ByteDance-Seed / ByteDance-Seed/Depth-Anything-3
training detals for DA3-Large
Open
- Dominant language
- Python
- Stars
- 6.3k
- Forks
- 702
- PR merge metrics
- No merged PRs in 30d
Description
Hi, thank you for your great work. May I ask whether the smaller DA3 models (e.g., DA3-BASE and DA3-Large) are distilled from DA3-GIANT, or trained directly using the same procedure as the largest model?
Contributor guide
No contributing guide indexed for this repository
Research direction
No file, test, or entry point is named. Start by locating the repository's training documentation or configuration for DA3-BASE, DA3-Large, and DA3-GIANT; done means documenting whether the smaller models are distilled from DA3-GIANT or trained directly, with the relevant procedure identified.
Written by the indexing model from the issue text.
Assessment
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100