# Lasagne/Lasagne

Lightweight library to build and train neural networks in Theano

Repository: https://github.com/Lasagne/Lasagne
Canonical: https://ross.abutalabs.com/products/lasagne
Homepage: http://lasagne.readthedocs.org/
Language: Python
License: NOASSERTION
License Family: other
Topics: deep-learning-library, neural-networks, python, theano
Last push: 2022-03-26T02:58:32+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 4374, "days_push": 1621, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3857, forks 929 (observed 2026-08-28T04:08:27.466233+00:00)

## What it is
Lasagne is a lightweight Python library for building and training neural networks on top of Theano. It supports feed-forward, convolutional, and recurrent architectures with transparent CPU/GPU execution via Theano's symbolic differentiation.

## Use cases
- build and train convolutional neural networks in Python
- implement LSTM recurrent networks for research
- train neural networks on GPU with Theano
- define custom cost functions without deriving gradients
- prototype multi-input multi-output network architectures

## When to choose
- you already use Theano and want a thin, transparent layer API
- you need full control over Theano expressions for research experiments
- you want modular layers, optimizers, and regularizers you can use independently

## When to avoid
- you are starting a new project - Theano is discontinued and PyTorch/TensorFlow are the modern choices
- you need an actively developed library with new features and community support
- you want high-level abstractions and prebuilt model zoos

## Facets
- artifact type: library
- maturity: maintenance
- function: deep-learning, machine-learning, gpu-computing
- domain: deep-learning, machine-learning
- platform: python, cross-platform
- tags: neural-networks, theano, cnn, lstm, research, gpu

## Member repositories
- Lasagne/Lasagne (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:27.466233+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:25:54.995771+00:00, confidence not recorded.
  - readme: https://github.com/Lasagne/Lasagne (fetched 2026-08-28T04:08:27.466233+00:00, sha 65d010c90131)
  - registry_pypi: https://pypi.org/pypi/lasagne/json (fetched 2026-08-29T09:21:02.753133+00:00, sha be93aa93ad9c)
- Data as of 2026-08-30T08:39:29.467469+00:00.