Skip to content


Switch branches/tags

Name already in use

A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?

Latest commit


Git stats


Failed to load latest commit information.
Latest commit message
Commit time


πŸ€– farabio ❀️

PyPI version DOI PyPI - Downloads Documentation Status GitHub commit activity GitHub

πŸŽ‰ What's New

August 26, 2021

Publishing farabio==0.0.3 (latest version):
PyPI | Release notes

August 18, 2021

Publishing farabio==0.0.2:
PyPI | Release notes

April 21, 2021

This work is presented at PyTorch Ecosystem day. Poster is here.

April 2, 2021

Publishing farabio==0.0.1:
PyPI | Release notes

March 3, 2021

This work is selected for PyTorch Ecosystem Day.

πŸ’‘ Introduction

farabio is a minimal PyTorch toolkit for out-of-the-box deep learning support in biomedical imaging. For further information, see Wikis and Docs.

πŸ”₯ Features

  • Biomedical datasets
  • Common DL models
  • Flexible trainers (*in progress)

πŸ“š Biodatasets

🚒 Models





πŸš€ Getting started (Installation)

1. Create and activate conda environment:

conda create -n myenv python=3.8
conda activate myenv

2. Install PyTorch:

pip install torch==1.9.0+cu111 torchvision==0.10.0+cu111 torchaudio==0.9.0 -f

3. Install farabio:

A. With pip:

pip install farabio

B. Setup from source:

git clone && cd farabio
pip install .

🀿 Tutorials

Tutorial 1: Training a classifier for ChestXrayDataset - Notebook
Tutorial 2: Training a segmentation model for DSB18Dataset - Notebook
Tutorial 3: Training a Faster-RCNN detection model for VinBigDataset - Notebook
Tutorial 4: Training a 3D-CNN to predict the presence of viral pneumonia in computer tomography (CT) scans for MosmedDataset - Script
Tutorial 5: Training a LSTM for epileptic seizures prediction using EpiSeizureDataset dataset - Script

πŸ”Ž Links

⭐ Credits

If you like this repository, please click on Star.

How to cite | doi:

  author       = {Sanzhar Askaruly and
                  Nurbolat Aimakov and
                  Alisher Iskakov and
                  Hyewon Cho and
                  Yujin Ahn and
                  Myeong Hoon Choi and
                  Hyunmo Yang and
                  Woonggyu Jung},
  title        = {Farabio: Deep learning for biomedical imaging},
  month        = dec,
  year         = 2021,
  publisher    = {Zenodo},
  version      = {v0.0.3-doi},
  doi          = {10.5281/zenodo.5746474},
  url          = {}

πŸ“ƒ Licenses

This work is licensed Apache 2.0.

🀩 Acknowledgements

This work is based upon efforts of open-source PyTorch Community. I have tried to acknowledge related works (github links, arxiv papers) inside the source material, eg. README, documentation, and code docstrings. Please contact if I missed anything.