bytedance / bytedance/1d-tokenizer

FID result can‘t match

Open
#65 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
1.2k
Forks
70
PR merge metrics
No merged PRs in 30d

Description

After testing Reproducing TiTok-L-32 and running the eval script, the FID is approximately 8.7 and cannot be matched I ran the script many times
联想截图_20241213205931

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by reproducing the TiTok-L-32 evaluation with the referenced eval script and confirm the reported FID of approximately 8.7 across repeated runs. Compare the evaluation setup and result with the expected FID, then document the cause and a reproducible resolution; the issue does not mention specific files or tests.

Written by the indexing model from the issue text.

Assessment

Tech stack
jupyter-notebook
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.