An unofficial toolkit to supercharge your CoralNet workflows with cutting-edge computer vision
| 🎯 Smart Annotation | 🤖 AI-Powered | 🚀 Complete Pipeline |
|---|---|---|
| Create patches, rectangles, and polygons with intelligent assistance | Leverage SAM, YOLO, and foundation models | From data collection to deployment |
| Precision meets efficiency | Cutting-edge AI at your fingertips | End-to-end workflow automation |
Get up and running in seconds:
# 💻 Installation
pip install coralnet-toolbox
# 🚀 Launch
coralnet-toolbox🎉 That's it! The toolbox will open and you're ready to start annotating!
For a complete installation guide (including CUDA setup), see the Installation Documentation.
| 📖 Guide | 🎯 Purpose | 🔗 Link |
|---|---|---|
| Overview | Get the big picture | 📋 Read More |
| Installation | Detailed setup instructions | ⚙️ Setup Guide |
| Usage | Learn the tools | 🛠️ User Manual |
| Hot Keys | Keyboard shortcuts | ⌨️ Shortcuts |
| Classification | Community tutorial | 🧠 AI Tutorial |
The toolbox integrates state-of-the-art models for efficient annotation workflows:
| YOLO Family | Versions Available |
|---|---|
| 🦾 Legacy | YOLOv3 • YOLOv4 • YOLOv5 |
| 🚀 Modern | YOLOv6 • YOLOv7 • YOLOv8 |
| ⚡ Latest | YOLOv9 • YOLOv10 • YOLO11 • YOLO12 |
Powered by the Ultralytics ecosystem
| Model | Specialty | Use Case |
|---|---|---|
| 🪸 SAM | General segmentation | High-quality masks |
| 🌊 CoralSCOP | Coral-specific | Marine biology focus |
| ⚡ FastSAM | Speed optimized | Real-time annotation |
| 📱 MobileSAM | Mobile-friendly | Edge deployment |
| ✂️ EdgeSAM | Efficient | Resource-constrained |
| 🔍 RepViT-SAM | Vision transformers | Advanced features |
Powered by our xSAM integration
| Framework | Models | Capability |
|---|---|---|
| YOLOE | See Anything | Visual prompt detection |
| Transformers | Grounding DINO • OWLViT • OmDetTurbo | Zero-shot detection |
 🎯 Patch Annotation |
 📐 Rectangle Annotation |
 🔷 Multi-Polygon Annotation |
|---|
 🧠 Image Classification |
 🎯 Object Detection |
 🎭 Instance Segmentation |
|---|
 🪸 Segment Anything (SAM) |
 🔍 Polygon Classification |
 📍 Region-based Detection |
|---|
 ✂️ Cut |
 🔗 Combine |
 🎨 Simplify |
|---|
 👁️ See Anything (YOLOE) |
 🗺️ LAI Classification |
|---|
 🎬 Video Inference & Analytics |
 🔍 Data Explorer & Clustering |
|---|
- 🔥 CoralNet Download: Retrieve source data and annotations
- 🎬 Video Processing: Extract frames from video files
- 📸 Image Import: Support for various image formats
- 👆 Manual Annotation: Intuitive point, rectangle, and polygon tools
- 🤖 AI-Assisted: SAM, YOLO, and visual prompting models
- 📐 Precision Editing: Cut, combine, subtract, and simplify shapes
- 🔬 Hyperparameter Tuning: Optimize training conditions
- 🚀 Model Training: Build custom classifiers and detectors
- ⚡ Model Optimization: Production-ready deployment
- 📈 Performance Evaluation: Comprehensive model metrics
- 🎯 Batch Inference: Process multiple images automatically
- 🎥 Video Analysis: Real-time processing with analytics
- 📋 Multi-format Export: CoralNet, Viscore, TagLab, GeoJSON
See the current tickets and planned features on the GitHub Issues Page
# Create a dedicated environment (recommended)
conda create --name coralnet10 python=3.10 -y
conda activate coralnet10# Install UV for faster package management
pip install uv
# Install CoralNet-Toolbox
uv pip install coralnet-toolboxFallback: If UV fails, use regular pip:
pip install coralnet-toolbox
For CUDA-enabled systems:
# Example for CUDA 12.9
# Install PyTorch with CUDA support
uv pip install torch torchvision --index-url https://download.pytorch.org/whl/cu129 --upgradecoralnet-toolbox- 🐢 CPU only
- 🐇 Single GPU
- 🚀 Multiple GPUs
- 🍎 Mac Metal (Apple Silicon)
Click the icon in the bottom-left to see available devices
# When updates are available
uv pip install -U coralnet-toolbox==[latest_version]
Using CoralNet-Toolbox in your research?
We'd love to feature your work! Share your success stories to help others learn and get inspired.
🪸 Protecting our oceans, one annotation at a time 🪸
Coral reefs are among Earth's most biodiverse ecosystems, supporting marine life and coastal communities worldwide. However, they face unprecedented threats from climate change, pollution, and human activities.
CoralNet is a revolutionary platform enabling researchers to:
- Upload and analyze coral reef photographs
- Create detailed species annotations
- Build AI-powered classification models
- Collaborate with the global research community
The CoralNet-Toolbox extends this mission by providing advanced AI tools that accelerate research and improve annotation quality.
If you use CoralNet-Toolbox in your research, please cite:
@misc{CoralNet-Toolbox,
author = {Pierce, Jordan and Battista, Tim and Kuester, Falko},
title = {CoralNet-Toolbox: Tools for Annotating and Developing Machine Learning Models for Benthic Imagery},
year = {2025},
howpublished = {\url{https://github.com/Jordan-Pierce/CoralNet-Toolbox}},
note = {GitHub repository}
}This is a scientific product and not official communication of NOAA or the US Department of Commerce. All code is provided 'as is' - users assume responsibility for its use.
Software created by US Government employees is not subject to copyright in the United States (17 U.S.C. §105). The Department of Commerce reserves rights to seek copyright protection in other countries.
🌊 Built with ❤️ for coral reef conservation 🌊
Empowering researchers • Protecting ecosystems • Advancing science