Instructions to use microsoft/OmniParser-v2.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/OmniParser-v2.0 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("microsoft/OmniParser-v2.0", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Credit MultimediaTechLab/YOLO (MIT) as the base implementation for icon_detect_v3
Verified signatured10c468 -
Use 0.05 confidence threshold in icon_detect_v3 example to match icon_detect default
Verified signature9c41f16 -
Add MIT LICENSE for icon_detect_v3 and document MIT detector weights in model card
Verified signature9db5ab1
-
Keep only the YOLOv9-E inference weight
Verified signatureef77ffa -
Add YOLOv9-E interactive region detector
Verified signatureAdds the best 10-epoch YOLOv9-E detector, compact EMA weights, a portable TorchScript inference artifact, architecture config, license, and validation results.3ad0420
-
Add `handler.py` and `requirements.txt` (#23)
Verified signature- Add `handler.py` and `requirements.txt` (acd5c25b4e94f3dff29ee1a1e3b3764c75d3e5f7) - Update handler.py (1ebdf336dc12fef6aba071bb3b5a905272ede53d) - Update README.md (3655c7c72dc109866aa38022f07735f7cc475b7b) - Apply suggestions from @ThomasDh-C code review (54dd9132c195511be5b6f4dbc46f14b32934ee4f) Co-authored-by: Alvaro Bartolome <alvarobartt@users.noreply.huggingface.co>6600256
-
Linking to the Space (#1)
Verified signature- Linking to the Space (f836618135ee39af31251b0753bd7b2648eba98e) Co-authored-by: Merve Noyan <merve@users.noreply.huggingface.co>09fae83
-
fix readme
yadonglu1145937 -
fix readme
yadonglude06658
-
fix readme
yadonglu71f73b6
-
fix readme
yadonglu1863367 -
add readme
yadonglu5b4586f -
upload weights
yadonglu8d0c5ee -
initial commit
Verified signature3f0f63f