facebookresearch / facebookresearch/sam2
MOSE train finetuning
Open
- Dominant language
- Jupyter Notebook
- Stars
- 19.9k
- Forks
- 2.5k
- PR merge metrics
- No merged PRs in 30d
Description
Hello, thank you for your contribution. I followed your training code and fine-tuned it on MOSE. All parameters and settings remained the same, but the result was 0.75 instead of 0.79. Is there a hidden setting or other tricks?
Contributor guide
Assessment
This issue has not been assessed yet.