Metadata-Version: 2.1
Name: eve-mli
Version: 0.0.1rc0
Summary: eve-mli: making learning interesting.
Home-page: https://github.com/densechen/eve
Author: densechen
Author-email: densechen@foxmail.com
License: MIT
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Operating System :: OS Independent
Requires-Python: >=3.6
Description-Content-Type: text/markdown
Requires-Dist: gym (==0.18.0)
Requires-Dist: numpy (==1.18.5)
Requires-Dist: optuna (==2.3.0)
Requires-Dist: seaborn (==0.11.0)
Requires-Dist: stable-baselines3 (==0.10.0)
Requires-Dist: tensorboard (==2.4.0)
Requires-Dist: tensorboard-plugin-wit (==1.7.0)
Requires-Dist: torch (==1.7.0)
Requires-Dist: torchfile (==0.1.0)
Requires-Dist: torchnet (==0.0.4)
Requires-Dist: torchvision (==0.8.1)

# eve-mli: making learning interesting

![GitHub last commit](https://img.shields.io/github/last-commit/densechen/eve-mli) [![Documentation Status](https://readthedocs.org/projects/eve-mli/badge/?version=latest)](https://eve-mli.readthedocs.io/en/latest/?badge=latest) [![PyPI](https://img.shields.io/pypi/v/eve-mli)](https://pypi.org/project/eve-mli) [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/eve-mli)](https://pypi.org/project/eve-mli)

Eve is an open-source deep learning framework used to devise various architectures in a more flexible and interesting way.

We provide a jupyter notebook to show the basic usage and the advanced features of Eve in `./examples`.

**Any contributions to Eve is welcome!**

## Installation

Install from [PyPI](https://pypi.org/project/eve-mli/):

```bash
pip install eve-mli
```

Developers can download and install the latest version from [GitHub](https://github.com/densechen/eve-mli):

```bash
git clone https://github.com/densechen/eve-mli.git
cd eve
python setup.py install
```

## About the project

This project is mainly based on [PyTorch](https://github.com/pytorch/pytorch) and [stable-baselines3](https://github.com/DLR-RM/stable-baselines3).
*eve.Cores.Eve* succeeds *torch.nn.Module* and keeps all the features of latter.
We design a *Trainer* to maintain training process and further wrapper it as a *gym.envs* to play with reinforcement learning.

The documentation can be found [here](https://eve-mli.readthedocs.io).

## About the authors

[Dengsheng Chen](https://densechen.github.io)
Master @ National University of Defense Technology
densechen@foxmail.com

The project remains in development. We encourage more volunteers to come together, and make learning more interesting!


