lasagne

Lightweight library to build and train neural networks in Theano

Science Score: 20.0%

This score indicates how likely this project is to be science-related based on various indicators:

○
CITATION.cff file
○
codemeta.json file
○
.zenodo.json file
○
DOI references
✓
Academic publication links
Links to: zenodo.org
✓
Committers with academic emails
5 of 72 committers (6.9%) from academic institutions
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (14.4%) to scientific vocabulary

Keywords

deep-learning-library neural-networks python theano

Keywords from Contributors

optimizing-compiler tensors aesara automatic-differentiation symbolic-computation term-rewriting-system transpiler deep-neural-networks distributed autograd

Last synced: 6 months ago · JSON representation

Repository

Lightweight library to build and train neural networks in Theano

Basic Info

Host: GitHub
Owner: Lasagne
License: other
Language: Python
Default Branch: master
Homepage: http://lasagne.readthedocs.org/
Size: 2.16 MB

Statistics

Stars: 3,862
Watchers: 214
Forks: 941
Open Issues: 139
Releases: 0

Topics

deep-learning-library neural-networks python theano

Created over 11 years ago · Last pushed almost 4 years ago

Metadata Files

Readme Changelog Contributing License

README.rst

.. image:: https://readthedocs.org/projects/lasagne/badge/
    :target: http://lasagne.readthedocs.org/en/latest/

.. image:: https://travis-ci.org/Lasagne/Lasagne.svg
    :target: https://travis-ci.org/Lasagne/Lasagne

.. image:: https://img.shields.io/coveralls/Lasagne/Lasagne.svg
    :target: https://coveralls.io/r/Lasagne/Lasagne

.. image:: https://img.shields.io/badge/license-MIT-blue.svg
    :target: https://github.com/Lasagne/Lasagne/blob/master/LICENSE

.. image:: https://zenodo.org/badge/16974/Lasagne/Lasagne.svg
   :target: https://zenodo.org/badge/latestdoi/16974/Lasagne/Lasagne

Lasagne
=======

Lasagne is a lightweight library to build and train neural networks in Theano.
Its main features are:

* Supports feed-forward networks such as Convolutional Neural Networks (CNNs),
  recurrent networks including Long Short-Term Memory (LSTM), and any
  combination thereof
* Allows architectures of multiple inputs and multiple outputs, including
  auxiliary classifiers
* Many optimization methods including Nesterov momentum, RMSprop and ADAM
* Freely definable cost function and no need to derive gradients due to
  Theano's symbolic differentiation
* Transparent support of CPUs and GPUs due to Theano's expression compiler

Its design is governed by `six principles
`_:

* Simplicity: Be easy to use, easy to understand and easy to extend, to
  facilitate use in research
* Transparency: Do not hide Theano behind abstractions, directly process and
  return Theano expressions or Python / numpy data types
* Modularity: Allow all parts (layers, regularizers, optimizers, ...) to be
  used independently of Lasagne
* Pragmatism: Make common use cases easy, do not overrate uncommon cases
* Restraint: Do not obstruct users with features they decide not to use
* Focus: "Do one thing and do it well"


Installation
------------

In short, you can install a known compatible version of Theano and the latest
Lasagne development version via:

.. code-block:: bash

  pip install -r https://raw.githubusercontent.com/Lasagne/Lasagne/master/requirements.txt
  pip install https://github.com/Lasagne/Lasagne/archive/master.zip

For more details and alternatives, please see the `Installation instructions
`_.


Documentation
-------------

Documentation is available online: http://lasagne.readthedocs.org/

For support, please refer to the `lasagne-users mailing list
`_.


