ewencedr/particle_fm

Easily train and evaluate multiple flow matching generative models on various particle physics datasets

21
/ 100
Experimental

This tool helps particle physicists train and evaluate various generative models on specialized particle physics datasets, like those from JetNet or LHC Olympics. It takes raw or preprocessed event data (e.g., particle jets or full events) as input and produces trained models capable of generating synthetic particle data that closely mimics real experimental or simulated results. Researchers can use this to explore and compare different generative neural network architectures and loss functions within the Flow Matching framework.

No commits in the last 6 months.

Use this if you are a particle physicist working with complex particle event data and need to generate realistic synthetic datasets or evaluate different generative modeling techniques for tasks like background generation or anomaly detection.

Not ideal if you are looking for a pre-trained, ready-to-use model for general particle physics data generation without needing to customize or evaluate different model architectures.

particle-physics high-energy-physics event-generation anomaly-detection jet-substructure
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

9

Forks

Language

Python

License

MIT

Last pushed

Jun 05, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ewencedr/particle_fm"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.