NVlabs / NVlabs/dexplore

List of selected GRAB training sequences

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

Nobody has claimed this yet.

Dominant language
Python
Stars
10
Forks
3
PR merge metrics
No merged PRs in 30d

Description

Hello, excellent work!

I’m trying to reproduce your results and ran into a question about data filtering. The paper mentions you selected 658 single-hand sequences from GRAB for training, but the original dataset contains quite a few sequences that aren’t suitable for single-hand manipulation — like lifting clips and bimanual interaction tasks.

I was wondering if you have a concrete list (e.g. sequence IDs / indices) of exactly which 658 clips were used for training . It would help a lot for alignment if you could share it.

Thanks!

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

No file or test is named; start by checking the paper’s description of the 658 GRAB training sequences against the original dataset metadata. Done means publishing a concrete sequence ID or index list that reproduces the stated single-hand training subset.

Written by the indexing model from the issue text.

Assessment

Domain
data, machine-learning
Issue type
Documentation
Difficulty
3/5
Estimated time
1-2 days
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
48/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.