https://github.com/okrasolar/pytorch-timeseries

PyTorch implementations of neural networks for timeseries classification
https://github.com/okrasolar/pytorch-timeseries

classification deep-learning machine-learning pytorch time-series

Last synced: about 2 months ago
JSON representation

PyTorch implementations of neural networks for timeseries classification

• Host: GitHub
• URL: https://github.com/okrasolar/pytorch-timeseries
• Owner: okrasolar
• Created: 2019-09-28T07:24:23.000Z (almost 5 years ago)
• Default Branch: master
• Last Pushed: 2022-01-27T19:08:46.000Z (over 2 years ago)
• Last Synced: 2024-07-31T01:46:25.872Z (about 2 months ago)
• Topics: classification, deep-learning, machine-learning, pytorch, time-series
• Language: Python
• Homepage:
• Size: 53.7 KB
• Stars: 105
• Watchers: 3
• Forks: 23
• Open Issues: 4
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# pytorch-timeseries

PyTorch implementations of deep neural neural nets for time series classification.

Currently, the following papers are implemented:

* [InceptionTime: Finding AlexNet for Time Series Classification](https://arxiv.org/abs/1909.04939)

* [Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline](https://arxiv.org/abs/1611.06455)

### Beyond the UCR/UEA archive

There are two ways use the Inception Time model on your own data:

1. Copy the [models](src/models), and write new training loops

2. Extend the [base trainer](src/trainer.py) by implementing an initializer, `get_loaders` and `save`. 

This allows the training code (which handles both single and multi-class outputs) to be used - an example of this is

the [`UCRTrainer`](src/ucr.py).

### Setup

[Anaconda](https://www.anaconda.com/download/#macos) running python 3.7 is used as the package manager. To get set up

with an environment, install Anaconda from the link above, and (from this directory) run

```bash

conda env create -f environment.yml

```

This will create an environment named `inception` with all the necessary packages to run the code. To 

activate this environment, run

```bash

conda activate inception

```

In addition, [UCR/UEA archive](https://www.cs.ucr.edu/~eamonn/time_series_data/) must be downloaded and stored in the 

[data folder](data).

### Scripts

Example scripts showing how to train and evaluate the model can be found in the [scripts folder](scripts).