# 4uiiurz1/pytorch-nested-unet

PyTorch implementation of UNet++ (Nested U-Net).

Repository: https://github.com/4uiiurz1/pytorch-nested-unet
Canonical: https://ross.abutalabs.com/products/pytorch-nested-unet
Language: Python
License: MIT
License Family: permissive
Topics: unet, pytorch, image-segmentation
Last push: 2020-04-10T03:55:37+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2842, "days_push": 2336, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1045, forks 221 (observed 2026-08-28T04:03:21.592041+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: deep-learning, computer-vision, image-processing, healthcare
- platform: python, windows
- tags: unet, unet-plus-plus, pytorch, image-segmentation, semantic-segmentation, medical-imaging, nested-unet, model-implementation, gpu, linux, macos

## Member repositories
- 4uiiurz1/pytorch-nested-unet (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:21.592041+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 2026-08-30T07:02:01.743023+00:00, confidence not recorded.
  - readme: https://github.com/4uiiurz1/pytorch-nested-unet (fetched 2026-08-28T04:03:21.592041+00:00, sha ca0284a9665f)
- Data as of 2026-08-30T08:39:29.467469+00:00.