tslearn-team / tslearn-team/tslearn
Soft DTW with ignore_padding_token
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.2k
- Forks
- 384
- Avg merge
- 3d 12h
- Merged PRs (30d)
- 11
Description
Hello,
I have a batch of pairs of sequences. Each pair contains sequences of different lengths, which are padded to equal lengths. Is there a way to ignore these padded elements to compute the soft-dtw alignment? For example, https://pytorch.org/docs/stable/generated/torch.nn.CrossEntropyLoss.html provides a feature to ignore a particular class index to compute cross-entropy loss.
Do you suggest any workaround to compute the dtw loss efficiently in such a case? I can only think of processing (removing paddings) each pair sample individually, but this will be too slow.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing tslearn's soft-DTW alignment behavior and the PyTorch CrossEntropyLoss ignore-index reference mentioned in the issue. Determine how padded elements should be identified and excluded in batched sequences; done means soft-DTW can handle differently sized padded pairs efficiently without processing each sample individually.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100