line / line/Skeleton-Temporal-Action-Localization

Masking the seq

Open
#1 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
14
Forks
1
PR merge metrics
No merged PRs in 30d

Description

I dont see any where, the padded mask applied on inputs/loss during training. Given this, a label is masked as '0', that implies a class?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by tracing the training path for padded inputs and loss computation, focusing on where labels are converted to or compared with 0. Determine whether the padded mask is applied and whether label 0 represents a class or padding; done means the behavior is documented or the missing masking behavior is clearly identified.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.