alexgkendall/caffe-segnet

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1083 stars · 443 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity abandoned

deep-learning machine-learning image-processing computer-vision deep-learning computer-vision image-processing machine-learning cpp semantic-segmentation segnet caffe encoder-decoder cudnn pixel-wise-labeling research-code linux gpu cuda

Member repositories

For agents

markdown · JSON · MCP: product_card(name="alexgkendall/caffe-segnet")