https://github.com/ramon-oliveira/aorun

Deep Learning over PyTorch
https://github.com/ramon-oliveira/aorun

bayesian-inference deeplearning neural-networks pytorch

Last synced: about 1 month ago
JSON representation

Deep Learning over PyTorch

• Host: GitHub
• URL: https://github.com/ramon-oliveira/aorun
• Owner: ramon-oliveira
• License: mit
• Created: 2017-03-10T19:24:27.000Z (almost 8 years ago)
• Default Branch: master
• Last Pushed: 2017-09-06T06:22:17.000Z (over 7 years ago)
• Last Synced: 2024-12-08T14:06:14.608Z (about 2 months ago)
• Topics: bayesian-inference, deeplearning, neural-networks, pytorch
• Language: Python
• Homepage:
• Size: 62.5 KB
• Stars: 61
• Watchers: 4
• Forks: 4
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• Awesome-pytorch-list-CNVersion - aorun
• Awesome-pytorch-list - aorun

README

        
# Aorun: Deep Learning over PyTorch

[![build](https://travis-ci.org/ramon-oliveira/aorun.svg?branch=master)](https://travis-ci.org/ramon-oliveira/aorun)

[![coverage](https://coveralls.io/repos/github/ramon-oliveira/aorun/badge.svg)](https://coveralls.io/github/ramon-oliveira/aorun)

[![Code Climate](https://codeclimate.com/github/ramon-oliveira/aorun/badges/gpa.svg)](https://codeclimate.com/github/ramon-oliveira/aorun)

[![python](https://img.shields.io/pypi/pyversions/aorun.svg)](https://pypi.python.org/pypi/aorun)

[![license](https://img.shields.io/github/license/ramon-oliveira/aorun.svg)](https://github.com/ramon-oliveira/aorun/blob/master/LICENSE)

Aorun intend to implement an API similar to [Keras](https://keras.io) with PyTorch as backend.

## Getting started

Here is a simple regression example:

```python

from aorun.models import Model

from aorun.layers import Dense, Activation

model = Model()

model.add(Dense(10, input_dim=3))

model.add(Activation('relu'))

model.add(Dense(1))

model.fit(X_train, y_train, loss='mse', optimizer='adam')

y_pred = model.predict(X_test)

```

## Install

First of all, it's import to mention that this project is develop with **Python 3.5+** in mind. I do not recommend using Aorun with older versions.

As prerequisite, you have to install the latest stable version of [PyTorch](http://pytorch.org)

Then you can install aorun as any other python package, with pip:

```bash

$ pip install aorun

```

## Why Aorun?

[Aorun](https://en.wikipedia.org/wiki/Aorun) is a Dinosaur. Dinosaurs are cool.