How karthik252007/debris-detection works
SONARX is a small Streamlit prototype: a user uploads a sonar image and sets a confidence threshold, the app runs YOLO inference, then displays an annotated image and per-detection details. The sampled app shows the inference and reporting path; the README documents a training notebook, but its contents were not sampled, so no internal training relationships are inferred.
Main entry points: app.py YOLO inference · debris.pt YOLO weights
Components 7
Detection app
- Upload and threshold
app.py - YOLO inference
app.py - YOLO weights
debris.pt - Detection report
app.py
Model training
- Training workflow
debris_detection_Autonomous_underwater_vehicles.ipynb
Other components
- Image user
- Ultralytics YOLO
Connections 7
- Image user → Upload and threshold: uploads image
app.py - Image user → Upload and threshold: sets threshold
app.py - Upload and threshold → YOLO inference: submits image
app.py - YOLO inference → Ultralytics YOLO: calls predict
app.py - YOLO inference → YOLO weights: loads weights
app.py - YOLO inference → Detection report: provides detections
app.py - Detection report → Image user: displays results
app.py