# zllrunning/face-parsing.PyTorch

Using modified BiSeNet for face parsing in PyTorch

Repository: https://github.com/zllrunning/face-parsing.PyTorch
Canonical: https://ross.abutalabs.com/products/face-parsingpytorch
Language: Python
License: MIT
License Family: permissive
Topics: face-parsing, semantic-segmentation, pytorch, celeba-hq-dataset, bisenet, face-segmentation
Last push: 2023-05-21T14:00:45+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": 2695, "days_push": 1200, "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 2586, forks 497 (observed 2026-08-28T04:07:02.669452+00:00)

## What it is
A PyTorch implementation of face parsing using a modified BiSeNet architecture, trained on the CelebAMask-HQ dataset. It provides training scripts and a pre-trained model for segmenting facial regions such as hair, lips, and skin.

## Use cases
- segment faces into semantic regions like hair, lips, and skin
- generate face parsing maps from portrait photos
- train a custom face segmentation model on CelebAMask-HQ
- build virtual makeup or face editing tools
- extract hair or lip masks for image editing pipelines

## When to choose
- you need per-pixel facial region segmentation in PyTorch
- you want a ready pre-trained model for face parsing
- you plan to fine-tune segmentation on CelebAMask-HQ

## When to avoid
- you need real-time segmentation on CPU-only devices
- you need full-body or general scene segmentation
- you prefer TensorFlow or ONNX-first workflows

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, image-processing, machine-learning, deep-learning
- domain: computer-vision, image-processing, machine-learning, deep-learning
- platform: python, cross-platform
- tags: face-parsing, semantic-segmentation, bisenet, pytorch, celeba-hq, face-segmentation, pretrained-model, gpu

## Member repositories
- zllrunning/face-parsing.PyTorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:02.669452+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 2026-08-30T02:22:27.093714+00:00, confidence not recorded.
  - readme: https://github.com/zllrunning/face-parsing.PyTorch (fetched 2026-08-28T04:07:02.669452+00:00, sha 7a536e04c118)
- Data as of 2026-08-30T08:39:29.467469+00:00.