Skip to main content
Help us improve PyPI by participating in user testing. All experience levels needed!

Deep Learning for Astronomers with Tensorflow

Project description

Documentation Status GitHub license Build Status Coverage Status

Getting Started

astroNN is a python package to do various kinds of neural networks with targeted application in astronomy. The working principle is using Keras as model and training rapid prototyping, but at the same time take advantage of Tensorflow’s flexibility.

For non-astronomy applications, astroNN contains custom loss functions and layers which are compatible with Keras. The custom loss functions mostly designed to deal with incomplete labels. astroNN contains demo for implementing Bayesian Neural Net with Dropout Variational Inference in which you can get reasonable uncertainty estimation and other neural nets.

For astronomy applications, astroNN contains some tools to deal with APOGEE and Gaia data. astroNN is mainly designed to apply neural nets on APOGEE spectra analysis and predicting absolute magnitude from spectra using data from Gaia parallax with reasonable uncertainty from Bayesian Neural Net. Generally, astroNN can handle 2D and 2D colored images too. Currently astroNN is a python package being developed by the main author to facilitate his undergraduate research project on deep learning application in stellar and galactic astronomy using SDSS APOGEE and Gaia satellite data.

For learning purpose, astroNN includes a deep learning toy dataset for astronomer - Galaxy10.

astroNN Documentation

Quick Start guide

Galaxy10 dataset AND Galaxy10 Tutorial Notebook

Uncertainty analysis with Dropout Variational Inference Neural Nets

Gaia DR2 with astroNN result

Acknowledging astroNN

Please cite astroNN in your publications if it helps your research. Here is an example BibTeX entry:

  author={Leung & Bovy},

or AASTex

\bibitem[Leung \& Bovy (2018)]{leung2018astroNN} Leung \& Bovy 2018, astroNN GitHub,


  • Henry Leung - Initial work and developer - henrysky
    Astronomy Undergrad, University of Toronto
    Contact Henry: henrysky.leung [at]
  • Jo Bovy - Supervisor of Henry Leung - jobovy
    Astronomy Professor, University of Toronto


This project is licensed under the MIT License - see the LICENSE file for details

Project details

Release history Release notifications

This version
History Node

History Node

History Node

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Filename, size & hash SHA256 hash help File type Python version Upload date
astroNN- (8.2 MB) Copy SHA256 hash SHA256 Source None Apr 27, 2018

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging CloudAMQP CloudAMQP RabbitMQ AWS AWS Cloud computing Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page