Example
-------

.. code-block:: python

  import lasagne
  import theano
  import theano.tensor as T

  # create Theano variables for input and target minibatch
  input_var = T.tensor4('X')
  target_var = T.ivector('y')

  # create a small convolutional neural network
  from lasagne.nonlinearities import leaky_rectify, softmax
  network = lasagne.layers.InputLayer((None, 3, 32, 32), input_var)
  network = lasagne.layers.Conv2DLayer(network, 64, (3, 3),
                                       nonlinearity=leaky_rectify)
  network = lasagne.layers.Conv2DLayer(network, 32, (3, 3),
                                       nonlinearity=leaky_rectify)
  network = lasagne.layers.Pool2DLayer(network, (3, 3), stride=2, mode='max')
  network = lasagne.layers.DenseLayer(lasagne.layers.dropout(network, 0.5),
                                      128, nonlinearity=leaky_rectify,
                                      W=lasagne.init.Orthogonal())
  network = lasagne.layers.DenseLayer(lasagne.layers.dropout(network, 0.5),
                                      10, nonlinearity=softmax)

  # create loss function
  prediction = lasagne.layers.get_output(network)
  loss = lasagne.objectives.categorical_crossentropy(prediction, target_var)
  loss = loss.mean() + 1e-4 * lasagne.regularization.regularize_network_params(
          network, lasagne.regularization.l2)

  # create parameter update expressions
  params = lasagne.layers.get_all_params(network, trainable=True)
  updates = lasagne.updates.nesterov_momentum(loss, params, learning_rate=0.01,
                                              momentum=0.9)

  # compile training function that updates parameters and returns training loss
  train_fn = theano.function([input_var, target_var], loss, updates=updates)

  # train network (assuming you've got some training data in numpy arrays)
  for epoch in range(100):
      loss = 0
      for input_batch, target_batch in training_data:
          loss += train_fn(input_batch, target_batch)
      print("Epoch %d: Loss %g" % (epoch + 1, loss / len(training_data)))

  # use trained network for predictions
  test_prediction = lasagne.layers.get_output(network, deterministic=True)
  predict_fn = theano.function([input_var], T.argmax(test_prediction, axis=1))
  print("Predicted class for first test input: %r" % predict_fn(test_data[0]))

For a fully-functional example, see `examples/mnist.py `_,
and check the `Tutorial
`_ for in-depth
explanations of the same. More examples, code snippets and reproductions of
recent research papers are maintained in the separate `Lasagne Recipes
`_ repository.


Citation
--------

If you find Lasagne useful for your scientific work, please consider citing it
in resulting publications. We provide a ready-to-use `BibTeX entry for citing
Lasagne `_.


Development
-----------

Lasagne is a work in progress, input is welcome.

Please see the `Contribution instructions
`_ for details
on how you can contribute!

Owner

Name: Lasagne
Login: Lasagne
Kind: organization

Repositories: 2
Profile: https://github.com/Lasagne

GitHub Events

Total

Watch event: 28
Pull request event: 1
Fork event: 4

Last Year

Watch event: 28
Pull request event: 1
Fork event: 4

Committers

Last synced: 9 months ago

All Time

Total Commits: 825
Total Committers: 72
Avg Commits per committer: 11.458
Development Distribution Score (DDS): 0.781

Past Year

Commits: 0
Committers: 0
Avg Commits per committer: 0.0
Development Distribution Score (DDS): 0.0

Top Committers

Name	Email	Commits
Jan Schlüter	j**r@o**t	181
Sander Dieleman	s**n@g**m	135
Colin Raffel	c**l@g**m	103
Eben Olson	e**n@g**m	66
skaae	s**y@g**m	64
Daniel Nouri	d**i@g**m	49
Daniel Maturana	d**a@c**u	30
Martin Thoma	i**o@m**e	24
Geoffrey French	f**5@g**m	18
Eric Battenberg	e**g@g**m	16
Eric Battenberg	e**g@g**m	10
Jack Kelly	j**t@x**k	8
Søren Kaae Sønderby	s**y@b**l	8
JeffreyDF	J**F@G**m	6
Reyhane Askari	r**t@g**m	5
Geoffrey French	b**3@g**m	5
Botev	b**g@g**m	4
Diogo Moitinho de Almeida	d**9@g**m	4
Hendrik Weideman	w**h@r**u	4
Michael Heilman	m**n@c**m	4
Mikhail Korobov	k**4@g**m	4
sentient07	v**5@g**m	4
danstowell	d**b@g**m	3
Kai Li	1**1@q**m	3
Joshua Chin	j**n@g**m	3
Brian McFee	b**e@n**u	3
Kaixhin	d**n@k**m	3
wuaalb	m**w@g**m	2
joncrall	e**c@g**m	2
Alexander Mathews	a**3@g**m	2
and 42 more...

