catapulta / ESRNN-GPU

This is WIP GPU implementation of the ES-RNN model by Slawek et al.

A PyTorch implementation of the ES-RNN Hybrid Model

A GPU-enabled version of the hybrid ES-RNN model by Slawek et al that won the M4 time-series forecasting competition by a large margin.

Getting Started

Prerequisites

Python (3.5+)
PyTorch (0.4.1)
Zalando Research's Dilated RNN

Built With

• Python - The data science language ;)
• PyTorch - The dynamic framework for computation

Contributing

Please read CONTRIBUTING.md for details on our code of conduct, and the process for submitting pull requests to us.

Authors

• Andrew Redd - aredd-cmu
• Kaung Khin - damitkwr
• Aldo Marini - catapulta

See also the list of contributors who participated in this project.

License

This project is licensed under the MIT License - see the LICENSE.md file for details

Acknowledgments

• Thank you to the original author of the algorithm Smyl Slawek slaweks17 for advice and for creating this amazing algorithm
• Zalando Research zalandoresearch for their implementation of Dilated RNN