Most of the academic code I develop is open and lives on Github, or at least that how it was until the beginning of 2020. During the past few months, I have been using a private Gitlab server at the Barcelona Supercomputing Center. My plan is to start mirroring some repositories to increase my activity on Github and the visibility of my code.

Below, are highlighted some repositories with code for past projects on astronomical high-contrast imaging (in which I am no longer involved):


The SODINN package is the consolidation and evolution of the framework proposed in Gomez Gonzalez et al. 2018. This is work in progress and is being developed “in the open” (see the repository on Github), as an exercise of open science. This framework for exoplanet detection in multidimensional (3d and 4d arrays) high-contrast imaging datacubes consists of 2 main components: a labeled data generation system and a discriminator, in the form of a deep neural network.


VIP is a Python package/library for angular, reference star and spectral differential imaging for exoplanet/disk detection through high-contrast imaging. Check the Github repository here and the documentation at readthedocs. VIP is available on PyPi:

pip install vip_hci


VIP extras

Datacubes, Jupyter tutorials and other materials related to VIP.


High-contrast Imaging Plotting library. The goal of this library is to be the “Swiss army” solution for plotting and visualizing multi-dimensional high-contrast imaging datacubes on Jupyter lab.

pip install hciplot



Code for the paper: “Supervised detection of exoplanets in high-contrast imaging sequences”, Gomez Gonzalez et al 2018. Developed in Python 2 but compatible with Python 3. This package enables the generation of labeled data (MLAR smaples) for training machine learning classifiers. It also contains a function for building and training the neural network model that succesfully exploits the 3 dimensions of the training samples (hybrid convolutional and recurrent network). Keras/Tensorflow were used for the implementing network. Finally, it also contains the code for generating the ROC curves (figures 7 and 8) comparing the supervised detection framework to standard model PSF subtraction techniques. Code on GitHub.


Python package dedicated to the planet orbit fitting using Markov chain Monte Carlo (MCMC) methods. GitHub repository.