Committer Domains (Top 20 + Academic)

ofai.at: 3 qq.com: 2 dkfz-heidelberg.de: 2 cmu.edu: 1 martin-thoma.de: 1 gracenote.com: 1 xlk.org.uk: 1 rpi.edu: 1 civisanalytics.com: 1 nyu.edu: 1 kaixhin.com: 1 vision.ee.ethz.ch: 1 ugent.be: 1 localhost.localdomain: 1 yandex.ru: 1 twitter.com: 1 debian.org: 1 kylemcdonald.net: 1 superfuzz.me: 1 cs.umass.edu: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time

Total issues: 69
Total pull requests: 33
Average time to close issues: 3 months
Average time to close pull requests: 9 months
Total issue authors: 48
Total pull request authors: 22
Average comments per issue: 5.26
Average comments per pull request: 3.3
Merged pull requests: 15
Bot issues: 0
Bot pull requests: 0

Past Year

Issues: 0
Pull requests: 1
Average time to close issues: N/A
Average time to close pull requests: N/A
Issue authors: 0
Pull request authors: 1
Average comments per issue: 0
Average comments per pull request: 0.0
Merged pull requests: 0
Bot issues: 0
Bot pull requests: 0

View more stats

Top Authors

Issue Authors

f0k (7)
guoxuesong (5)
saitarslanboun (3)
botev (3)
ghost (3)
rahashwini (3)
twiecki (2)
yzhl0929 (2)
justheuristic (2)
radarsat1 (1)
MartinThoma (1)
Erotemic (1)
ciaua (1)
quintendewilde (1)
ashish2811 (1)

Pull Request Authors

f0k (6)
Sentient07 (6)
ReyhaneAskari (2)
skaae (2)
digantamisra98 (1)
vvmurthy (1)
JasonnnW3000 (1)
SimonKohl (1)
luizgh (1)
TobyPDE (1)
jonashen (1)
rp2872 (1)
wafuwafu13 (1)
christopher-beckham (1)
pleabargain (1)

Top Labels

Issue Labels

easy (3) documentation (2) enhancement (1)

Pull Request Labels

documentation (1)

Packages

Total packages: 2
Total downloads:
- pypi 1,145 last-month

Total dependent packages: 2
(may contain duplicates)
Total dependent repositories: 43
(may contain duplicates)
Total versions: 3
Total maintainers: 1

pypi.org: lasagne

A lightweight library to build and train neural networks in Theano

Homepage: https://github.com/Lasagne/Lasagne
Documentation: https://lasagne.readthedocs.io/
License: MIT
Latest release: 0.1dev
published over 2 years ago

Versions: 2
Dependent Packages: 1
Dependent Repositories: 42
Downloads: 1,145 Last month

Rankings

Stargazers count: 1.1%

Forks count: 1.3%

Dependent repos count: 2.3%

Average: 3.5%

Downloads: 5.7%

Dependent packages count: 7.3%

Maintainers (1)

sedielem

Last synced: 6 months ago

conda-forge.org: lasagne

A lightweight library to build and train neural networks in Theano

Homepage: https://github.com/Lasagne/Lasagne
License: MIT
Latest release: 0.1
published over 6 years ago

Versions: 1
Dependent Packages: 1
Dependent Repositories: 1

Rankings

Forks count: 4.9%

Stargazers count: 5.8%

Average: 15.9%

Dependent repos count: 24.1%

Dependent packages count: 28.9%

Last synced: 6 months ago

Dependencies

requirements-dev.txt pypi

Jinja2 ==2.7.3 development
Sphinx ==1.2.3 development
mock * development
numpydoc * development
pep8 ==1.6.2 development
pytest * development
pytest-cov * development
pytest-pep8 * development
sphinx_rtd_theme * development

requirements.txt pypi

Theano >=0.8.2

setup.py pypi

Theano *
numpy *