# google-research/simclr

SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners

Repository: https://github.com/google-research/simclr
Canonical: https://ross.abutalabs.com/products/simclr
Homepage: https://arxiv.org/abs/2006.10029
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: simclr, contrastive-learning, representation-learning, self-supervised-learning, unsupervised-learning, computer-vision, simclrv2
Archived: true
Last push: 2023-05-22T04:42:53+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2367, "days_push": 1199, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4502, forks 664 (observed 2026-08-28T04:08:51.536709+00:00)

## What it is
Google Research's official implementation of SimCLR and SimCLRv2, a framework for contrastive learning of visual representations, with 65 pretrained ResNet checkpoints in TensorFlow. It supports unsupervised pretraining, semi-supervised fine-tuning on few labels, and distillation into smaller models.

## Use cases
- pretrain image models with self-supervised contrastive learning
- fine-tune pretrained vision models with few labeled examples
- download SimCLRv2 pretrained ResNet checkpoints
- distill a large vision model into a smaller one
- learn how contrastive learning works from reference code

## When to choose
- you want proven SimCLRv2 pretrained checkpoints in TensorFlow
- you have lots of unlabeled images and few labels
- you need a research-grade reference implementation of contrastive learning

## When to avoid
- you need PyTorch rather than TensorFlow
- you want an actively developed library with new features
- you need a general-purpose training framework rather than a research codebase

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

## Member repositories
- google-research/simclr (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:51.536709+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 2026-08-29T18:20:24.444347+00:00, confidence not recorded.
  - readme: https://github.com/google-research/simclr (fetched 2026-08-28T04:08:51.536709+00:00, sha 1b141e96691d)
  - homepage: https://arxiv.org/abs/2006.10029 (fetched 2026-08-29T09:06:33.181412+00:00, sha 9ef6722ab397)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T09:06:33.190655+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T09:06:33.194096+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T09:06:33.196016+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T09:06:33.192452+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.