microsoft / microsoft/OmniParser

Poor result on local device compared to web

Open
#313 0 comments 0 reactions 0 assignees View on GitHub

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 tested the performance of local device (GTX 1060) and web app (https://huggingface.co/spaces/microsoft/OmniParser-v2). Most of the icons are detected on the web app but only a few icons are detected locally. The problem is mainly related to YOLO prediction. I keep the following factors the same.

  • original image
  • Box Threshold = 0.05
  • IOU Threshold = 0.1
  • Icon Detect Image Size = 640 (I tried to increase the value locally but there is no improvement.)
  • No preprocessing on both sides.
  • model.pt (The YOLO model is downloaded from the repository.)

Anybody knows what makes the difference?

Image

Image

Image

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the local YOLO prediction with model.pt, the original image, and the listed box, IOU, and image-size settings. Compare its detections with the linked OmniParser-v2 web app; done means identifying and documenting the cause of the difference or a reproducible fix.

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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.