microsoft / microsoft/OmniParser
OutOfMemoryError: CUDA out of memory when the keyboard on the phone screenShot
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 25.4k
- Forks
- 2.2k
- PR merge metrics
- No merged PRs in 30d
Description
I’ve been using OmniParse 1.0, and it often crashes due to exceeding the maximum GPU memory when there’s a keyboard in the current phone screenshot. However, everything works fine when there’s no keyboard present. My maximum GPU memory is 11GB. Could it be that when a keyboard is present, there are more small images(A,B,C.....), so the total GPU usage for image recognition increases?
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No source files, tests, or entry points are named. Reproduce the CUDA out-of-memory crash with a phone screenshot containing a keyboard, compare it with a screenshot without one, and inspect GPU usage during image recognition; done means the keyboard case no longer exceeds the available 11GB GPU memory.
Written by the indexing model from the issue text.
Assessment
- Domain
- computer-vision, machine-learning, mobile-dev
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100