bytedance / bytedance/1d-tokenizer
512 images decoder result are extremly bad
Open
- Dominant language
- Jupyter Notebook
- Stars
- 1.2k
- Forks
- 70
- PR merge metrics
- No merged PRs in 30d
Description
Got an image like this
Is there a way to reconstruct it?
Currently only got:
Contributor guide
No contributing guide indexed for this repository
Research direction
The issue provides only two image examples and does not name a file, test, or decoder entry point. Start by locating the image decoding and reconstruction path in the repository, reproduce the reported 512-image result, and establish what reconstruction quality should be considered fixed.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- jupyter-notebook
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100