# jakeret/tf_unet

Generic U-Net Tensorflow implementation for image segmentation

Repository: https://github.com/jakeret/tf_unet
Canonical: https://ross.abutalabs.com/products/tf_unet
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: image-segmentation, neural-network, deep-learning, tensorflow
Last push: 2020-05-05T09:29:55+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3673, "days_push": 2311, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1907, forks 731 (observed 2026-08-28T04:05:52.551840+00:00)

## What it is
A generic U-Net implementation built on TensorFlow 1.x for training image segmentation models on arbitrary imaging data. Originally developed for radio frequency interference mitigation in radio astronomy and now discontinued in favor of a TensorFlow 2 reimplementation.

## Use cases
- train a U-Net for image segmentation on custom imaging data
- detect radio frequency interference in radio astronomy data
- segment galaxies and stars in wide-field astronomical images
- run a toy segmentation problem like detecting circles in noisy images
- learn how U-Net architectures are implemented in TensorFlow

## When to choose
- you are working with TensorFlow 1.x and need a flexible U-Net for segmentation
- you want a reference implementation tied to the published RFI mitigation paper
- your use case matches the astronomy examples in the documentation

## When to avoid
- you are starting a new project, since the project is discontinued in favor of the TensorFlow 2 successor jakeret/unet
- you need TensorFlow 2 or Keras compatibility
- you need actively maintained code with recent bug fixes

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: machine-learning, deep-learning, computer-vision, image-processing
- platform: python
- tags: unet, image-segmentation, tensorflow, convolutional-neural-networks, radio-astronomy

## Member repositories
- jakeret/tf_unet (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:52.551840+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 2026-08-30T03:11:16.087120+00:00, confidence not recorded.
  - readme: https://github.com/jakeret/tf_unet (fetched 2026-08-28T04:05:52.551840+00:00, sha 3d8023fddec3)
- Data as of 2026-08-30T08:39:29.467469+00:00.