# VainF/DeepLabV3Plus-Pytorch

Pretrained DeepLabv3 and DeepLabv3+ for Pascal VOC & Cityscapes

Repository: https://github.com/VainF/DeepLabV3Plus-Pytorch
Canonical: https://ross.abutalabs.com/products/deeplabv3plus-pytorch
Language: Python
License: MIT
License Family: permissive
Topics: deeplabv3plus, deeplabv3, pytorch, pascal-voc, cityscapes, segmentation
Last push: 2022-11-15T13:01:22+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": 2743, "days_push": 1387, "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 2699, forks 521 (observed 2026-08-28T04:07:11.318920+00:00)

## What it is
A PyTorch library providing pretrained DeepLabv3 and DeepLabv3+ semantic segmentation models for Pascal VOC and Cityscapes datasets. It includes multiple backbone architectures (ResNet, MobileNet, HRNet, Xception), training scripts, and prediction tools.

## Use cases
- run semantic segmentation on images with pretrained deeplabv3+
- segment cityscapes street scenes
- train deeplabv3+ on my own dataset
- compare segmentation backbones like resnet, mobilenet, hrnet, xception
- predict segmentation masks for a folder of images
- fine-tune a pretrained segmentation model in pytorch

## When to choose
- you need ready-to-use pretrained DeepLabv3/v3+ models in PyTorch
- you want to train or fine-tune semantic segmentation on custom datasets
- you need Pascal VOC or Cityscapes segmentation baselines

## When to avoid
- you need real-time or instance/panoptic segmentation
- you work outside PyTorch (e.g., TensorFlow)
- you need actively maintained code with recent updates

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: machine-learning, computer-vision, image-processing
- platform: python, cross-platform
- tags: semantic-segmentation, deeplabv3plus, pytorch, pretrained-models, pascal-voc, cityscapes

## Member repositories
- VainF/DeepLabV3Plus-Pytorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:11.318920+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 2026-08-30T02:16:07.146269+00:00, confidence not recorded.
  - readme: https://github.com/VainF/DeepLabV3Plus-Pytorch (fetched 2026-08-28T04:07:11.318920+00:00, sha 51cbffc7fdec)
- Data as of 2026-08-30T08:39:29.467469+00:00.