# open-mmlab/mmfashion

Open-source toolbox for visual fashion analysis based on PyTorch

Repository: https://github.com/open-mmlab/mmfashion
Canonical: https://ross.abutalabs.com/products/mmfashion
Homepage: https://open-mmlab.github.io/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: visual-fashion-analysis, fashion-ai, attribute-prediction, clothes-retrieval, landmark-detection, deep-learning
Last push: 2024-05-10T22:41:30+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2504, "days_push": 845, "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 1369, forks 298 (observed 2026-08-28T04:04:31.800147+00:00)

## What it is
MMFashion is an open-source PyTorch-based toolbox for visual fashion analysis from the OpenMMLab project. It provides modular implementations and pre-trained models for attribute prediction, clothes retrieval, landmark detection, parsing/segmentation, outfit compatibility and recommendation, and virtual try-on.

## Use cases
- predict clothing attributes from images
- build a shop-the-look clothes retrieval system
- detect fashion landmarks on garment photos
- segment and parse clothing in images
- recommend compatible outfits
- try clothes on models virtually

## When to choose
- you need ready-to-use deep learning models for fashion image analysis
- you want a modular PyTorch codebase to extend with custom fashion tasks
- you want pre-trained model zoo checkpoints for fashion benchmarks like DeepFashion

## When to avoid
- you need actively maintained code with recent PyTorch support
- you need general-purpose clothing detection rather than analysis tasks
- you need production e-commerce infrastructure rather than research tooling

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: computer-vision, image-processing, deep-learning, e-commerce
- platform: python
- tags: fashion-analysis, attribute-prediction, clothes-retrieval, landmark-detection, virtual-try-on, fashion-segmentation, pytorch, open-mmlab, pretrained-models, linux, docker, gpu

## Member repositories
- open-mmlab/mmfashion (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:31.800147+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 2026-08-30T04:41:00.484061+00:00, confidence not recorded.
  - readme: https://github.com/open-mmlab/mmfashion (fetched 2026-08-28T04:04:31.800147+00:00, sha 98a965526de3)
  - homepage: https://open-mmlab.github.io/ (fetched 2026-08-29T11:57:53.386504+00:00, sha 1cf9be975246)
- Data as of 2026-08-30T08:39:29.467469+00:00.