https://github.com/khirotaka/typhoon
Transformer based neural network model for time series tasks.
https://github.com/khirotaka/typhoon
Last synced: 2 months ago
JSON representation
Transformer based neural network model for time series tasks.
- Host: GitHub
- URL: https://github.com/khirotaka/typhoon
- Owner: khirotaka
- License: apache-2.0
- Created: 2019-08-02T15:02:22.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2019-09-24T15:06:44.000Z (over 5 years ago)
- Last Synced: 2025-02-13T03:41:22.608Z (4 months ago)
- Language: Python
- Homepage:
- Size: 72.3 KB
- Stars: 1
- Watchers: 2
- Forks: 0
- Open Issues: 6
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Typhoon
Transformer based neural network model for time series tasks.
## Structure
```
.
├── Dockerfile
├── LICENSE
├── Pipfile
├── Pipfile.lock
├── README.md
├── docker-compose.yml
│
├── Typhoon
│ ├── __init__.py
│ ├── core
│ │ ├── __init__.py
│ │ ├── model.py
│ │ └── modules.py
│ │
│ └── utils
│ ├── __init__.py
│ ├── dataset.py
│ ├── functions.py
│ └── trainer.py
│
└── experiments
├── README.md
├── check.py
├── train_har.py
└── train_mhealth.py
```
* `utils/` ... This directory contain training script and sub functions.
## System Requirements
* OS: Unix-like
* macOS Mojave 10.14.6
* Debian 9.9 (GCP Deep Learning Image: PyTorch 1.1.0 and fastai m32)
* Ubuntu 16.04 or Ubuntu 18.04
* Python 3.5 or later
* PyTorch 1.1.0
* (optional) NVIDIA GPU
## References
* [Attention is all you need](https://arxiv.org/abs/1706.03762)
* [Attend and Diagnose: Clinical Time Series Analysis Using Attention Models](https://arxiv.org/abs/1711.03905)
* [TimeNet: Pre-trained deep recurrent neural network for time series classification](https://arxiv.org/abs/1706.08838)