Instructions to use ghostsas001/docverify-yolo-fields with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ultralytics
How to use ghostsas001/docverify-yolo-fields with ultralytics:
# Couldn't find a valid YOLO version tag. # Replace XX with the correct version. from ultralytics import YOLOvXX model = YOLOvXX.from_pretrained("ghostsas001/docverify-yolo-fields") source = 'http://images.cocodataset.org/val2017/000000039769.jpg' model.predict(source=source, save=True) - Notebooks
- Google Colab
- Kaggle
YOLO — payslip field detector (docverify)
Finds the 10 fields of a French payslip so that an edit found by the tamper model can be pinned to net pay or gross salary instead of "pixels at (812, 640)". In docverify, an edit inside a money field is what turns a page into high risk.
Part of docverify: project · tamper model
Classes
net_paye (net pay) · brut (gross salary) · salaire_base (base salary) ·
net_avant_impot (net before tax) · cotisations (total contributions) · iban · employee ·
employer · siret · period
Results
250 synthetic test pages, scans and phone photos mixed.
| mAP50 | mAP50-95 | |
|---|---|---|
| All fields | 0.995 | 0.975 |
| Weakest field (employee name) | 0.995 | 0.943 |
19 ms per page on a T4; part of the 6.7 s full pipeline on 4 CPU threads.
Limits
Synthetic French payslips only (generated, fake people and companies); other layouts need their own field list.
License
AGPL-3.0, inherited from Ultralytics YOLO. The rest of docverify (code, tamper model) is Apache-2.0.
- Downloads last month
- 5

