# jfzhang95/pytorch-deeplab-xception

DeepLab v3+ model in PyTorch. Support different backbones.

Repository: https://github.com/jfzhang95/pytorch-deeplab-xception
Canonical: https://ross.abutalabs.com/products/pytorch-deeplab-xception
Language: Python
License: MIT
License Family: permissive
Topics: deeplab-v3-plus, pytorch, xception, resnet, mobilenetv2, drn
Last push: 2024-08-04T04:22:21+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": 3002, "days_push": 759, "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 3000, forks 770 (observed 2026-08-28T04:07:37.432517+00:00)

## What it is
A PyTorch implementation of the DeepLab v3+ semantic segmentation model with support for multiple backbones (Xception, ResNet, MobileNet, DRN). It includes training and evaluation scripts for Pascal VOC, SBD, Cityscapes, and COCO datasets with multi-GPU support.

## Use cases
- train a DeepLab v3+ semantic segmentation model in PyTorch
- segment images with pretrained DeepLab v3+ weights on Pascal VOC
- swap segmentation backbones like ResNet, Xception, or MobileNetV2
- train semantic segmentation on Cityscapes or COCO datasets
- reproduce DeepLab v3+ mIoU benchmark results
- fine-tune a segmentation model with focal loss or balanced class weights

## When to choose
- you need a well-known, benchmarked DeepLab v3+ PyTorch implementation with pretrained weights
- you want to experiment with different segmentation backbones and datasets
- you need multi-GPU training for semantic segmentation

## When to avoid
- you need actively maintained code compatible with recent PyTorch versions
- you want the latest segmentation architectures like SegFormer or Mask2Former
- you need production-ready inference serving rather than research training code

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: computer-vision, deep-learning, machine-learning, image-processing
- platform: python, cross-platform
- tags: semantic-segmentation, deeplab-v3-plus, pytorch, xception, resnet, mobilenetv2, pretrained-models, pascal-voc, cityscapes, gpu, linux

## Member repositories
- jfzhang95/pytorch-deeplab-xception (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:37.432517+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 2026-08-30T07:30:35.215592+00:00, confidence not recorded.
  - readme: https://github.com/jfzhang95/pytorch-deeplab-xception (fetched 2026-08-28T04:07:37.432517+00:00, sha 41ecbd6e60e1)
- Data as of 2026-08-30T08:39:29.467469+00:00.