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.
MiraPy can be used for problem solving using ML techniques and will continue to grow to tackle new problems in Astronomy. 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 catalog of variable stars by ATLAS
HTRU1 Pulsar Dataset Image Classification using Convolutional Neural Network
Variable star Classification using Recurrent Neural Network (RNN)
2D visualization of feature sets using Principal Component Analysis (PCA)
Curve Fitting using Autograd (basic implementation)
There are more projects that we will add soon and some of them are as following:
Feature Engineering (Selection, Reduction and Visualization)
Classification of different states of GRS1905+105 X-Ray Binaries using Recurrent Neural Network (RNN)
Feature extraction from Images using Autoencoders and its applications in Astronomy
You can find the applications MiraPy in our tutorial repository.
In future, MiraPy will be able to do more and in better ways and we need your suggestions! Tell us what you would like to see as a part of this package on Slack.
You can download the package using pip package installer:
pip install mirapy
You can also build from source code:
git clone --recursive https://github.com/mirapy-org/mirapy.git cd mirapy pip install -r requirements.txt python setup.py install
MiraPy is far from perfect and we would love to see your contributions to open source community! MiraPy is open source, built on open source, and we’d love to have you hang out in our community.