https://github.com/atoosaparsa/cgm-torch

Code for "Gradient-based Design of Computational Granular Crystals", Parsa et al.
https://github.com/atoosaparsa/cgm-torch

deep-learning differentiable-simulators gradient-based-optimisation granular-material metamaterial-design metamaterials pytorch unconventional-computing

Last synced: about 1 month ago
JSON representation

Code for "Gradient-based Design of Computational Granular Crystals", Parsa et al.

• Host: GitHub
• URL: https://github.com/atoosaparsa/cgm-torch
• Owner: AtoosaParsa
• License: mit
• Created: 2024-06-15T18:36:23.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2025-08-18T21:13:02.000Z (about 2 months ago)
• Last Synced: 2025-08-18T23:25:23.195Z (about 2 months ago)
• Topics: deep-learning, differentiable-simulators, gradient-based-optimisation, granular-material, metamaterial-design, metamaterials, pytorch, unconventional-computing
• Language: Python
• Homepage:
• Size: 38.2 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# CGM-Torch: A Differentiable Simulator for Granular Materials

This repository contains the source code for all the experiments in the following paper:

[Parsa, A., O'Hern, C. S., Kramer-Bottiglio, R., & Bongard, J. (2024). Gradient-based Design of Computational Granular Crystals. arXiv preprint arXiv:2404.04825.](https://arxiv.org/abs/2404.04825)



  



## Installation

Clone this repository and install the following using your preferred python environment or package management tool:

## Usage

### Training a new model:

```

python train.py --name "test" --savedir "./test/" --seed 1

```

### Loading a previously trained model:

```

python loadModel.py --savedir "./test/" --name "test" --seed 1 --plotName 'AND'

```

## AND Gate

![](https://github.com/AtoosaParsa/GCTorch/blob/main/media/AND_config.gif)

![](https://github.com/AtoosaParsa/GCTorch/blob/main/media/AND_plot.gif)

## XOR Gate

![](https://github.com/AtoosaParsa/GCTorch/blob/main/media/XOR_config.gif)

![](https://github.com/AtoosaParsa/GCTorch/blob/main/media/XOR_plot.gif)

## Citation

If you find our paper or this repository useful or relevant to your work please consider citing us:

```

@article{parsa2024gradient,

  title={Gradient-based Design of Computational Granular Crystals},

  author={Parsa, Atoosa and O'Hern, Corey S and Kramer-Bottiglio, Rebecca and Bongard, Josh},

  journal={arXiv preprint arXiv:2404.04825},

  year={2024}

}

```