Giter Site home page Giter Site logo

aod-net-pytorch's Introduction

AOD-Net

Introducion

This project is a pytorch implementation of AOD-Net : All-in-One Network for Dehazing. Recently, there are a number of good implementations:

During our implementing, we referred the above implementations. However, our implementation has several unique and new features compared with the above implementations:

  • It has both train and test code We provided both train and test code and pre-trained pytorch pickle file
  • It has more clearly code structure We refactore the code structure of the dataloader to make it more consistent with pytorch dataset
  • It has better logging decorator We add logging decorator for network pipeline function calling

Preparation

First of all, clone the code

git clone https://github.com/walsvid/AOD-Net.pytorch.git

Then, install prerequisites

pip install -r requirements.txt

Data Preparation

Please download the training images and original images from author's web page.

Then make a directory for data, change the parameters about data directories.

Pre-trained model

Please download the pretrained model from this download link.

Train

chmod +x run_train.sh
./run_train.sh

You can change the parameter in train bash script to satisfied your project.

Test

chmod +x run_test.sh
./run_test.sh

Demo

This is the dehazing result image comparison. Left image is haze image, right image is clean image processed by AOD-Net.

TODO

  • Integrate existing models with detection tasks

Citation

If you using this project in your work, please don't forget to cite the original author's paper.

@inproceedings{li2017aod,
  title={Aod-net: All-in-one dehazing network},
  author={Li, Boyi and Peng, Xiulian and Wang, Zhangyang and Xu, Jizheng and Feng, Dan},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
  volume={1},
  number={4},
  pages={7},
  year={2017}
}

aod-net-pytorch's People

Contributors

walsvid avatar

Watchers

James Cloos avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.