GuyTevet / GuyTevet/motion-diffusion-model

How can I train MDM unconditionally with amass?

Open
#64 3 comments 0 reactions 0 assignees View on GitHub
enhancement wontfix
Dominant language
Python
Stars
4.1k
Forks
462
PR merge metrics
No merged PRs in 30d

Description

I tried to train MDM unconditionally using amass instead of humanact12, but the num of joints in amass is 21 while humanact has 23.

Contributor guide

No contributing guide indexed for this repository

Research direction

The issue names AMASS and HumanAct12, but it does not mention any files, tests, or entry points. Start by comparing how the two datasets represent joints and how unconditional training is configured; done means documenting or enabling a supported AMASS training path despite the 21-versus-23 joint mismatch.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.