LogoopenSUSE Build Service > Projects
Sign Up | Log In


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"

Source Files

Filename Size Changed Actions
Lasagne-master-20160426.tar.gz 127 KB about 2 years ago Download File
python-Lasagne.changes 235 Bytes about 2 years ago Download File
python-Lasagne.spec 4.54 KB about 2 years ago Download File

Comments for home:inescid:learning (0)