facebookresearch / facebookresearch/sam2
Plans to update model weights.
- Dominant language
- Jupyter Notebook
- Stars
- 19.9k
- Forks
- 2.5k
- PR merge metrics
- No merged PRs in 30d
Description
Hello,
Are there any plans to update the model weights for the SAM2 models in this repo to match the weights used in the [online demo](https://sam2.metademolab.com/)?
I discussed with someone from Meta last week at ECCV2024 who said the SAM2 model used in the online demo is trained on the Meta dataset and many open-source datasets, however, the model released on GitHub is only trained on the Meta dataset.
I have found that the online demo works well at segmenting some underwater data that I'm using. Still, when using the notebooks provided in the repo, the SAM2 model cannot segment the objects of interest. I am interested in zero-shot segmentation approaches.
Thanks.
Contributor guide
Assessment
This issue has not been assessed yet.