# luuuyi/CBAM.PyTorch

Non-official implement of Paper：CBAM: Convolutional Block Attention Module

Repository: https://github.com/luuuyi/CBAM.PyTorch
Canonical: https://ross.abutalabs.com/products/cbampytorch
Language: Python
License Family: other
Last push: 2023-07-12T10:24:30+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": 2913, "days_push": 1148, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1500, forks 290 (observed 2026-08-28T04:04:54.171390+00:00)

## What it is
A non-official PyTorch re-implementation of the CBAM (Convolutional Block Attention Module) paper from ECCV 2018. It provides channel and spatial attention modules that can be inserted into convolutional networks like ResNet to improve image classification accuracy.

## Use cases
- add attention modules to a resnet in pytorch
- reproduce CBAM paper results on ImageNet
- improve image classification accuracy with attention
- learn how channel and spatial attention works
- plug CBAM blocks into my own CNN architecture

## When to choose
- you want a simple PyTorch implementation of CBAM to drop into your models
- you are studying or reproducing the ECCV 2018 CBAM paper
- you need verified ImageNet gains from adding attention to ResNet

## When to avoid
- you need an officially maintained library with a license
- you want a broad toolkit of many attention mechanisms
- you need support for modern PyTorch versions out of the box

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: computer-vision, deep-learning, image-processing
- platform: python
- tags: attention-module, cbam, pytorch, image-classification, resnet, paper-implementation

## Member repositories
- luuuyi/CBAM.PyTorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:54.171390+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 2026-08-30T04:33:00.349628+00:00, confidence not recorded.
  - readme: https://github.com/luuuyi/CBAM.PyTorch (fetched 2026-08-28T04:04:54.171390+00:00, sha ede1291440a0)
- Data as of 2026-08-30T08:39:29.467469+00:00.