zhixuhao/unet

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

4941 stars · 2001 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A Keras implementation of the U-Net convolutional network architecture for image segmentation, based on the original biomedical segmentation paper. It includes training scripts, data augmentation via Keras ImageDataGenerator, and a sample ISBI membrane dataset.

Use cases

• segment biomedical images like cell membranes
• train a U-Net model on my own image masks
• do binary image segmentation with Keras
• learn how U-Net is implemented in Keras
• apply data augmentation to a small segmentation dataset
• predict segmentation masks for test images

When to choose

• you want a simple, well-known Keras U-Net reference implementation
• you are doing binary segmentation on small datasets with augmentation
• you want a teaching example or starting point to modify the architecture

When to avoid

• you need multi-class segmentation or modern architectures out of the box
• you need actively maintained code compatible with recent TensorFlow/Keras versions
• you need a production-grade segmentation pipeline with evaluation metrics

Facets

library · maturity maintenance

deep-learning image-processing computer-vision machine-learning deep-learning computer-vision image-processing machine-learning python cross-platform unet keras tensorflow semantic-segmentation biomedical-imaging jupyter-notebook gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="zhixuhao/unet")