# bubbliiiing/deeplabv3-plus-pytorch

这是一个deeplabv3-plus-pytorch的源码，可以用于训练自己的模型。

Repository: https://github.com/bubbliiiing/deeplabv3-plus-pytorch
Canonical: https://ross.abutalabs.com/products/deeplabv3-plus-pytorch
Language: Python
License: MIT
License Family: permissive
Last push: 2023-10-18T07:07:50+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 1833, "days_push": 1050, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1292, forks 201 (observed 2026-08-28T04:04:16.090280+00:00)

## What it is
A PyTorch implementation of the DeepLabv3+ semantic segmentation model with MobileNetV2 and Xception backbones. It includes scripts for training on custom VOC-format datasets, prediction, and mIoU evaluation, with downloadable pretrained weights.

## Use cases
- train a semantic segmentation model on my own dataset
- segment objects in images with deeplabv3+
- evaluate mIoU of a segmentation model on VOC
- run image segmentation with pretrained xception weights
- fine-tune deeplabv3+ with mobilenet backbone
- segment objects in a video

## When to choose
- you need a well-documented, easy-to-run DeepLabv3+ implementation in PyTorch
- you want to train semantic segmentation on custom VOC-format labeled data
- you want pretrained weights and simple predict/train scripts for learning or prototyping

## When to avoid
- you need a production-grade segmentation pipeline or a maintained library with an API
- you need other segmentation architectures or the latest SOTA models
- you need support for newer PyTorch versions or active development

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: computer-vision, image-processing, deep-learning, machine-learning
- platform: python
- tags: semantic-segmentation, deeplabv3-plus, pytorch, model-training, pretrained-weights

## Member repositories
- bubbliiiing/deeplabv3-plus-pytorch (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:16.090280+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 2026-08-30T04:54:43.687343+00:00, confidence not recorded.
  - readme: https://github.com/bubbliiiing/deeplabv3-plus-pytorch (fetched 2026-08-28T04:04:16.090280+00:00, sha 8642bb95078a)
- Data as of 2026-08-30T08:39:29.467469+00:00.