4uiiurz1/pytorch-nested-unet

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1045 stars · 221 forks observed · 2026-08-28

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

A PyTorch implementation of the UNet++ (Nested U-Net) architecture for image segmentation, based on the paper 'UNet++: A Nested U-Net Architecture for Medical Image Segmentation'. It includes training and evaluation scripts with support for multi-class segmentation and datasets like the 2018 Data Science Bowl.

Use cases

• train a UNet++ model for image segmentation in pytorch
• segment medical images with nested u-net
• reproduce UNet++ results on the 2018 Data Science Bowl dataset
• train a segmentation model on my own images and masks
• compare U-Net and UNet++ IoU on a segmentation benchmark
• multi-class semantic segmentation with pytorch

When to choose

• you need a ready-to-run PyTorch implementation of UNet++ for segmentation tasks
• you want to reproduce the paper's results or benchmark against U-Net
• you have a dataset in images/masks folder structure and want a simple training pipeline

When to avoid

• you need a maintained, production-grade segmentation framework with many architectures
• you work in TensorFlow, Keras, or another non-PyTorch ecosystem
• you need deep supervision, attention gates, or other advanced variants beyond the paper's core model
• you require active updates or recent PyTorch version compatibility guarantees

Facets

library · maturity maintenance

machine-learning deep-learning image-processing computer-vision deep-learning computer-vision image-processing healthcare python windows unet unet-plus-plus pytorch image-segmentation semantic-segmentation medical-imaging nested-unet model-implementation gpu linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="4uiiurz1/pytorch-nested-unet")