Meddlr is a config-driven framework built to simplify ML-based medical image reconstruction and analysis.
Project description
meddlr
Meddlr is a config-driven ML framework built to simplify medical image reconstruction and analysis problems.
Installation
To avoid cuda-related issues, downloading torch
, torchvision
, and cupy
(optional)
must be done prior to downloading other requirements.
# Create and activate the environment.
conda create -n meddlr_env python=3.7
conda activate meddlr_env
# Install cuda-dependant libraries. Change cuda version as needed.
# Below we show examples for cuda-10.2
conda install pytorch torchvision cudatoolkit=10.2 -c pytorch
pip install cupy-cuda102
# Go to https://github.com/ad12/meddlr and fork the repository.
# Install as package in virtual environment (recommended):
git clone https://github.com/<your-github-username>/meddlr.git
cd meddlr && python -m pip install -e '.[dev]'
# For all contributors, install development packages.
make dev
Contributing
See CONTRIBUTING.md for more information.
Acknowledgements
Meddlr's design for rapid experimentation and benchmarking is inspired by detectron2.
About
If you use Meddlr for your work, please consider citing the following work:
@article{desai2021noise2recon,
title={Noise2Recon: A Semi-Supervised Framework for Joint MRI Reconstruction and Denoising},
author={Desai, Arjun D and Ozturkler, Batu M and Sandino, Christopher M and Vasanawala, Shreyas and Hargreaves, Brian A and Re, Christopher M and Pauly, John M and Chaudhari, Akshay S},
journal={arXiv preprint arXiv:2110.00075},
year={2021}
}
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
meddlr-0.0.1a2.tar.gz
(164.5 kB
view hashes)
Built Distribution
meddlr-0.0.1a2-py2.py3-none-any.whl
(222.3 kB
view hashes)
Close
Hashes for meddlr-0.0.1a2-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | e64653eaf1c8f375daba64dd4b42708a9d70c70d35a827f45df35e17028df001 |
|
MD5 | e6c714a6c8c270ce6c4607a8686f8eea |
|
BLAKE2b-256 | a85c7ccdf402f550619e25a85709263b8ea14ac0890ff87fb1ff2adf80da2e2e |