Releasing MiraPy v0.1.0: A Python Package of Deep Learning in Astronomy! 🎉


MiraPy is a Python package for Deep Learning in Astronomy. It is built using Keras for developing ML models to run on CPU and GPU seamlessly. The aim is to make applying machine learning techniques on astronomical data easy for astronomers, researchers and students. We are releasing the first official release v0.1.0 with proper documentation and tutorials!

Following are some of the experiments that you can perform right now:

  • Classification of X-Ray Binaries using neural network

  • Astronomical Image Reconstruction using Autoencoder

  • Classification of the first catalogue of variable stars by ATLAS

  • HTRU1 Pulsar Dataset Image Classification using Convolutional Neural Network (CNN)

  • OGLE Catalogue Variable Star Classification using Recurrent Neural Network (RNN)

  • 2D and 3D visualization of feature sets using Principal Component Analysis (PCA)

You can download it using pip: pip install mirapy

The complete code is open source and is available in our Github repository. Documentation is available here. All the experiments are available in the Jupyter notebooks here. You can join our conversations on Slack!