microsoft / microsoft/OmniParser
The model produced different results
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 25.4k
- Forks
- 2.2k
- PR merge metrics
- No merged PRs in 30d
Description
Use same image
The results get from running gradio_demo.py locally are significantly different from the results obtained from the website ：https://huggingface.co/spaces/microsoft/OmniParser-v2,The website is much more accurate.
For example：
the back icon in the browser, the “content” value returned in the website is 'BACK', while the “content” value in the Demo is 'the push pin or pinning function.' What causes this difference?
I am using microsoft/Florence-2-base-ft to interpret the icons, with
generated_ids = @model.generate(input_ids=inputs["input_ids"],pixel_values=inputs["pixel_values"],max_new_tokens=20,num_beams=1, @do_sample=False)."
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
Start with gradio_demo.py and compare its Florence-2 configuration and generation call with the configuration used by the linked Hugging Face Space. Reproduce the back-icon example using the same image, then identify the differing input or inference setting. Done means the local and website results are consistent, or the cause of the discrepancy is documented.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100