced by topological features, going beyond traditional geometric approaches.
202 stars.
Use this if you are developing novel machine learning algorithms and want to explore how the underlying topological structure of your data can improve model performance and provide deeper insights, especially in areas like biological image analysis.
Not ideal if you are looking for an off-the-shelf solution for standard machine learning tasks, or if you do not have a strong understanding of computational topology and PyTorch.
Stars
202
Forks
31
Language
Python
License
BSD-3-Clause
Category
Last pushed
Feb 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/aidos-lab/pytorch-topological"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
lmcinnes/umap
Uniform Manifold Approximation and Projection
pyRiemann/pyRiemann
Machine learning for multivariate data through the Riemannian geometry of positive definite...
geomstats/geomstats
Computations and statistics on manifolds with geometric structures.
higra/Higra
Hierarchical Graph Analysis
pavlin-policar/openTSNE
Extensible, parallel implementations of t-SNE