PythonOT/POT
POT : Python Optimal Transport
Implements differentiable solvers for linear, entropic, and quadratic regularized optimal transport problems using algorithms like Sinkhorn-Knopp and conditional gradient, plus specialized variants for Gromov-Wasserstein distances, unbalanced/partial OT, and domain adaptation. Provides multiple computational backends (PyTorch, JAX, TensorFlow, NumPy, CuPy) enabling seamless integration with deep learning frameworks and GPU acceleration for large-scale problems.
2,772 stars. Used by 12 other packages. Actively maintained with 1 commit in the last 30 days. Available on PyPI.
Stars
2,772
Forks
540
Language
Python
License
MIT
Category
Last pushed
Mar 11, 2026
Commits (30d)
1
Dependencies
2
Reverse dependents
12
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/PythonOT/POT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related frameworks
recursionpharma/gflownet
GFlowNet library specialized for graph & molecular data
IShengFang/SpectralNormalizationKeras
Spectral Normalization for Keras Dense and Convolution Layers
dfdazac/wassdistance
Approximating Wasserstein distances with PyTorch
iamalexkorotin/NeuralOptimalTransport
PyTorch implementation of "Neural Optimal Transport" (ICLR 2023 Spotlight)
joisino/otbook
書籍『最適輸送の理論とアルゴリズム』のサポートページです。