facebookresearch / facebookresearch/co-tracker

Inference by segmentation mask and selected points simultaneously

Open
#147 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
5.1k
Forks
389
PR merge metrics
No merged PRs in 30d

Description

Hello. Thanks for your excellent work!
I would like to know if it is possible to inference co-tracker model prediction in segmentation mask and manually selection point at the same time.
Based on my current experimental results, the argument brought in with `segm_mask` para will be overwritten by that of `queries` para when predicting.
Always happy to hear from you.

Contributor guide

Open the contributing guide

Research direction

Start by reproducing inference with both `segm_mask` and `queries` supplied, then inspect where the two inputs are processed and why `queries` overwrites `segm_mask`. Done means the intended simultaneous behavior is established and verified, or the supported behavior is clearly documented.

Written by the indexing model from the issue text.

Assessment

Domain
computer-vision, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.