# PaddlePaddle/PaddleSeg

Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks in Semantic Segmentation, Interactive Segmentation, Panoptic Segmentation, Image Matting, 3D Segmentation, etc.

Repository: https://github.com/PaddlePaddle/PaddleSeg
Canonical: https://ross.abutalabs.com/products/paddleseg
Homepage: https://arxiv.org/abs/2101.06175
Language: Python
License: Apache-2.0
License Family: permissive
Topics: semantic-segmentation, image-segmentation, image-matting, interactive-segmentation, panoptic-segmentation, transformer, lane-detection, autonomous-driving, human-segmentation, video-segmentation, medical-image-segmentation
Last push: 2026-02-05T16:49:17+00:00

## Health v2 (maintenance only)
Score: 52/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 66, release rhythm 8, longevity 100
- inputs: {"age_days": 2565, "days_push": 209, "days_rel": 666, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 9382, forks 1711 (observed 2026-08-28T04:10:30.943142+00:00)

## What it is
PaddleSeg is an end-to-end image segmentation toolkit built on PaddlePaddle, offering a model zoo with dozens of pre-trained models for semantic, panoptic, interactive, and 3D segmentation as well as image matting. It supports the full workflow from model design and training to performance optimization and deployment.

## Use cases
- segment images with deep learning
- train a semantic segmentation model
- remove image backgrounds with matting
- detect road lanes for autonomous driving
- segment medical images like organs or tumors
- run real-time human or portrait segmentation
- fine-tune a pre-trained segmentation model on my own dataset

## When to choose
- you need pre-trained segmentation models out of the box
- you want an end-to-end pipeline from training to deployment
- you work with PaddlePaddle or need industrial-grade segmentation tasks like matting or lane detection

## When to avoid
- your stack is PyTorch- or TensorFlow-based and you need ecosystem interoperability
- you need general image classification or object detection rather than segmentation
- you want a lightweight inference-only tool without training infrastructure

## Facets
- artifact type: library
- maturity: active
- function: image-processing, computer-vision, machine-learning, deep-learning
- domain: computer-vision, image-processing, machine-learning, autonomous-vehicles, healthcare
- platform: python, cross-platform
- tags: semantic-segmentation, image-segmentation, panoptic-segmentation, image-matting, interactive-segmentation, medical-image-segmentation, lane-detection, pretrained-models, paddlepaddle, gpu

## Member repositories
- PaddlePaddle/PaddleSeg (main) score 52

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:30.943142+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 2026-08-29T17:22:21.036003+00:00, confidence not recorded.
  - readme: https://github.com/PaddlePaddle/PaddleSeg (fetched 2026-08-28T04:10:30.943142+00:00, sha c4df2451170a)
  - homepage: https://arxiv.org/abs/2101.06175 (fetched 2026-08-29T08:22:20.287475+00:00, sha d06da36755fb)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T08:22:20.296826+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T08:22:20.300346+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T08:22:20.302378+00:00, sha a1f16f915a9a)
  - registry_pypi: https://pypi.org/pypi/paddleseg/json (fetched 2026-08-29T08:22:20.304351+00:00, sha 47c8ea5fed53)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T08:22:20.298640+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.