28 lines
680 B
Markdown
28 lines
680 B
Markdown
|
# Contradiction Gap Analysis
|
||
|
|
|
||
|
|
VIMS instance for contradiction-gap.
|
||
|
|
|
||
|
|
## Related Article
|
||
|
|
[/insights/contradiction-gap/](https://landvex.com/insights/contradiction-gap/)
|
||
|
|
|
||
|
|
## Anomaly Classes
|
||
|
|
- official_mismatch
|
||
|
|
- reported_vs_observed
|
||
|
|
- data_conflict
|
||
|
|
- unrecorded_change
|
||
|
|
- false_claim
|
||
|
|
|
||
|
|
## Quick Start
|
||
|
|
|
||
|
|
1. Add training images to `data/raw/`
|
||
|
|
2. Annotate using LabelImg (YOLO format)
|
||
|
|
3. Run preprocessing: `python src/detector.py`
|
||
|
|
4. Train model: `python src/detector.py --train`
|
||
|
|
5. Run inference: `python src/detector.py --predict data/test/image.jpg`
|
||
|
|
|
||
|
|
## API
|
||
|
|
|
||
|
|
Once deployed, access via:
|
||
|
|
- REST: `POST /api/contradiction-gap/predict`
|
||
|
|
- WebSocket: `ws://host/ws/contradiction-gap/alerts`
|