Downloads · 30 days
0
Reef-Bleaching-Edge-Audit
SOTAagi2030/Reef-Bleaching-Edge-Audit
Reef-Bleaching-Edge-Audit is a image classification model from SOTAagi2030. Use it when you need a label for an image. It is set up for onnx. The card lists the license as apache-2.0.
This release classifies survey frames into healthy, watch, and bleached classes for offline triage. It is intended for analyst review and must not replace field verification.
Access
Public
Updated Sep 22, 2026
Repo size
41 B
Likes
0
Public
Repo makeup
Click a slice to open those files.
.md584 B · 43%
At a glance
- Task
- Image Classification
- Library
- onnx
- License
- apache-2.0
- Access
- Public
- Created
- Sep 22, 2026
- Updated
- Sep 22, 2026
- SHA
- 94341709
Model card
From the Hugging Face model README
Reef Bleaching Edge Audit
This release classifies survey frames into healthy, watch, and bleached classes for offline triage. It is intended for analyst review and must not replace field verification.
Inputs
RGB reef-camera frames are normalized according to deployment/camera_profile.yaml.
Validation
The audit split contains lagoon transects held out by monitoring site. See audit/lagoon_holdout.jsonl for the preserved evaluation examples.
- Task
- Image Classification
- Library
- onnx
- License
- apache-2.0
- Created
- Sep 22, 2026
- Updated
- Sep 22, 2026