Metadata-Version: 2.1
Name: metallic
Version: 0.1.0
Summary: A simple toolbox for meta-learning research based on Pytorch.
Home-page: https://github.com/Renovamen/metallic
Author: Xiaohan Zou
Author-email: renovamenzxh@gmail.com
License: MIT
Platform: UNKNOWN
Description-Content-Type: text/markdown
Requires-Dist: numpy (<1.20.0,>=1.14.0)
Requires-Dist: torch (>=1.4.0)
Requires-Dist: torchvision (>=0.5.0)
Requires-Dist: higher (>=0.2.1)
Requires-Dist: requests
Requires-Dist: tqdm

# Metallic

Metallic is a clean library for meta-learning research based on [PyTorch](https://github.com/pytorch/pytorch).

Different from other meta-learning libraries, Metallic aims at providing a lightweight modularized toolbox for setting up meta-learning experiments quickly with the least amount of code.

The library is **work in progress**.


&nbsp;

## Installation

```bash
git clone https://github.com/Renovamen/metallic.git
cd metallic
python setup.py install
```

or

```bash
pip install git+https://github.com/Renovamen/metallic.git --upgrade
```


&nbsp;

## Documentations

Check the API documentation here: [metallic-docs.vercel.app](https://metallic-docs.vercel.app)


&nbsp;

## Acknowledgements

Metallic is highly inspired by the following awesome libraries:

- [learn2learn](https://github.com/learnables/learn2learn)
- [Torchmeta](https://github.com/tristandeleu/pytorch-meta)
- [higher](https://github.com/facebookresearch/higher)

&nbsp;

## License

Metallic is MIT licensed, see the [LICENSE](LICENSE) file for more details.


