# microsoft/Swin-Transformer

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

Repository: https://github.com/microsoft/Swin-Transformer
Canonical: https://ross.abutalabs.com/products/swin-transformer
Homepage: https://arxiv.org/abs/2103.14030
Language: Python
License: MIT
License Family: permissive
Topics: swin-transformer, image-classification, object-detection, semantic-segmentation, imagenet, mscoco, ade20k, mask-rcnn
Last push: 2024-07-24T17:09:57+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1987, "days_push": 770, "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 16051, forks 2215 (observed 2026-08-28T04:11:14.736504+00:00)

## What it is
Official PyTorch implementation of the Swin Transformer, a hierarchical vision transformer using shifted windows that serves as a general-purpose backbone for computer vision. It provides code and pretrained models for image classification and links to companion repos for detection, segmentation, and video tasks.

## Use cases
- classify images with a pretrained vision transformer
- train a Swin Transformer backbone on ImageNet
- use Swin as a backbone for object detection on COCO
- semantic segmentation on ADE20K with Swin
- fine-tune Swin Transformer V2 models
- run masked image modeling pretraining

## When to choose
- you need a strong, well-tested vision transformer backbone for classification or dense prediction
- you want official pretrained checkpoints from a widely cited paper
- you need linear-complexity attention for high-resolution images

## When to avoid
- you need a lightweight model for edge or mobile deployment
- you want a plug-and-play pip package rather than research code
- you need tasks outside vision, such as NLP

## Facets
- artifact type: library
- maturity: stable
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: computer-vision, deep-learning, machine-learning, image-processing
- platform: python
- tags: vision-transformer, shifted-windows, image-classification, object-detection, semantic-segmentation, pretrained-models, pytorch, gpu, linux

## Member repositories
- microsoft/Swin-Transformer (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:14.736504+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 2026-08-29T17:05:15.771384+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/Swin-Transformer (fetched 2026-08-28T04:11:14.736504+00:00, sha f24f06e54b3d)
  - homepage: https://arxiv.org/abs/2103.14030 (fetched 2026-08-29T08:03:05.597613+00:00, sha 2c689c502ab0)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T08:03:05.601045+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T08:03:05.604851+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T08:03:05.606886+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T08:03:05.603009+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.