# switchablenorms/DeepFashion2

DeepFashion2 Dataset https://arxiv.org/pdf/1901.07973.pdf

Repository: https://github.com/switchablenorms/DeepFashion2
Canonical: https://ross.abutalabs.com/products/deepfashion2
Language: Jupyter Notebook
License Family: other
Last push: 2025-01-28T04:30:15+00:00

## Health v2 (maintenance only)
Score: 34/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 3, release rhythm 35, longevity 100
- inputs: {"age_days": 2787, "days_push": 582, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2625, forks 379 (observed 2026-08-28T04:07:05.269141+00:00)

## What it is
DeepFashion2 is a large-scale fashion dataset with 491K images covering 13 clothing categories, annotated with bounding boxes, dense landmarks, per-pixel masks, and 873K commercial-consumer clothing pairs. It includes train, validation, and test splits plus baseline code for tasks like landmark estimation and clothes retrieval.

## Use cases
- train a clothing detection model
- segment clothes in images with per-pixel masks
- estimate dense landmarks on garments
- build a consumer-to-shop clothes retrieval system
- benchmark fashion image classification across 13 categories
- research clothing style and viewpoint variation

## When to choose
- you need labeled fashion imagery for detection, segmentation, or landmark tasks
- you are researching cross-domain commercial-consumer clothing matching
- you want a benchmark for fashion computer vision challenges

## When to avoid
- you need a permissively licensed dataset for commercial products (no license is specified)
- your domain is not fashion or clothing imagery
- you need video or text fashion data rather than images

## Facets
- artifact type: dataset
- maturity: stable
- function: computer-vision, image-processing, machine-learning
- domain: computer-vision, image-processing, machine-learning
- platform: python, cross-platform
- tags: fashion, dataset, image-segmentation, landmark-estimation, clothes-retrieval, object-detection, instance-segmentation

## Member repositories
- switchablenorms/DeepFashion2 (main) score 34

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:05.269141+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 2026-08-30T02:19:51.663060+00:00, confidence not recorded.
  - readme: https://github.com/switchablenorms/DeepFashion2 (fetched 2026-08-28T04:07:05.269141+00:00, sha 4e8d21d6be06)
- Data as of 2026-08-30T08:39:29.467469+00:00.