# shelhamer/fcn.berkeleyvision.org

Fully Convolutional Networks for Semantic Segmentation by Jonathan Long*, Evan Shelhamer*, and Trevor Darrell. CVPR 2015 and PAMI 2016.

Repository: https://github.com/shelhamer/fcn.berkeleyvision.org
Canonical: https://ross.abutalabs.com/products/fcnberkeleyvisionorg
Homepage: http://fcn.berkeleyvision.org
Language: Python
License Family: other
Last push: 2021-09-27T10:14:15+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 4103, "days_push": 1801, "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 3350, forks 1429 (observed 2026-08-28T04:07:57.806243+00:00)

## What it is
Reference implementation of Fully Convolutional Networks (FCN) for semantic segmentation from the CVPR 2015 / PAMI 2016 papers, built on Caffe. It includes pretrained PASCAL VOC models (FCN-32s/16s/8s and FCN-AlexNet) and training/evaluation code.

## Use cases
- run semantic segmentation on images with pretrained FCN models
- reproduce FCN PASCAL VOC benchmark results
- fine-tune FCN-32s/16s/8s on my own segmentation dataset
- study the original fully convolutional network implementation
- train an FCN-AlexNet segmentation model in Caffe

## When to choose
- you need the canonical FCN models and code from the original authors
- your stack is already Caffe-based
- you want pretrained PASCAL VOC segmentation weights

## When to avoid
- you use PyTorch or TensorFlow rather than Caffe
- you need actively maintained or production-ready segmentation tooling
- you want modern architectures like DeepLab or Mask R-CNN

## Facets
- artifact type: library
- maturity: maintenance
- function: deep-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning, image-processing
- platform: python
- tags: semantic-segmentation, fcn, caffe, pascal-voc, research-code, cvpr-2015, linux, gpu

## Member repositories
- shelhamer/fcn.berkeleyvision.org (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:57.806243+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 2026-08-29T18:40:58.396864+00:00, confidence not recorded.
  - readme: https://github.com/shelhamer/fcn.berkeleyvision.org (fetched 2026-08-28T04:07:57.806243+00:00, sha 96158b97a9bf)
  - homepage: http://fcn.berkeleyvision.org (fetched 2026-08-29T09:34:10.738188+00:00, sha 86399788b3c6)
- Data as of 2026-08-30T08:39:29.467469+00:00.