# xmu-xiaoma666/External-Attention-pytorch

🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

Repository: https://github.com/xmu-xiaoma666/External-Attention-pytorch
Canonical: https://ross.abutalabs.com/products/external-attention-pytorch
Language: Python
License: MIT
License Family: permissive
Topics: attention, pytorch, paper, cbam, squeeze, excitation-networks, linear-layers, visual-tasks
Last push: 2026-03-16T08:58:41+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 72, release rhythm 35, longevity 100
- inputs: {"age_days": 1943, "days_push": 170, "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 12183, forks 1941 (observed 2026-08-28T04:10:51.964326+00:00)

## What it is
A PyTorch library (fightingcv-attention) providing clean, minimal implementations of numerous attention mechanisms, MLP variants, re-parameterization modules, and convolution blocks from research papers. It is designed to help researchers and learners understand paper core ideas without digging through complex task-specific codebases.

## Use cases
- implement attention mechanisms in pytorch
- understand attention papers through code
- add cbam or squeeze-excitation to my model
- find minimal implementations of vision transformer attention modules
- learn how re-parameterization modules work
- use attention blocks as plug-and-play components in my network
- compare different attention mechanism implementations

## When to choose
- you want readable, standalone implementations of attention/MLP/conv modules from papers
- you need plug-and-play PyTorch modules for research experiments
- you are learning deep learning architecture concepts from code

## When to avoid
- you need production-tested, heavily optimized layers
- you need full model architectures for detection or segmentation rather than individual modules
- you need frameworks other than PyTorch

## Facets
- artifact type: library
- maturity: active
- function: deep-learning, machine-learning, image-processing
- domain: deep-learning, computer-vision, machine-learning
- platform: python
- tags: attention-mechanisms, pytorch, paper-implementations, mlp, re-parameterization, convolution, cbam, squeeze-excitation, research, educational

## Member repositories
- xmu-xiaoma666/External-Attention-pytorch (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:51.964326+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 2026-08-29T17:14:51.610183+00:00, confidence not recorded.
  - readme: https://github.com/xmu-xiaoma666/External-Attention-pytorch (fetched 2026-08-28T04:10:51.964326+00:00, sha 264275e3c552)
- Data as of 2026-08-30T08:39:29.467469+00:00.