CoralNet-Toolbox

[![python-version](https://img.shields.io/pypi/pyversions/CoralNet-Toolbox.svg)](https://pypi.org/project/CoralNet-Toolbox) [![version](https://img.shields.io/pypi/v/CoralNet-Toolbox.svg)](https://pypi.python.org/pypi/CoralNet-Toolbox) [![pypi-passing](https://github.com/Jordan-Pierce/CoralNet-Toolbox/actions/workflows/pypi.yml/badge.svg)](https://pypi.org/project/CoralNet-Toolbox) [![windows](https://github.com/Jordan-Pierce/CoralNet-Toolbox/actions/workflows/windows.yml/badge.svg)](https://pypi.org/project/CoralNet-Toolbox) [![macos](https://github.com/Jordan-Pierce/CoralNet-Toolbox/actions/workflows/macos.yml/badge.svg)](https://pypi.org/project/CoralNet-Toolbox) [![ubuntu](https://github.com/Jordan-Pierce/CoralNet-Toolbox/actions/workflows/ubuntu.yml/badge.svg)](https://pypi.org/project/CoralNet-Toolbox) [![downloads](https://static.pepy.tech/badge/coralnet-toolbox)](https://pepy.tech/projects/coralnet-toolbox)

Quick Start

Running the following command will install the coralnet-toolbox, which you can then run from the command line:

# cmd

# Install
pip install coralnet-toolbox

# Run
coralnet-toolbox

For further instructions please see the following:

Watch the Video Demos

TL;Dr

The CoralNet-Toolbox is an unofficial codebase that can be used to augment processes associated with those on CoralNet.

It uses✨Ultralytics🚀 as a base, which is an open-source library for computer vision and deep learning built in PyTorch. For more information on their AGPL-3.0 license, see here.

The toolbox also uses the following to create rectangle and polygon annotations:

Tools

Enhance your CoralNet experience with these tools:

✏️ Annotate: Create annotations freely
👁️ Visualize: See CoralNet and CPCe annotations superimposed on images
🔬 Sample: Sample patches using various methods (Uniform, Random, Stratified)
🧩 Patches: Create patches (points)
🔳 Rectangles: Create rectangles (bounding boxes)
🟣 Polygons: Create polygons (instance masks)
🦾 SAM: Use FastSAM, CoralSCOP, RepViT-SAM, EdgeSAM, MobileSAM, and SAM to create polygons
🧪 AutoDistill: Use AutoDistill to access GroundingDINO for creating rectangles
🧠 Train: Build local patch-based classifiers, object detection, and instance segmentation models
🔮 Deploy: Use trained models for predictions
📊 Evaluation: Evaluate model performance
🚀 Optimize: Productionize models for faster inferencing
⚙️ Batch Inference: Perform predictions on multiple images, automatically
↔️ I/O: Import and Export annotations from / to CoralNet, Viscore, and TagLab
📸 YOLO: Import and Export YOLO datasets for machine learning

TODO

🔍 API: Get predictions from any CoralNet source model
📥 Download: Retrieve source data from CoralNet
📤 Upload: Add images and annotations to CoralNet
📦 Toolshed: Access tools from the old repository

This site is open source. Improve this page.