https://github.com/aboucaud/debvader

Deblending astrophysical sources with variational autoencoders

https://github.com/aboucaud/debvader

Science Score: 10.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
    Links to: arxiv.org
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (8.2%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Deblending astrophysical sources with variational autoencoders

Basic Info
  • Host: GitHub
  • Owner: aboucaud
  • License: bsd-3-clause
  • Default Branch: main
  • Size: 1.66 GB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Fork of BastienArcelin/debvader
Created over 4 years ago · Last pushed over 4 years ago

https://github.com/aboucaud/debvader/blob/main/

# DebVAder: Deblending galaxies with Variational Autoencoders

[![License][license-badge]][license-web]
[![Paper][arxiv-badge]][arxiv-paper]

[license-badge]: https://img.shields.io/badge/license-BSD-blue.svg?style=flat
[license-web]: https://choosealicense.com/licenses/bsd-3-clause/
[arxiv-paper]: https://arxiv.org/abs/2005.12039
[arxiv-badge]: https://img.shields.io/badge/arXiv-2005.12039-brightgreen.svg?style=flat
[dc2-paper]: https://arxiv.org/abs/2010.05926


This repo contains the scripts to use the deblending algorithm based on variational autoencoders presented in [Arcelin et al. (2020)][arxiv-paper]. It is pip installable and can be used exclusively (for now) on images generated by the [LSST DESC DC2 simulation][dc2-paper].

## Example

An example of application of `debvader` on DC2 images is presented in [this tutorial](notebooks/deblending_dc2_images.ipynb).

## Installation

It requires few packages to work:
- `scikit-image`>=0.17
- `tensorflow` == 2.1.0
- `tensorflow-probability` == 0.9.0
- `scipy`
- `numpy`
- `matplotlib`
- `jupyter`

They can be installed with
```
pip install -r requirements.txt
```

Debvader can then be pip installed with
``` 
pip install --index-url https://test.pypi.org/simple/ debvader 
```

## Authors

- [Bastien Arcelin](https://github.com/BastienArcelin) - arcelin at apc.in2p3.fr
- [Cyrille Doux](https://github.com/xuod)
- [Thomas Sainrat](https://github.com/thuiop)
- [Biswajit Biswas](https://github.com/b-biswas)
- [Alexandre Boucaud](https://github.com/aboucaud)

## License

BSD 3-Clause license, see the [LICENSE file](LICENSE) for more information

Owner

  • Name: Alexandre Boucaud
  • Login: aboucaud
  • Kind: user
  • Location: Paris, France
  • Company: Laboratoire APC, CNRS/IN2P3

GitHub Events

Total
Last Year