# divamgupta/image-segmentation-keras

Implementation of Segnet, FCN, UNet , PSPNet and other models in Keras.

Repository: https://github.com/divamgupta/image-segmentation-keras
Canonical: https://ross.abutalabs.com/products/image-segmentation-keras
Homepage: https://divamgupta.com/image-segmentation/2019/06/06/deep-learning-semantic-segmentation-keras.html
Language: Python
License: MIT
License Family: permissive
Last push: 2024-05-12T08:11:21+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": 3453, "days_push": 843, "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 3003, forks 1149 (observed 2026-08-28T04:07:37.504723+00:00)

## What it is
A Keras library implementing popular deep learning semantic image segmentation models including SegNet, FCN, U-Net, and PSPNet. It provides both Python and CLI interfaces for training and inference, with a PyPI package (keras-segmentation).

## Use cases
- train a semantic segmentation model in keras
- segment images pixel-wise with unet
- implement FCN or PSPNet without writing from scratch
- fine-tune a pretrained segmentation model on my own dataset
- run image segmentation from the command line
- classify every pixel of an image into classes

## When to choose
- you want ready-made implementations of classic segmentation architectures in Keras
- you need a simple Python API or CLI to train and predict segmentation masks
- you want to fine-tune models like VGG-U-Net or ResNet-PSPNet on custom data

## When to avoid
- you need PyTorch or TensorFlow 2-native modern segmentation toolkits
- you need instance segmentation or object detection rather than semantic segmentation
- you need actively developed state-of-the-art architectures like transformers-based segmentation

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, image-processing, computer-vision, cli
- domain: computer-vision, image-processing, deep-learning, machine-learning
- platform: python, cross-platform
- tags: semantic-segmentation, keras, unet, fcn, pspnet, segnet, deep-learning

## Member repositories
- divamgupta/image-segmentation-keras (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:37.504723+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 2026-08-30T07:30:25.405818+00:00, confidence not recorded.
  - readme: https://github.com/divamgupta/image-segmentation-keras (fetched 2026-08-28T04:07:37.504723+00:00, sha 9a1768daa350)
  - homepage: https://divamgupta.com/image-segmentation/2019/06/06/deep-learning-semantic-segmentation-keras.html (fetched 2026-08-29T09:45:45.572840+00:00, sha f846a2059d1d)
  - site_page: https://divamgupta.com/about (fetched 2026-08-29T09:45:45.583406+00:00, sha 09b177e5ab31)
- Data as of 2026-08-30T08:39:29.467469+00:00.