README.md

metadata

license: cc-by-4.0
tags:
  - ocean
  - object-detection
  - object-localization
  - single-class

FathomNet Megalodon Detector

Model Details

• Trained by researchers at the Monterey Bay Aquarium Research Institute (MBARI).
• Ultralytics YOLOv8x
• Object detection model
• Fine-tuned to detect 1 class, called 'object', using all FathomNet localizations

Intended Use

• Post-process video and images collected by marine researchers
• Can be used to build a localized set of training images, when neither training data nor a model exists for the imagery being analyzed

Factors

• Distribution shifts related to sampling platform, camera parameters, illumination, and deployment environment are expected to impact model performance
• Evaluation was performed on an IID subset of available training data as well as out-of-distribution data

Metrics

• Normalized confusion matrix, precision-recall curve, and F1-confidence curve were evaluated at test time
• mAP@0.5 = 0.782

Training and Evaluation Data

• All publicly-available data on FathomNet

Deployment

1. Clone this repository
2. In an environment with the ultralytics Python package installed, run:

yolo predict model=best.pt