DREEM Relates Every Entity's Motion

Welcome to the documentation for DREEM – an open-source tool for multiple object tracking. DREEM is a framework that enables you to train your own models, run inference on new data, and evaluate your results. DREEM supports a variety of detection types, including keypoints, bounding boxes, and segmentation masks. You can use any detection model you want, convert the output to a format DREEM can use, and train a model or run inference using a pretrained model.

Key Features

• Command-Line & API Access: Use DREEM via a simple CLI or integrate into your own Python scripts.
• Configurable Workflows: Easily customize training and inference using YAML configuration files.
• Pretrained Models: Get started quickly with models trained specially for microscopy and animal domains.
• Visualization: Tracking outputs are directly compatible with SLEAP's GUI.
• Examples: Step-by-step notebooks and guides for common workflows.

Installation

Head over to the Installation Guide to get started.

Quickstart

Ready to try DREEM? Follow the Quickstart Guide to:

1. Download example datasets and pretrained models
2. Run tracking on sample videos
3. Visualize your results

Example Workflows

Explore the Examples section for notebooks that walk you through the DREEM pipeline. We have an end-to-end demo that includes model training, as well as a microscopy example that shows how to use DREEM with an off-the-shelf detection model.

Documentation Structure

• Installation
• Quickstart
• Usage Guide
• Examples
• API Reference

Get Help

• Questions? Open an issue on GitHub.
• Contributions: We welcome contributions! See our Contributing Guide for details (link to be added).