light-side 0.1.0

PyTorch Lightning Implementations of Recent Low-Light Image Enhancement !

Light Side of the Night

Low-Light Image Enhancement

Website • Docs • Pypi

TABLE OF CONTENTS

1. About The Light Side
2. Prerequisites
3. Installation
   • From Pypi
   • From Source
4. Usage Examples
5. Architectures
6. Datasets
7. Deployments
8. Training
9. Tests
10. Contributing
11. Contributors
12. Contact
13. License
14. References
15. Citations

About The Light Side

Light Side is an low-light image enhancement library that consist state-of-the-art deep learning methods. The light side of the Force is referenced. The aim is to create a light structure that will find the Light Side of the Night.

The light side of the Force, also known as Ashla, was one of two methods of using the Force. The light side was aligned with calmness, peace, and passiveness, and was used only for knowledge and defense. The Jedi were notable practitioners of the light, being selfless servants of the will of the Force, and their enemies, the Sith followed the dark side of the Force.

Source: Wookieepedia

Low-light image enhancement aims at improving the perception or interpretability of an image captured in an environment with poor illumination.

Source: paperswithcode

Prerequisites

Before you begin, ensure you have met the following requirements:

requirement	version
imageio	~=2.15.0
numpy	~=1.22.0
pytorch_lightning	~=1.7.0
scikit-learn	~=1.0.2
torch	~=1.9.1

Installation

To install Light Side, follow these steps:

From Pypi

pip install light_side

From Source

git clone https://github.com/canturan10/light_side.git
cd light_side
pip install .

From Source For Development

git clone https://github.com/canturan10/light_side.git
cd light_side
pip install -e ".[all]"

Usage Examples

import imageio
import light_side as ls

img = imageio.imread("test.jpg")

model = ls.Enhancer.from_pretrained("model_config_dataset")
model.eval()

results = model.predict(img)

APIs

• Available Models
• Available Versions for a Spesific Model
• Latest Version for a Spesific Model
• Pretrained Model
• Model with Random Weight Initialization
• Pretrained Arch Model
• Arch Model with Random Weight Initialization

For more information, please refer to the APIs

Architectures

• Zero DCE
• EnlightenGAN
• MBLLEN
• LLFlow

For more information, please refer to the Architectures

Datasets

• Zero DCE
• LOL
• DICM
• MEF

For more information, please refer to the Datasets

Deployments

• FastAPI
• ONNX
• DeepSparse
• TensorFlow
• TensorFlow Lite

For more information, please refer to the Deployment

Training

To training, follow these steps:

For installing Light Side, please refer to the Installation.

python training/zerodce_training.py

For optional arguments,

python training/zerodce_training.py --help

Tests

During development, you might like to have tests run.

Install dependencies

pip install -e ".[test]"

Linting Tests

pytest light_side --pylint --pylint-error-types=EF

Document Tests

pytest light_side --doctest-modules

Coverage Tests

pytest --doctest-modules --cov light_side --cov-report term

Contributing

To contribute to Light Side, follow these steps:

1. Fork this repository.
2. Create a branch: git checkout -b <branch_name>.
3. Make your changes and commit them: git commit -m '<commit_message>'
4. Push to the original branch: git push origin
5. Create the pull request.

Alternatively see the GitHub documentation on creating a pull request.

Contributors

Oğuzcan Turan

You ?

Contact

If you want to contact me you can reach me at [e-mail].

License

This project is licensed under MIT license. See LICENSE for more information.

References

The references used in the development of the project are as follows.

• Satellighte
• Img Shields
• GitHub Pages
• PyTorch Lightning
• Torchvision

Citations

Click to expand!

@misc{Turan_satellighte,
author = {Turan, Oguzcan},
title = {{satellighte}},
url = {https://github.com/canturan10/satellighte}
}

@article{DBLP:journals/corr/abs-2001-06826,
  author    = {Chunle Guo and
               Chongyi Li and
               Jichang Guo and
               Chen Change Loy and
               Junhui Hou and
               Sam Kwong and
               Runmin Cong},
  title     = {Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement},
  journal   = {CoRR},
  volume    = {abs/2001.06826},
  year      = {2020},
  url       = {https://arxiv.org/abs/2001.06826},
  eprinttype = {arXiv},
  eprint    = {2001.06826},
  timestamp = {Sat, 23 Jan 2021 01:20:17 +0100},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2001-06826.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

Give a ⭐️ if this project helped you!

This readme file is made using the readme-template