This is a pre-production deployment of Warehouse. Changes made here affect the production instance of PyPI (
Help us improve Python packaging - Donate today!

A lightweight library to build and train neural networks in Theano

Project Description


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”


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

pip install -r
pip install

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


Documentation is available online:

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


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),
network = lasagne.layers.Conv2DLayer(network, 32, (3, 3),
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,
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,

# 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/, 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.


Lasagne is a work in progress, input is welcome.

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


0.1 (2015-08-13)

First release.

  • core contributors, in alphabetical order:
    • Eric Battenberg (@ebattenberg)
    • Sander Dieleman (@benanne)
    • Daniel Nouri (@dnouri)
    • Eben Olson (@ebenolson)
    • Aäron van den Oord (@avdnoord)
    • Colin Raffel (@craffel)
    • Jan Schlüter (@f0k)
    • Søren Kaae Sønderby (@skaae)
  • extra contributors, in chronological order:
    • Daniel Maturana (@dimatura): documentation, cuDNN layers, LRN
    • Jonas Degrave (@317070): get_all_param_values() fix
    • Jack Kelly (@JackKelly): help with recurrent layers
    • Gábor Takács (@takacsg84): support broadcastable parameters in lasagne.updates
    • Diogo Moitinho de Almeida (@diogo149): MNIST example fixes
    • Brian McFee (@bmcfee): MaxPool2DLayer fix
    • Martin Thoma (@MartinThoma): documentation
    • Jeffrey De Fauw (@JeffreyDF): documentation, ADAM fix
    • Michael Heilman (@mheilman): NonlinearityLayer, lasagne.random
    • Gregory Sanders (@instagibbs): documentation fix
    • Jon Crall (@erotemic): check for non-positive input shapes
    • Hendrik Weideman (@hjweide): set_all_param_values() test, MaxPool2DCCLayer fix
    • Kashif Rasul (@kashif): ADAM simplification
    • Peter de Rivaz (@peterderivaz): documentation fix
Release History

Release History

This version
History Node


History Node


Download Files

Download Files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

File Name & Checksum SHA256 Checksum Help Version File Type Upload Date
Lasagne-0.1.tar.gz (125.1 kB) Copy SHA256 Checksum SHA256 Source Aug 13, 2015

Supported By

WebFaction WebFaction Technical Writing Elastic Elastic Search Pingdom Pingdom Monitoring Dyn Dyn DNS Sentry Sentry Error Logging CloudAMQP CloudAMQP RabbitMQ Heroku Heroku PaaS Kabu Creative Kabu Creative UX & Design Fastly Fastly CDN DigiCert DigiCert EV Certificate Rackspace Rackspace Cloud Servers DreamHost DreamHost Log Hosting