Setup Guide#

This page provides instructions on setting up this repository, both for the initial setup and for subsequent sessions.

Initial Setup#

For the first-time setup, ensure you have a functional mamba (or conda) installation. To optimize environment resolution and package installation speed, it is recommended to use mamba. Follow the official instructions. to install mamba.

Then,

# 1. Clone the repository
git clone ssh://git@gitlab.cern.ch:7999/gdl4hep/etx4velo.git
# Using https: git clone https://gitlab.cern.ch/gdl4hep/etx4velo.git
cd etx4velo

# 2. Switch to the `dev` branch
git switch dev

# 3. Fetch the `montetracko` git submodule
git submodule update --init

# 4. Setup the Conda environment
mamba env create -f setup/gpu_enviroment.yaml # with CUDA
# or CPU only: mamba env create -f setup/cpu_enviroment.yaml

# 5. Optionally, activate jupyter widgets
jupyter nbextension enable --py widgetsnbextension

Additionally, you have the flexibility to customize the paths to various output directories according to your preferences. Modify these paths in the setup/common_config.yaml file, where relative paths are based on the etx4velo folder within this repository.

Subsequent Sessions#

For each new session, follow these steps to prepare your environment:

  1. Source the setup/setup.sh file, which accomplishes the following:

    • Defines the environment variable ETX4VELO_REPO, containing the absolute path to this repository.

    • Adds montetracko, etx4velo and etx4velo/pipeline to the PYTHONPATH.

    source setup/setup.sh

  2. Activate the conda environment

    conda activate etx4velo_env

  3. If desired, start a Jupyter Lab server:

    jupyter-lab

Next Steps#

you can refer to the test sample guide to set up the test samples, or directly processed to the training guide for instructions on running a training of a pipeline.