Projects

archeo: Bayesian framework for black-hole archaeology

Archeo is a package for inferring the natal kick and parental masses posterior of black holes. It help study the parental black holes of GW190521 and investigate the probability that the component black holes in GW190521 are a result of black hole merger. The detailed methodology is described in arxiv:2404.00720, and it can be applied to any other gravitational wave event.

classifier-trains: tool to finetune SOTA classifiers

Classifier-trains is a package aims to provide a primitive tool to finetune state-of-the-art models with PyTorch implementation, similar to Nvidia TAO but with more flexibility in augmentation and models. Like TAO classification, all parameters are configurable in yaml file to minimize the need of modifying scripts.