qubvel/segmentation_models

Health v2 · maintenance only

Adoption not part of the score

4923 stars · 1041 forks observed · 2026-08-28

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

A Python library providing neural network architectures for image segmentation (Unet, FPN, Linknet, PSPNet) built on Keras and TensorFlow Keras. It offers 25 pretrained backbones per architecture plus segmentation losses and metrics, with a two-line high-level API.

Use cases

• train an image segmentation model with pretrained backbones
• build a UNet in Keras with two lines of code
• semantic segmentation of medical images
• binary and multi-class pixel-wise classification
• use EfficientNet or ResNet encoders for segmentation
• apply Dice and Focal losses for segmentation training

When to choose

• you need ready-made segmentation architectures with pretrained encoders in Keras/TensorFlow
• you want a simple high-level API for image segmentation experiments
• you need segmentation-specific losses and metrics out of the box

When to avoid

• you work in PyTorch (use segmentation_models.pytorch instead)
• you need cutting-edge transformer-based segmentation models
• you require frequent updates or new architecture support

Facets

library · maturity maintenance

machine-learning deep-learning image-processing computer-vision image-processing deep-learning machine-learning python image-segmentation unet fpn pspnet linknet pretrained-backbones keras tensorflow

Member repositories

For agents

markdown · JSON · MCP: product_card(name="qubvel/segmentation_models")