Skip to content

Lighter is a framework for streamlining deep learning experiments with configuration files. PyTorch Lightning + MONAI Bundle.

License

Notifications You must be signed in to change notification settings

project-lighter/lighter

Repository files navigation


Lighter logo



 

Focus on your deep learning experiments and forget about (re)writing code. lighter is:

  1. Task-agnostic

    Whether you’re working on classification, segmentation, or self-supervised learning, lighter provides generalized training logic that you can use out-of-the-box.

  2. Configuration-based

    Easily define, track, and reproduce experiments with lighter’s configuration-driven approach, keeping all your hyperparameters organized.

  3. Customizable

    Seamlessly integrate your custom models, datasets, or transformations into lighter’s flexible framework.

 

lighter stands on the shoulder of these two giants:


Simply put, lighter = config(trainer + system) 😇

📖 Getting Started

📚 Documentation    🎥 YouTube Channel    👾 Discord Server

Install:

pip install project-lighter
Pre-release (up-to-date with the main branch):
pip install project-lighter --pre
For development:
make setup
make install             # Install lighter via Poetry
make pre-commit-install  # Set up the pre-commit hook for code formatting
poetry shell             # Once installed, activate the poetry shell

💡 Projects

Projects that use lighter:

Project Description
Foundation Models for Quantitative Imaging Biomarker Discovery in Cancer Imaging A foundation model for lesions on CT scans that can be applied to down-stream tasks related to tumor radiomics, nodule classification, etc.

Cite

@software{lighter,
author       = {Ibrahim Hadzic and
                Suraj Pai and
                Keno Bressem and
                Hugo Aerts},
title        = {Lighter},
publisher    = {Zenodo},
doi          = {10.5281/zenodo.8007711},
url          = {https://doi.org/10.5281/zenodo.8007711}
}