facebookresearch / facebookresearch/sam2
Multiple object mask_input
Open
- Dominant language
- Jupyter Notebook
- Stars
- 19.9k
- Forks
- 2.5k
- PR merge metrics
- No merged PRs in 30d
Description
I'm trying to do real-time video segmentation by feeding each step the mask from the last inference.
It works quite well with a single object, but when trying to do it for multiple objects I can't get it to work
as mask_input expects 1XHXW
Is there any way to do this?
Contributor guide
Assessment
This issue has not been assessed yet.