Coder Social home page Coder Social logo

aorun's Introduction

Aorun: Deep Learning over PyTorch

build coverage Code Climate python license

Aorun intend to implement an API similar to Keras with PyTorch as backend.

Getting started

Here is a simple regression example:

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

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

$ pip install aorun

Why Aorun?

Aorun is a Dinosaur. Dinosaurs are cool.

aorun's People

Contributors

ramon-oliveira avatar

Stargazers

Ryan Davis avatar  avatar Michael Corrado avatar  avatar LiuZhuang avatar jan-matthis avatar  avatar Ally Jr  avatar Žiga Avsec avatar Eric Alcaide avatar  avatar Padam Sethia avatar Surajit Dasgupta avatar György Orosz avatar Peter Clarke avatar Khushmeet Singh avatar Liang Shuailong avatar Matt Laporte avatar Zoha Hamid avatar Madhur Tandon avatar Harshvardhan Kalra avatar Divam Gupta avatar Evgeniy Koryagin avatar Yili Zhao avatar 杨培文 (Yang Peiwen) avatar  avatar Yuliang Xiu avatar Matthew Koski avatar Silvio Rodrigues avatar BenJueWeng avatar Rahul V avatar Yossi Keshet avatar  avatar Chen Qiu avatar Sudar S avatar David P. Larson avatar lanye avatar Aldiantoro Nugroho avatar  avatar weijing avatar Manu Agarwal avatar tangzk avatar Yuchao Jin avatar  avatar  avatar Gu Wang avatar  avatar Ellery Queen avatar George Gondim-Ribeiro avatar  avatar Jia Feng avatar OdinLin avatar 爱可可-爱生活 avatar  avatar Emre Şafak avatar Pedro Tabacof avatar Albert Zhuang avatar Meet Shah  avatar Karan Desai avatar TENSORTALK avatar Soumith Chintala avatar

Watchers

 avatar Gu Wang avatar Silvio Rodrigues avatar lanye avatar

aorun's Issues

MNIST assertion error

(py3) MBP:examples $ python mnist.py
11222it [00:04, 2786.04it/s]
(60000, 28, 28) (10000, 28, 28)
Traceback (most recent call last):
  File "mnist.py", line 38, in <module>
    history = model.fit(X, y, loss=loss, val_data=(X_test, y_test))
  File "/Users/MY/Dropbox (Personal)/x/aorun/aorun/models.py", line 92, in fit
    self._build()
  File "/Users/MY/Dropbox (Personal)/x/aorun/aorun/models.py", line 33, in _build
    next_layer.build(prev_layer.output_dim)
  File "/Users/MY/Dropbox (Personal)/x/aorun/aorun/layers.py", line 57, in build
    assert type(input_dim) is int
AssertionError

models.py

  File "aorun/aorun/models.py", line 39
    n_samples, *_ = X.size()
               ^
SyntaxError: invalid syntax```

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.