# facebookresearch/mae

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

Repository: https://github.com/facebookresearch/mae
Canonical: https://ross.abutalabs.com/products/mae
Language: Python
License: NOASSERTION
License Family: other
Archived: true
Last push: 2024-07-23T18:15:40+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": 1731, "days_push": 771, "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 8370, forks 1348 (observed 2026-08-28T04:10:20.541302+00:00)

## What it is
A PyTorch/GPU re-implementation of the Masked Autoencoders (MAE) paper for self-supervised vision learning. It includes pre-training code, fine-tuning code, pre-trained ViT checkpoints, and a visualization demo.

## Use cases
- pretrain vision transformers with masked autoencoding
- fine-tune MAE checkpoints on ImageNet classification
- reproduce the MAE paper results in PyTorch
- visualize masked image reconstruction
- use self-supervised pretraining for downstream vision tasks

## When to choose
- you want to pretrain or fine-tune ViT models with MAE in PyTorch
- you need official pre-trained MAE checkpoints
- you are studying or reproducing self-supervised vision research

## When to avoid
- you need a maintained production library with regular updates
- you want a general-purpose computer vision toolkit rather than MAE specifically
- you cannot use PyTorch or GPU resources

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing
- domain: computer-vision, deep-learning, machine-learning
- platform: python
- tags: pytorch, self-supervised-learning, masked-autoencoder, vision-transformer, pretrained-models, research-code, gpu, linux

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

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:20.541302+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 2026-08-29T17:27:33.578183+00:00, confidence not recorded.
  - readme: https://github.com/facebookresearch/mae (fetched 2026-08-28T04:10:20.541302+00:00, sha 8a2546073cb5)
- Data as of 2026-08-30T08:39:29.467469+00:00.