SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1912.03458 · 2019

Dynamic Convolution: Attention over Convolution Kernels

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 1 has 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/1912.03458.json · badge: /api/ran/1912.03458.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
TArdelean/DynamicConvolution community (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
prstrive/CondConv-tensorflow community (classifier label)
classifier basis not recorded on the link
0 ran · 2 no recorded run
FunctionStatusWhere it lives
compute_entropy Ran
ran on a synthesized input
TArdelean/DynamicConvolution/inspect_attention.py
code served (permissive licence) · get_code("e36ca5f4167e4e43")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function expects prob_dict, which is a dictionary where:
# - keys are arbitrary (used as output keys)
# - values are lists/iterables of tensors that can be concatenated
# Each value is passed to one_resolution which:
# 1. Calls torch.cat(prob) on the list of tensors
# 2. Passes the result to torch.distributions.Categorical
# 3. Calls .entropy() and .mean() on it

# Categorical expects probabilities that sum to 1 along the last dimension
# We'll create small probability tensors (batch_size=2, num_categories=4)

prob_list_1 = [
    torch.tensor([[0.1, 0.2, 0.3, 0.4], [0.25, 0.25, 0.25, 0.25]]),
    torch.tensor([[0.4, 0.3, 0.2, 0.1], [0.1, 0.1, 0.7, 0.1]])
]

prob_list_2 = [
    torch.tensor([[0.5, 0.5, 0.0, 0.0], [0.2, 0.2, 0.3, 0.3]]),
]

ARGS = {
    "prob_dict": {
        "resolution_a": prob_list_1,
        "resolution_b": prob_list_2
    }
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
make_divisible Ran
ran, honoured the contract we drafted
TArdelean/DynamicConvolution/models/mobilenetv3.py
pointer only (licence: MIT); the stored copy get_code serves, from chris-boson/fashion_mnist, is pointer only (licence: NONE) · get_code("63ec083689f80f47")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from chris-boson/fashion_mnist, and GitHub detected no licence in that repository 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.

get_cifar_dataset Not yet run
unverified (harvested, no recorded run)
prstrive/CondConv-tensorflow/dataset.py
code served (permissive licence) · get_code("2376fefdf0b2d1bc")
How it ran

no invocation recorded.

get_datasets Not yet run
unverified (harvested, no recorded run)
prstrive/CondConv-tensorflow/dataset.py
code served (permissive licence) · get_code("f9cfc6fd89dbb714")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 3 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.

FunctionAlso present inEarliest-datedOthers named
make_divisible 12 other papers
6 dated earlier, 6 later · 1 only as an assembly brick
1503.03832 (2015-03)
FaceNet: A Unified Embedding for Face Recognition and Clustering
1801.04381 (2018-01)
MobileNetV2: Inverted Residuals and Linear Bottlenecks
1811.08383 (2018-11)
TSM: Temporal Shift Module for Efficient Video Understanding
and 9 more not named here

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) suffer performance degradation as their low computational budgets constrain both the depth (number of convolution layers) and the width (number of channels) of CNNs, resulting in limited representation capability. To address this issue, we present Dynamic Convolution, a new design that increases model complexity without increasing the network depth or width. Instead of using a single convolution kernel per layer, dynamic convolution aggregates multiple parallel convolution kernels dynamically based upon their attentions, which are input dependent. Assembling multiple kernels is not only computationally efficient due to the small kernel size, but also has more representation power since these kernels are aggregated in a non-linear way via attention. By simply using dynamic convolution for the state-of-the-art architecture MobileNetV3-Small, the top-1 accuracy of ImageNet classification is boosted by 2.9% with only 4% additional FLOPs and 2.9 AP gain is achieved on COCO keypoint detection.

For agents

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

get_harvested_code_for_paper("1912.03458")
get_code_for_paper("1912.03458")
have("1912.03458")

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

curl https://syntology.ai/api/ran/1912.03458.json

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

[![Syntology run record](https://syntology.ai/api/ran/1912.03458.svg)](https://syntology.ai/paper/1912.03458)

Connect an agent — have() is free.