# facebookresearch/swav

PyTorch implementation of SwAV https//arxiv.org/abs/2006.09882

Repository: https://github.com/facebookresearch/swav
Canonical: https://ross.abutalabs.com/products/swav
Language: Python
License: NOASSERTION
License Family: other
Archived: true
Last push: 2023-04-13T16:40:34+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2239, "days_push": 1238, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2096, forks 286 (observed 2026-08-28T04:06:13.317504+00:00)

## What it is
PyTorch implementation of SwAV, a self-supervised method for pre-training convolutional networks without labels by swapping cluster assignments between augmented image views. Includes pretrained ResNet-50 models and training scripts for ImageNet-scale experiments.

## Use cases
- pretrain a vision backbone without labels
- download SwAV pretrained ResNet-50 weights
- reproduce self-supervised learning research results
- replace supervised ImageNet backbone with self-supervised features
- train self-supervised models with large or small batches

## When to choose
- you need label-free visual representation pretraining
- you want efficient self-supervised training without large memory banks or momentum encoders
- you want a strong pretrained ResNet-50 backbone for transfer learning

## When to avoid
- you need transformer-based self-supervised methods like DINO or MAE
- you need a production-ready maintained library rather than research code
- you work outside PyTorch

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: computer-vision, machine-learning, deep-learning
- platform: python
- tags: self-supervised-learning, contrastive-learning, pytorch, pretrained-models, representation-learning, research-code, gpu

## Member repositories
- facebookresearch/swav (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:13.317504+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 2026-08-30T02:54:36.062340+00:00, confidence not recorded.
  - readme: https://github.com/facebookresearch/swav (fetched 2026-08-28T04:06:13.317504+00:00, sha fd8a9b971607)
- Data as of 2026-08-30T08:39:29.467469+00:00.