facebookresearch / facebookresearch/sam2
I want to implement video segmentation. The source code is to divide the video into images and then pass them into predictor. init_state(). Can I directly pass the URL and how to simultaneously infer the points of different frame numbers
Open
- Dominant language
- Jupyter Notebook
- Stars
- 19.9k
- Forks
- 2.5k
- PR merge metrics
- No merged PRs in 30d
Description
I want to implement video segmentation. The source code is to divide the video into images and then pass them into predictor. init_state(). Can I directly pass the URL and how to simultaneously infer the points of different frame numbers
Contributor guide
Research direction
Start by reading init_state() and the predictor call path to understand how video frames and point prompts are currently passed. Determine whether the requested URL input and simultaneous inference for points on different frame numbers fit the existing workflow; done means the supported behavior and usage are clearly established.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- jupyter-notebook
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100