# bonlime/keras-deeplab-v3-plus

Keras implementation of Deeplab v3+ with pretrained weights

Repository: https://github.com/bonlime/keras-deeplab-v3-plus
Canonical: https://ross.abutalabs.com/products/keras-deeplab-v3-plus
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2024-11-13T21:31:06+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3092, "days_push": 658, "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 1375, forks 421 (observed 2026-08-28T04:04:33.136810+00:00)

## What it is
A Keras implementation of the DeepLab v3+ semantic image segmentation model with pretrained weights imported from the original TensorFlow checkpoint. It supports custom input shapes and class counts, and produces per-pixel class labels for images.

## Use cases
- segment images into semantic classes with a pretrained deeplab v3+ model
- run pixel-level image segmentation in keras
- load original TF deeplab weights into a keras model
- fine-tune deeplab v3+ with a custom number of classes
- get per-pixel segmentation labels for photos

## When to choose
- you need DeepLab v3+ semantic segmentation in a Keras/TensorFlow pipeline
- you want pretrained weights matching the original TF model's results
- you need custom input shapes or a custom number of segmentation classes

## When to avoid
- you need an actively maintained project with issue support
- you use PyTorch or non-Keras frameworks
- you need the latest segmentation architectures or recent model improvements

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: computer-vision, image-processing, deep-learning, machine-learning
- platform: python
- tags: semantic-segmentation, keras, deeplabv3-plus, pretrained-weights, tensorflow, mobilenetv2, xception

## Member repositories
- bonlime/keras-deeplab-v3-plus (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:33.136810+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 2026-08-30T04:40:33.741818+00:00, confidence not recorded.
  - readme: https://github.com/bonlime/keras-deeplab-v3-plus (fetched 2026-08-28T04:04:33.136810+00:00, sha d0dbf99c4972)
- Data as of 2026-08-30T08:39:29.467469+00:00.