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
#574 1 comment 1 reaction 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 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

Open the contributing 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.