This repo contains the scripts to use the deblending algorithm based on variational autoencoders presented in Arcelin et al. (2020). It is pip installable and can be used exclusively (for now) on images generated by the LSST DESC DC2 simulation.
An example of application of debvader
on DC2 images is presented in this tutorial.
It requires few packages to work:
scikit-image
>=0.17tensorflow
== 2.1.0tensorflow-probability
== 0.9.0scipy
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
- Bastien Arcelin - arcelin at apc.in2p3.fr
- Cyrille Doux
- Thomas Sainrat
- Biswajit Biswas
- Alexandre Boucaud
BSD 3-Clause license, see the LICENSE file for more information