facebookresearch / facebookresearch/segment-anything
Image split body?
- Dominant language
- Jupyter Notebook
- Stars
- 54.9k
- Forks
- 6.4k
- PR merge metrics
- No merged PRs in 30d
Description
I don't want it to cut so much at once, so can I change some parameters to make it cut less and still keep the main body intact?
If there is a parameter, the element will not be cut if it is too small
Now the generated elements are too small, can we generate a distinct effect? Which parameters should be adjusted to make this work? Because I debugged all the parameters, it didn't work, the effect changed very little...Thanks for your help @likethesky @Celebio @colesbury @pdollar @minqi
Contributor guide
Research direction
The issue does not name a file, test, or entry point. Start by locating the image-splitting behavior and the parameters exposed for controlling it, then reproduce the shown over-segmentation; done means establishing whether a parameter can preserve the main body while producing fewer, larger elements.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- jupyter-notebook
- 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