# alexgkendall/caffe-segnet

Implementation of SegNet: A Deep Convolutional Encoder-Decoder Architecture for Semantic Pixel-Wise Labelling

Repository: https://github.com/alexgkendall/caffe-segnet
Canonical: https://ross.abutalabs.com/products/caffe-segnet
Homepage: http://mi.eng.cam.ac.uk/projects/segnet/
Language: C++
License: NOASSERTION
License Family: other
Last push: 2018-03-15T08:10:01+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": 4044, "days_push": 3093, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1083, forks 443 (observed 2026-08-28T04:03:31.161929+00:00)

## What it is
A modified version of the Caffe deep learning framework implementing SegNet, a deep convolutional encoder-decoder architecture for semantic pixel-wise image segmentation. It supports training and inference of SegNet models with cuDNN v2 acceleration.

## Use cases
- train a SegNet model for semantic segmentation
- run pixel-wise image labeling on a custom dataset
- reproduce the SegNet paper results
- run a live webcam semantic segmentation demo
- implement Bayesian SegNet for scene understanding research

## When to choose
- you need the original SegNet implementation for research reproduction
- you are already working with the Caffe framework
- you need a non-commercial, research-use segmentation codebase

## When to avoid
- you need a maintained framework with modern GPU support
- you want commercial use - the license is CC BY-NC only
- you prefer PyTorch or TensorFlow ecosystems
- you need recent cuDNN versions without switching forks

## Facets
- artifact type: library
- maturity: abandoned
- function: deep-learning, machine-learning, image-processing, computer-vision
- domain: deep-learning, computer-vision, image-processing, machine-learning
- platform: cpp
- tags: semantic-segmentation, segnet, caffe, encoder-decoder, cudnn, pixel-wise-labeling, research-code, linux, gpu, cuda

## Member repositories
- alexgkendall/caffe-segnet (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:31.161929+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 2026-08-30T06:50:21.058364+00:00, confidence not recorded.
  - readme: https://github.com/alexgkendall/caffe-segnet (fetched 2026-08-28T04:03:31.161929+00:00, sha 1ba81349a3dc)
- Data as of 2026-08-30T08:39:29.467469+00:00.