DeepTrack as Community Partner #172
Description
- Description of your software, organization, company or team.
DeepTrackAI is an open-source organization dedicated to advancing deep learning tools for microscopy and related fields. Our mission is to provide researchers and developers with robust, flexible, and user-friendly software solutions to facilitate quantitative digital microscopy. We develop tools that support both simulation and analysis of microscopy data, making deep learning accessible and effective.
- Description of the resources that you plan to contribute. Please also include the url to your project repo.
We plan to contribute deep learning models from DeepTrack2 and deeplay, which are designed for a range of microscopy tasks, including cell detection and tracking. DeepTrack2 is a flexible Python library for simulating microscopy data, making it easy to generate physics-based synthetic datasets for training deep learning models without the need for manual annotation. Deeplay is a modular deep learning framework built on PyTorch, designed to simplify the development of customizable and reusable neural network models. Its design encourages reproducibility and scalability, providing researchers with efficient tools for building and deploying deep learning models across a wide range of applications, including image analysis.
- Description of future plans on how your project will be maintained.
To ensure the longevity and effectiveness of these tools, we actively maintain and develop them by introducing new functionalities, refining existing code, and incorporating community feedback.
These codes are actively maintained by the groups of Giovanni Volpe at the University of Gothenburg, Sweden, and of Carlo Manzo at the University of Vic, Spain.
Our main project repositories are available at:
DeepTrack2: https://github.com/DeepTrackAI/DeepTrack2
deeplay: https://github.com/DeepTrackAI/deeplay