Skip to content

Generating Realistic Nanorough Surfaces Using an N-Gram-Graph Augmented Deep Convolutional Generative Adversarial Network

License

Notifications You must be signed in to change notification settings

billsioros/RoughGAN

Repository files navigation

RoughGAN

Latest Release CD pre-commit.ci status Renovate - Enabled License Open In Colab Open in GitHub Codespaces Cookiecutter Template Buy me a coffee

Accompanying code for the paper Generating Realistic Nanorough Surfaces Using an N-Gram-Graph Augmented Deep Convolutional Generative Adversarial Network presented at SETN 2022.

In this work, we look at how a Generative Adversarial Network (GAN)-based strategy, given a nanorough surface data set, may learn to produce nanorough surface samples that are statistically equivalent to the ones belonging to the training data set. We also look at how combining the GAN framework with a variety of nanorough similarity measures might improve the realisticity of the synthesized nanorough surfaces. We showcase via multiple experiments that our framework is able to produce sufficiently realistic nanorough surfaces, in many cases indistinguishable from real ones.

Attention: We are in the midst of updating this repository so a few things might not work as expected 🔥

💿 Getting started

You can run the model locally using the following commands:

docker build . -t roughgan:$( git tag -l | tail -1 | cut -c2- ) -t build:train -f Dockerfile
docker run -v $(pwd)/data:/home/app/app/data -v $(pwd)/models:/home/app/app/models --gpus $(nvidia-smi --list-gpus | wc -l) roughgan:latest

The project's documentation can be found here.

❤️ Support the project

If you would like to contribute to the project, please go through the Contributing Guidelines first. You can also support the project by Buying me a coffee! ☕.

📑 Citation

@inproceedings{10.1145/3549737.3549794,
  author = {Sioros, Vasilis and Giannakopoulos, George and Constantoudis, Vassileios},
  title = {Generating Realistic Nanorough Surfaces Using an N-Gram-Graph Augmented Deep Convolutional Generative Adversarial Network},
  year = {2022},
  isbn = {9781450395977},
  publisher = {Association for Computing Machinery},
  address = {New York, NY, USA},
  url = {https://doi.org/10.1145/3549737.3549794},
  doi = {10.1145/3549737.3549794},
  booktitle = {Proceedings of the 12th Hellenic Conference on Artificial Intelligence},
  articleno = {53},
  numpages = {10},
  keywords = {Machine Learning, Rough Surfaces, Graph Theory, Nanotechnology, Artificial Intelligence},
  location = {Corfu, Greece},
  series = {SETN '22}
}

This project was generated using the billsioros/cookiecutter-pypackage cookiecutter template.

About

Generating Realistic Nanorough Surfaces Using an N-Gram-Graph Augmented Deep Convolutional Generative Adversarial Network

Resources

License

Code of conduct

Security policy

Stars

Watchers

Forks

Packages

No packages published