# lisa-lab/pylearn2

Warning: This project does not have any current developer. See bellow.

Repository: https://github.com/lisa-lab/pylearn2
Canonical: https://ross.abutalabs.com/products/pylearn2
Language: Python
License: BSD-3-Clause
License Family: permissive
Last push: 2021-08-20T18:03:31+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 5763, "days_push": 1839, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2767, forks 1082 (observed 2026-08-28T04:07:18.680627+00:00)

## What it is
Pylearn2 is a Python machine learning research library built on top of Theano, developed by the LISA lab at Université de Montréal. It provides models, training algorithms, and datasets for deep learning research, including GPU-accelerated convolutional network wrappers.

## Use cases
- train deep neural networks on MNIST or CIFAR-10
- run machine learning experiments with Theano
- implement custom models and training algorithms for research
- use GPU-accelerated convolutional networks
- reproduce historical state-of-the-art deep learning results

## When to choose
- you need to reproduce or extend legacy research code written with Pylearn2 or Theano
- you are studying historical deep learning implementations like maxout networks

## When to avoid
- you are starting a new machine learning project - the project has no active developers
- you want a maintained framework - use PyTorch, TensorFlow, or Keras instead

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning
- platform: python
- tags: theano, deep-learning, research-library, deprecated, neural-networks, research, gpu

## Member repositories
- lisa-lab/pylearn2 (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:18.680627+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 2026-08-30T08:16:44.344097+00:00, confidence not recorded.
  - readme: https://github.com/lisa-lab/pylearn2 (fetched 2026-08-28T04:07:18.680627+00:00, sha 67c61523ea7d)
- Data as of 2026-08-30T08:39:29.467469+00:00.