# shekkizh/FCN.tensorflow

Tensorflow implementation of Fully Convolutional Networks for Semantic Segmentation (http://fcn.berkeleyvision.org)

Repository: https://github.com/shekkizh/FCN.tensorflow
Canonical: https://ross.abutalabs.com/products/fcntensorflow
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: segmentation, tensorflow, fcn
Last push: 2022-03-17T18:05:54+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": 3618, "days_push": 1630, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1248, forks 520 (observed 2026-08-28T04:04:07.755557+00:00)

## What it is
A TensorFlow implementation of Fully Convolutional Networks (FCN) for semantic segmentation, based on the reference code from the original paper authors. It was trained on the MIT Scene Parsing Challenge dataset and includes training, visualization, and debug tooling.

## Use cases
- implement fcn for semantic segmentation in tensorflow
- train a scene parsing model on mit ade20k dataset
- learn how fully convolutional networks work with example code
- segment objects in images with a pretrained fcn model
- reference implementation of fcn paper in tensorflow

## When to choose
- you need a simple, readable TensorFlow 0.x implementation of FCN for learning purposes
- you want to reproduce the FCN paper on the MIT Scene Parsing dataset
- you are studying semantic segmentation model architecture and training details

## When to avoid
- you need support for modern TensorFlow versions (2.x) or current Python
- you need a production-ready or actively maintained segmentation solution
- you want state-of-the-art segmentation accuracy with modern architectures

## 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, cross-platform
- tags: semantic-segmentation, fully-convolutional-networks, tensorflow, scene-parsing, fcn, jupyter-notebook, gpu, linux

## Member repositories
- shekkizh/FCN.tensorflow (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:07.755557+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 2026-08-30T05:07:54.578165+00:00, confidence not recorded.
  - readme: https://github.com/shekkizh/FCN.tensorflow (fetched 2026-08-28T04:04:07.755557+00:00, sha dcb082dbd789)
- Data as of 2026-08-30T08:39:29.467469+00:00.