jakeret/tf_unet

Health v2 · maintenance only

Adoption not part of the score

1907 stars · 731 forks observed · 2026-08-28

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

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

library · maturity abandoned

machine-learning deep-learning image-processing computer-vision machine-learning deep-learning computer-vision image-processing python unet image-segmentation tensorflow convolutional-neural-networks radio-astronomy

Member repositories

For agents

markdown · JSON · MCP: product_card(name="jakeret/tf_unet")