Welcome to Lasagne

Lasagne is a lightweight library to build and train neural networks in Theano.

Lasagne is a work in progress, input is welcome. The available documentation is limited for now. The project is on GitHub.

User Guide

The Lasagne user guide explains how to install Lasagne, how to build and train neural networks using Lasagne, and how to contribute to the library as a developer.

• Installation
  • Prerequisites
  • Stable Lasagne release
  • Bleeding-edge version
  • Development installation
  • GPU support
  • Docker
• Tutorial
  • Before we start
  • Run the MNIST example
  • Understand the MNIST example
  • Where to go from here
• Layers
  • Creating a layer
  • Creating a network
  • Naming layers
  • Initializing parameters
  • Parameter sharing
  • Propagating data through layers
• Creating custom layers
  • A simple layer
  • A layer that changes the shape
  • A layer with parameters
  • A layer with multiple behaviors
• Development
  • Philosophy
  • What to contribute
  • How to contribute

API Reference

If you are looking for information on a specific function, class or method, this part of the documentation is for you.

• lasagne.layers
• lasagne.updates
  • Examples
  • Update functions
  • Update modification functions
  • Helper functions
• lasagne.init
  • Examples
  • Initializers
  • Detailed description
• lasagne.nonlinearities
  • Detailed description
• lasagne.objectives
  • Examples
  • Loss functions
  • Aggregation functions
  • Evaluation functions
• lasagne.regularization
  • Examples
  • Helper functions
  • Penalty functions
• lasagne.random
• lasagne.utils

Indices and tables

• Index
• Module Index
• Search Page