GANsforVirtualEye 0.1.7

This package provides an implementation of Generative Adversarial Networks (GANs) for time series generation, with flexible architecture options. Users can select different combinations of generator and discriminator models, including Convolutional Neural Networks (CNN) and Long Short-Term Memory networks (LSTM), to suit their specific needs.

GANsForVirtualEye: Time Series Generation Package

GANsForVirtualEye is a Python package that implements Generative Adversarial Networks (GANs) for time series data generation, offering flexible architecture options with CNN and LSTM models for both generators and discriminators.

Architecture

Installation

Prerequisites

• Python 3.6 or higher
• pip package manager

Steps

1. Clone the Repository

   git clone https://github.com/shailendrabhandari/GANsForVirtualEye.git
   cd GANsForVirtualEye
   

2. Install Required Packages

   It's recommended to use a virtual environment.

   pip install -r requirements.txt
   

3. Install the Package

   pip install .
   

Documentation

Detailed documentation is available at Read the Docs.

Author

• Shailendra Bhandari
  GitHub | Email

---

Citation

If you use this package in your research or projects, please cite it as:

@misc{bhandari2024modelingeyegazevelocity,
      title={Modeling Eye Gaze Velocity Trajectories using GANs with Spectral Loss for Enhanced Fidelity}, 
      author={Shailendra Bhandari and Pedro Lencastre and Rujeena Mathema and Alexander Szorkovszky and Anis Yazidi and Pedro Lind},
      year={2024},
      eprint={2412.04184},
      archivePrefix={arXiv},
      primaryClass={cs.NE},
      url={https://arxiv.org/abs/2412.04184}, 
}

---

Acknowledgment

Thank You for Using GAN Time Series Generation Package!

We hope this package helps you in your research or projects involving time series data generation.