NVIDIA/torch-harmonics
Differentiable signal processing on the sphere for PyTorch
This tool helps scientists, meteorologists, or climate modelers analyze and process data that exists on the surface of a sphere, like atmospheric conditions or planetary features. It takes gridded data from a spherical surface as input and transforms it into a set of coefficients, which can then be used to model or reconstruct the data. This allows for advanced analysis and simulation of global phenomena.
650 stars. Actively maintained with 27 commits in the last 30 days.
Use this if you need to perform advanced signal processing or develop machine learning models for data distributed across a spherical surface, such as in geophysical or astrophysical applications.
Not ideal if your data is defined on a flat grid or a different geometric shape, as this tool is specifically designed for spherical data.
Stars
650
Forks
65
Language
Jupyter Notebook
License
—
Category
Last pushed
Mar 12, 2026
Commits (30d)
27
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/NVIDIA/torch-harmonics"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
kaanaksit/odak
Scientific computing library for optics, computer graphics and visual perception.
PreFab-Photonics/PreFab
Artificial nanofabrication of integrated photonic circuits using deep learning
MatthewFilipovich/torchoptics
Differentiable wave optics simulation library built on PyTorch
artificial-scientist-lab/XLuminA
XLuminA, a highly-efficient, auto-differentiating discovery framework for super-resolution microscopy.
raminmh/liquid_time_constant_networks
Code Repository for Liquid Time-Constant Networks (LTCs)