PythonOT/POT
POT : Python Optimal Transport
This library helps data scientists and machine learning engineers analyze how two different datasets or signals can be optimally transformed to match each other. It takes in various types of data distributions (like images, signals, or feature sets) and outputs the most efficient "transport plan" or mapping between them. This is particularly useful for tasks such as comparing different image patterns or adapting models across varied data domains.
2,772 stars. Used by 12 other packages. Available on PyPI.
Use this if you need to compare, merge, or transform complex data distributions, especially when dealing with tasks like domain adaptation, signal alignment, or understanding structural similarities between different datasets.
Not ideal if your primary goal is simple statistical comparison using standard metrics, or if you need to solve linear programming problems that are unrelated to optimal transport.
Stars
2,772
Forks
540
Language
Python
License
MIT
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
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)
PetrMokrov/Large-Scale-Wasserstein-Gradient-Flows
Source code for Large-Scale Wasserstein Gradient Flows (NeurIPS 2021)