cetin/tracking-parametrisation-tuner
1
1
Fork 0
Code Issues Pull Requests repo.project_board Releases Wiki Activity
13 Commits 1 Branch 0 Tags 5.1 GiB
Jupyter Notebook 85.5%
Python 13.2%
C++ 1.3%
c0c20a8af0
Go to file
cetin c0c20a8af0 training of nn
2024-01-15 09:39:38 +01:00
data_results training of nn 2024-01-15 09:39:38 +01:00
env first commit 2023-12-19 13:00:59 +01:00
moore_options training of nn 2024-01-15 09:39:38 +01:00
neural_net_training training of nn 2024-01-15 09:39:38 +01:00
nn_neural_net_training nn trained 2024-01-09 16:32:06 +01:00
parameterisations training of nn 2024-01-15 09:39:38 +01:00
scripts Rework New 2024-01-09 13:55:39 +01:00
.gitignore training of nn 2024-01-15 09:39:38 +01:00
.gitlab-ci.yml first commit 2023-12-19 13:00:59 +01:00
.pre-commit-config.yaml first commit 2023-12-19 13:00:59 +01:00
electron_main.py first commit 2023-12-19 13:00:59 +01:00
LICENSE first commit 2023-12-19 13:00:59 +01:00
main_tracking_losses.py first commit 2023-12-19 13:00:59 +01:00
main.py training of nn 2024-01-15 09:39:38 +01:00
README.md readme 2023-12-19 13:05:56 +01:00
setup.sh first commit 2023-12-19 13:00:59 +01:00
tuner.code-workspace first commit 2023-12-19 13:00:59 +01:00

README.md

Parameterisation Tuner

This project provides utils for producing magic parameters used by the pattern recognition algorithms in the Rec project. Typical parameters are coefficients for extrapolation polynomials and weights for TMVA methods. This is based on this repo by André Günther.

Setup

There's a bash script for setting up the necessary (python) environment. Simply do:

chmod +x setup.sh
./setup.sh

This will install dependencies like ROOT and Jupyter. To enter the environment do:

source env/tuner_env/bin/activate
conda activate tuner