The Galaxy Morphology Network (GaMorNet) is a convolutional neural network that can classify galaxies as being disk-dominated, bulge-dominated or indeterminate based on their bulge to total light ratio. GaMorNet doesn’t need a large amount of training data and can work across different data-sets. For more details about GaMorNet’s design, how it was trained etc., please refer to Publication & Other Data.

Schematic diagram of Galaxy Morphology Network.

## First contact with GaMorNet¶

GaMorNet’s user-faced functions have been written in a way so that it’s easy to start using them even if you have not dealt with convolutional neural networks before. For. eg. to perform predictions on an array of SDSS images using our trained models, the following line of code is all you need.

from gamornet.keras_module import gamornet_predict_keras



In order to start using GaMorNet, please first look at the Getting Started section for instructions on how to install GaMorNet. Thereafter, we recommend trying out the Tutorials in order to get a handle on how to use GaMorNet.

Finally, you should have a look at the Public Data Release Handbook for our recommendations on how to use different elements of GaMorNet’s public data release for your own work and the API Documentation for detailed documentation of the different functions in the module.

## Publication & Other Data¶

You can look at this ApJ paper to learn the details about GaMorNet’s architecture, how it was trained, and other details not mentioned in this documentation.

We strongly suggest you read the above-mentioned publication if you are going to use our trained models for performing predictions or as the starting point for training your own models.

All the different elements of the public data release (including the new Keras models) are summarized in Public Data Release Handbook.

Please cite the above mentioned publication if you make use of this software module or some code herein.

@article{Ghosh2020,
doi = {10.3847/1538-4357/ab8a47},
url = {https://doi.org/10.3847/1538-4357/ab8a47},
year = {2020},
month = jun,
publisher = {American Astronomical Society},
volume = {895},
number = {2},
pages = {112},
author = {Aritra Ghosh and C. Megan Urry and Zhengdong Wang and Kevin Schawinski and Dennis Turp and Meredith C. Powell},
title = {Galaxy Morphology Network: A Convolutional Neural Network Used to Study Morphology and Quenching in $\sim$100, 000 {SDSS} and $\sim$20, 000 {CANDELS} Galaxies},
journal = {The Astrophysical Journal}
}


Additionally, if you want, please include the following text in the Software/Acknowledgment section.

This work uses trained models/software made available as a part of the Galaxy Morphology Network public data release.


If you have a question, please first have a look at the FAQs section. If your question is not answered there, please send me an e-mail at this aritraghsh09+gamornet@xxxxx.com GMail address.