<h2 align="center">junky lib: PyTorch utilities</h2>
[![PyPI Version](https://img.shields.io/pypi/v/junky?color=blue)](https://pypi.org/project/junky/)
[![Python Version](https://img.shields.io/pypi/pyversions/junky?color=blue)](https://www.python.org/)
[![License: BSD-3](https://img.shields.io/badge/License-BSD-brightgreen.svg)](https://opensource.org/licenses/BSD-3-Clause)
Provides a bunch of tools and utilities to use with PyTorch.
## Content
[Autotrain](https://github.com/fostroll/junky/blob/master/doc/README_AUTOTRAIN.md)
[Layers](https://github.com/fostroll/junky/blob/master/doc/README_LAYERS.md)
[Datasets](https://github.com/fostroll/junky/blob/master/doc/README_DATASETS.md)
[Utilities](https://github.com/fostroll/junky/blob/master/doc/README_UTILITIES.md)
[Plotter](https://github.com/fostroll/junky/blob/master/doc/README_PLOTTER.md)
## Installation
### pip
***junky*** supports *Python 3.5* or later. To install it via *pip*, run:
```sh
$ pip install junky
```
If you currently have a previous version of ***junky*** installed, use:
```sh
$ pip install junky -U
```
### From Source
Alternatively, you can also install ***junky*** from source of this *git
repository*:
```sh
$ git clone https://github.com/fostroll/junky.git
$ cd junky
$ pip install -e .
```
## License
***junky*** is released under the BSD License. See the
[LICENSE](https://github.com/fostroll/junky/blob/master/LICENSE) file for more
details.