c-hofer/torchph
The essence of my research, distilled for reusability. Enjoy 🥃!
This tool helps machine learning researchers and scientists who work with complex data to understand its underlying shape and structure. It takes in data that can be represented as point clouds or graphs, and outputs 'persistent homology' information, which describes the topological features (like holes or connected components) within the data at different scales. The output helps users interpret abstract data in a more intuitive, geometric way.
No commits in the last 6 months.
Use this if you are a machine learning researcher or data scientist using PyTorch and need to extract and differentiate topological features from your data for tasks like representation learning or data analysis.
Not ideal if you are not familiar with PyTorch or the concepts of persistent homology and topological data analysis.
Stars
73
Forks
12
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Aug 13, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/c-hofer/torchph"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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