# MarvinTeichmann/tensorflow-fcn

An Implementation of Fully Convolutional Networks in Tensorflow.

Repository: https://github.com/MarvinTeichmann/tensorflow-fcn
Canonical: https://ross.abutalabs.com/products/tensorflow-fcn
Language: Python
License: MIT
License Family: permissive
Topics: tensorflow, vgg, segmentation
Last push: 2017-12-15T15:43:15+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": 3750, "days_push": 3183, "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 1094, forks 421 (observed 2026-08-28T04:03:34.024620+00:00)

## What it is
A single-file TensorFlow implementation of Fully Convolutional Networks (FCN) for semantic segmentation, using VGG16 weights loaded from a .npy file. It is designed to be integrated into custom segmentation pipelines and finetuned on user data.

## Use cases
- implement fully convolutional networks in tensorflow
- semantic segmentation of images
- finetune vgg16 for pixel-wise classification
- convert vgg classification weights into an fcn
- build a segmentation pipeline for datasets like kitti or pascal voc

## When to choose
- you are maintaining legacy TensorFlow 1.x code that needs an FCN
- you want a minimal, single-file FCN implementation to study or modify
- you need VGG16-based segmentation without a Caffe dependency

## When to avoid
- you are starting a new project - use TensorFlow 2.x, PyTorch, or modern segmentation libraries
- you need pretrained Pascal VOC segmentation weights out of the box
- you require active maintenance, GPU modern features, or recent TensorFlow versions

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, image-processing
- domain: computer-vision, machine-learning, deep-learning
- platform: python
- tags: tensorflow, fcn, semantic-segmentation, vgg16, computer-vision, deprecated, linux, gpu

## Member repositories
- MarvinTeichmann/tensorflow-fcn (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:34.024620+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 2026-08-30T06:47:27.398004+00:00, confidence not recorded.
  - readme: https://github.com/MarvinTeichmann/tensorflow-fcn (fetched 2026-08-28T04:03:34.024620+00:00, sha 2634b4642f02)
- Data as of 2026-08-30T08:39:29.467469+00:00.