facebookresearch / facebookresearch/sam2

MOSE train finetuning

Open
#591 1 comment 0 reactions 0 assignees View on GitHub
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

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.