SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2211.12905 · NeurIPS · 2022

GhostNetV2: Enhance Cheap Operation with Long-Range Attention

Kai Han, Chang Xu, Yunhe Wang, Yehui Tang, Chao Xu, Jianyuan Guo

arXiv · PDF · Open in the Atlas

Code that ran

8 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (7 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 7 have no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2211.12905.json · badge: /api/ran/2211.12905.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
likyoo/GhostNetV2-PyTorch community
Papers with Code archive
8 ran · 2 no recorded run
FunctionStatusWhere it lives
Activation Ran
ran on a synthesized input · constructed an object; no result was computed
likyoo/GhostNetV2-PyTorch/ghostnetv2.py
pointer only (licence: NONE) · get_code("f295958130866a4d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, likyoo/GhostNetV2-PyTorch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ConvUnit Ran
ran on a synthesized input · constructed an object; no result was computed
likyoo/GhostNetV2-PyTorch/ghostnetv2.py
pointer only (licence: NONE) · get_code("5bc1a810d3aa4dfd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, likyoo/GhostNetV2-PyTorch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

GhostModule Ran
ran on a synthesized input · constructed an object; no result was computed
likyoo/GhostNetV2-PyTorch/ghostnetv2.py
pointer only (licence: NONE) · get_code("8e0938682f8c46bd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, likyoo/GhostNetV2-PyTorch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

GhostModuleMul Ran
ran on a synthesized input · constructed an object; no result was computed
likyoo/GhostNetV2-PyTorch/ghostnetv2.py
pointer only (licence: NONE) · get_code("0362c80e323d4270")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, likyoo/GhostNetV2-PyTorch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

GlobalAvgPooling Ran
ran on a synthesized input · constructed an object; no result was computed
likyoo/GhostNetV2-PyTorch/ghostnetv2.py
pointer only (licence: NONE) · get_code("5ba455372a5f8ea8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, likyoo/GhostNetV2-PyTorch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

MyHSigmoid Ran
ran on a synthesized input · constructed an object; no result was computed
likyoo/GhostNetV2-PyTorch/ghostnetv2.py
pointer only (licence: NONE) · get_code("218a488e241986f2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, likyoo/GhostNetV2-PyTorch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

SE Ran
ran on a synthesized input · constructed an object; no result was computed
likyoo/GhostNetV2-PyTorch/ghostnetv2.py
pointer only (licence: NONE) · get_code("3c1bd49a9cc3a99d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, likyoo/GhostNetV2-PyTorch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

_make_divisible Ran
ran, honoured the contract we drafted
likyoo/GhostNetV2-PyTorch/ghostnetv2.py
pointer only (licence: NONE) · get_code("75495d6418418155")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, likyoo/GhostNetV2-PyTorch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

GhostBottleneck Not yet run
unverified (harvested, no recorded run)
likyoo/GhostNetV2-PyTorch/ghostnetv2.py
pointer only (licence: NONE) · get_code("7394379d320c1eb9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, likyoo/GhostNetV2-PyTorch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

GhostNet Not yet run
unverified (harvested, no recorded run)
likyoo/GhostNetV2-PyTorch/ghostnetv2.py
pointer only (licence: NONE) · get_code("ae3b3871629b22b2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, likyoo/GhostNetV2-PyTorch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 10 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Light-weight convolutional neural networks (CNNs) are specially designed for applications on mobile devices with faster inference speed. The convolutional operation can only capture local information in a window region, which prevents performance from being further improved. Introducing self-attention into convolution can capture global information well, but it will largely encumber the actual speed. In this paper, we propose a hardware-friendly attention mechanism (dubbed DFC attention) and then present a new GhostNetV2 architecture for mobile applications. The proposed DFC attention is constructed based on fully-connected layers, which can not only execute fast on common hardware but also capture the dependence between long-range pixels. We further revisit the expressiveness bottleneck in previous GhostNet and propose to enhance expanded features produced by cheap operations with DFC attention, so that a GhostNetV2 block can aggregate local and long-range information simultaneously. Extensive experiments demonstrate the superiority of GhostNetV2 over existing architectures. For example, it achieves 75.3% top-1 accuracy on ImageNet with 167M FLOPs, significantly suppressing Ghost-NetV1 (74.5%) with a similar computational cost.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2211.12905")
get_code_for_paper("2211.12905")
have("2211.12905")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2211.12905.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2211.12905.svg)](https://syntology.ai/paper/2211.12905)

Connect an agent — have() is free.