facebookresearch / facebookresearch/segment-anything
Running out of memory
Open
- Dominant language
- Jupyter Notebook
- Stars
- 54.9k
- Forks
- 6.4k
- PR merge metrics
- No merged PRs in 30d
Description
Hi all,
I am trying to segment a large image (225Mb), unfortunately, the process stops due to a lack of RAM memory. I have 20Gb of RAM available but it seems this is not enough.
Is there a solution to avoid using all the available memory?
Contributor guide
Research direction
Start by reproducing segmentation of the 225 MB image while monitoring RAM, then inspect the example notebooks and inference path used by the repository. Done means a documented or tested approach can segment the reported image without exhausting the available memory.
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