Skip to content
This repository has been archived by the owner on Sep 1, 2022. It is now read-only.

Latest commit

 

History

History
25 lines (15 loc) · 649 Bytes

README.md

File metadata and controls

25 lines (15 loc) · 649 Bytes

LHCb PID Compression

In this repository, we compress PID data via autoencoder

Pipeline description

First of all, we split data on train/validation/test and train autoencoder and xgboost

Alt text

Then, we train GAN on compressed data (with given PIDs) and generate new data

Alt text

Finally, we compute all accuracies

Alt text

How to run

  1. Create ./data/ and ./data/input/ folder
  2. Add data.csv to ./data/input/
  3. Configure config.py
  4. Run run_pipeline.sh from ./scripts/
  5. Collect results from ./data/output/