keonlee9420/Soft-DTW-Loss
PyTorch implementation of Soft-DTW: a Differentiable Loss Function for Time-Series in CUDA
This is a tool for machine learning practitioners and researchers working with time-series data. It helps train sequential models by providing a loss function that measures the similarity between predicted and actual time-series. You input your model's time-series predictions and the corresponding true time-series, and it outputs a differentiable loss value that can be used to optimize your model.
148 stars. No commits in the last 6 months.
Use this if you are developing or training deep learning models that generate time-series outputs and need a robust, differentiable loss function for comparing sequences.
Not ideal if you are working with non-sequential data or do not have access to a CUDA-enabled GPU.
Stars
148
Forks
11
Language
Python
License
MIT
Category
Last pushed
Aug 03, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/keonlee9420/Soft-DTW-Loss"
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