# ozan-oktay/Attention-Gated-Networks

Use of Attention Gates in a Convolutional Neural Network / Medical Image Classification and Segmentation

Repository: https://github.com/ozan-oktay/Attention-Gated-Networks
Canonical: https://ross.abutalabs.com/products/attention-gated-networks
Language: Python
License: MIT
License Family: permissive
Topics: convolutional-neural-networks, attention-model, image-classification, image-segmentation, attention-gates
Last push: 2020-11-13T15:17:55+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3075, "days_push": 2119, "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 2064, forks 436 (observed 2026-08-28T04:06:10.027854+00:00)

## What it is
A PyTorch implementation of attention gates for convolutional neural networks, applied to U-Net and VGG-16 architectures. It targets medical image classification and segmentation tasks, as described in the authors' MIDL 2018 papers.

## Use cases
- add attention gates to a U-Net segmentation model
- train a CNN for medical image segmentation
- implement Attention U-Net for pancreas segmentation
- classify ultrasound scan planes with attention-gated networks
- reproduce results from the Attention U-Net paper
- improve CNN interpretability with attention maps

## When to choose
- you need a reference PyTorch implementation of attention gates for medical imaging
- you want to reproduce or extend the Attention U-Net or Sononet papers
- you are doing research on attention mechanisms in CNNs

## When to avoid
- you need a maintained, production-ready segmentation framework
- you want a general-purpose attention/transformer library
- you need support for frameworks other than PyTorch

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: deep-learning, computer-vision, healthcare, image-processing
- platform: python
- tags: pytorch, attention-gates, unet, medical-imaging, image-segmentation, image-classification, research-code

## Member repositories
- ozan-oktay/Attention-Gated-Networks (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:10.027854+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 2026-08-30T02:57:09.364616+00:00, confidence not recorded.
  - readme: https://github.com/ozan-oktay/Attention-Gated-Networks (fetched 2026-08-28T04:06:10.027854+00:00, sha 15f6bc19e929)
- Data as of 2026-08-30T08:39:29.467469+00:00.