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。
This project provides practical, hands-on examples for applying optimal transport theory to various data analysis and machine learning tasks. You input different types of data, such as image pixels or point clouds, and it helps you understand how to compare distributions, transform images, or even summarize shapes using advanced algorithms. Data scientists, machine learning engineers, and researchers working with complex data distributions would find these notebooks valuable.
100 stars. No commits in the last 6 months.
Use this if you are studying or implementing optimal transport methods and need concrete, executable examples to understand concepts like comparing point clouds, color transformations, clustering with size constraints, or shape morphing.
Not ideal if you are looking for a plug-and-play library for general-purpose data analysis without specific interest in optimal transport theory, or if you prefer a graphical user interface over programmatic notebooks.
Stars
100
Forks
10
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Oct 07, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/joisino/otbook"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PythonOT/POT
POT : Python Optimal Transport
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)