toinsson/pysdtw
Torch implementation of Soft-DTW, supports CUDA.
This project offers a highly optimized tool for calculating the similarity between different time series data. It takes in various time series, even those with different lengths, and outputs a 'distance' score indicating how alike or unalike they are. This is particularly useful for machine learning engineers, data scientists, and researchers working with sequential data who need an efficient way to compare time-series patterns.
Used by 1 other package. Available on PyPI.
Use this if you are a machine learning engineer or data scientist working with time series data and need to calculate differentiable distances between sequences efficiently, especially on GPU hardware.
Not ideal if you are an end-user needing to compare time series without writing Python code or if you don't require gradient computation for machine learning models.
Stars
49
Forks
2
Language
Python
License
MIT
Category
Last pushed
Jan 25, 2026
Commits (30d)
0
Dependencies
2
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/toinsson/pysdtw"
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