facebookresearch / facebookresearch/sam2

Multiple object mask_input

Open
#240 2 comments 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

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

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.