# vturrisi/solo-learn

solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning

Repository: https://github.com/vturrisi/solo-learn
Canonical: https://ross.abutalabs.com/products/solo-learn
Language: Python
License: MIT
License Family: permissive
Topics: simclr, nvidia-dali, contrastive-learning, pytorch, pytorch-lightning, barlow-twins, self-supervised-learning, swav, byol, moco, simsiam, vicreg, nnclr, dino, deepcluster, ressl, vibcreg, transformer-models, mae, masked-input-prediction
Last push: 2026-07-27T18:04:22+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 94, release rhythm 8, longevity 100
- inputs: {"age_days": 2006, "days_push": 37, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1573, forks 206 (observed 2026-08-28T04:05:05.604329+00:00)

## What it is
solo-learn is a Python library of state-of-the-art self-supervised methods for unsupervised visual representation learning, built on PyTorch Lightning. It implements methods like SimCLR, MoCo, BYOL, SwAV, DINO, MAE, and VicReg in a comparable, configurable environment with training tricks and utilities.

## Use cases
- train self-supervised models on images without labels
- pretrain a vision backbone with contrastive learning
- compare SSL methods like SimCLR, BYOL, and DINO under the same setup
- learn visual representations for downstream classification
- pretrain MAE or transformer models on ImageNet
- run linear evaluation and finetuning of pretrained backbones

## When to choose
- you need many self-supervised vision methods in one consistent framework
- you want PyTorch Lightning-based training with Hydra/OmegaConf configs
- you need ImageNet-scale SSL training with GPU/DALI support

## When to avoid
- you need supervised image classification out of the box
- you work outside computer vision (e.g., NLP or audio SSL)
- you want a maintained library with frequent updates

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, nlp
- domain: machine-learning, deep-learning, computer-vision, image-processing
- platform: python
- tags: self-supervised-learning, contrastive-learning, pytorch-lightning, simclr, byol, moco, swav, dino, mae, vicreg, barlow-twins, representation-learning, nvidia-dali, gpu, linux, docker

## Member repositories
- vturrisi/solo-learn (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:05.604329+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 2026-08-30T03:58:04.595761+00:00, confidence not recorded.
  - readme: https://github.com/vturrisi/solo-learn (fetched 2026-08-28T04:05:05.604329+00:00, sha 768c1a39c933)
  - registry_pypi: https://pypi.org/pypi/solo-learn/json (fetched 2026-08-29T11:28:09.530406+00:00, sha 22508f6d6905)
- Data as of 2026-08-30T08:39:29.467469+00:00.