Fast CUDA implementation of (differentiable) soft dynamic time warping for PyTorch

Python implementation of soft-DTW.

PyTorch implementation of Soft-DTW: a Differentiable Loss Function for Time-Series in CUDA

An implementation of soft-DTW divergences.

Dynamic Time Warping (DTW) and related algorithms in Julia, at Julia speeds

Implementation of soft dynamic time warping in pytorch

Torch implementation of Soft-DTW, supports CUDA.

Deep Non-Adversarial Gesture Generation

Custom TensorFlow2 implementations of forward and backward computation of soft-DTW algorithm in batch mode.

Fast CUDA implementation of (differentiable) otam for PyTorch using Numba

Differentiable dynamic programming operators (Soft-DTW, soft shortest path) for structured prediction and attention.