⭐ Star us on GitHub it helps!
Welcome to VItamin, a python toolkit for producing fast gravitational wave posterior samples.
This repository is the official implementation of Bayesian Parameter Estimation using Conditional Variational Autoencoders for Gravitational Wave Astronomy.
Hunter Gabbard, Chris Messenger, Ik Siong Heng, Francesco Tonlini, Roderick Murray-Smith
Official Documentation can be found at https://joseph.bayley.docs.ligo.org/vitamin.
Note: This repository is a work in progress. No official release of code just yet.
VItamin requires python3.7. You may use python3.7 by initializing a virtual environment.
conda create -n vitc_keras python=3.7
conda activate vitc_keras
conda install tensorflow=2.6.0
conda install pip
pip install -r requirements.txt
Optionally, install basemap and geos in order to produce sky plots of results.
For installing basemap:
- Install geos-3.3.3 from source
- Once geos is installed, install basemap using
pip install git+https://github.com/matplotlib/basemap.git
Install VItamin using pip (not currently working):
pip install vitamin-c
To train an example model from the paper, try out the demo.
Full model definitions are given in models directory. Data is generated from gen_benchmark_pe.py.
We train using a network derived from first principals:
We track the performance of the model during training via loss curves:
Finally, we produce posteriors after training and other diagnostic tests comparing our approach with 4 other independent methods:
Posterior example:
KL-Divergence between posteriors:
PP Tests:
