https://github.com/zzw922cn/tf2_soft_dtw

Custom TensorFlow2 implementations of forward and backward computation of soft-DTW algorithm in batch mode.
https://github.com/zzw922cn/tf2_soft_dtw

custom dtw-algorithm edit-distance gradient soft-dtw tensorflow2

Last synced: about 2 months ago
JSON representation

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

• Host: GitHub
• URL: https://github.com/zzw922cn/tf2_soft_dtw
• Owner: zzw922cn
• Created: 2021-06-01T10:14:30.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2021-06-07T03:35:27.000Z (over 3 years ago)
• Last Synced: 2023-08-09T16:48:02.098Z (over 1 year ago)
• Topics: custom, dtw-algorithm, edit-distance, gradient, soft-dtw, tensorflow2
• Language: Python
• Homepage:
• Size: 15.6 KB
• Stars: 22
• Watchers: 4
• Forks: 1
• Open Issues: 3
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
Batch Soft-DTW(Dynamic Time Warping) in TensorFlow2 including forward and backward computation

===

Custom TensorFlow2 implementations of forward and backward computation of soft-DTW(Dynamic Time Warping) algorithm in batch mode, which is proposed in paper 《Soft-DTW: a Differentiable Loss Function for Time-Series》.

I have implemented two versions of soft-DTW, one is the original paper, the other is Parallel Tacotron2's paper(with warp penalty). For latter version, I solved the equations of backward computation myself.

If you have questions or improvements about the code, welcome to submit issues ASAP!