Papers › Searching for MobileNetV3

Searching for MobileNetV3

6 May 2019ICCV 2019 10arXiv:1905.02244archive 2025-07-28

Andrew Howard, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang, Yukun Zhu, Ruoming Pang, Vijay Vasudevan, Quoc V. Le, Hartwig Adam

We present the next generation of MobileNets based on a combination of complementary search techniques as well as a novel architecture design. MobileNetV3 is tuned to mobile phone CPUs through a combination of hardware-aware network architecture search (NAS) complemented by the NetAdapt algorithm and then subsequently improved through novel architecture advances. This paper starts the exploration of how automated search algorithms and network design can work together to harness complementary approaches improving the overall state of the art. Through this process we create two new MobileNet models for release: MobileNetV3-Large and MobileNetV3-Small which are targeted for high and low resource use cases. These models are then adapted and applied to the tasks of object detection and semantic segmentation. For the task of semantic segmentation (or any dense pixel prediction), we propose a new efficient segmentation decoder Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP). We achieve new state of the art results for mobile classification, detection and segmentation. MobileNetV3-Large is 3.2% more accurate on ImageNet classification while reducing latency by 15% compared to MobileNetV2. MobileNetV3-Small is 4.6% more accurate while reducing latency by 5% compared to MobileNetV2. MobileNetV3-Large detection is 25% faster at roughly the same accuracy as MobileNetV2 on COCO detection. MobileNetV3-Large LR-ASPP is 30% faster than MobileNetV2 R-ASPP at similar accuracy for Cityscapes segmentation.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 105 code samples harvested from 22 repositories linked to this paper: 86 ran (of which 22 constructed an object rather than computing a result; 75 with no instrument failure: 9 honoured, 2 violated, 64 with no contract checked; 11 where Syntology's instrument failed) · 19 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 105 samples from 22 repositories, 86 ran (75 with no instrument failure; 11 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 21 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

67 repositories listed; official and paper-mentioned ones first.

2023-MindSpore-1/ms-code-185 mentioned on GitHubmindsporeSyntology: not harvested report
Deci-AI/super-gradients mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications (arXiv:1704.04861; that paper's own run record: 53 ran (of which 28 constructed an object rather than computing a result; 44 with no instrument failure: 4 honoured, 0 violated, 40 with no contract checked; 9 where Syntology's instrument failed) · 30 unverified), RepVGG: Making VGG-style ConvNets Great Again (arXiv:2101.03697; that paper's own run record: 13 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
IMvision12/keras-vision-models mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Swin Transformer: Hierarchical Vision Transformer using Shifted Windows (arXiv:2103.14030; that paper's own run record: 123 ran (of which 45 constructed an object rather than computing a result; 79 with no instrument failure: 6 honoured, 3 violated, 70 with no contract checked; 44 where Syntology's instrument failed) · 84 unverified); nothing checks that they implement this paper's method. report
Mind23-2/MindCode-58 mentioned on GitHubmindsporeSyntology: not harvested report
MrD1360/Keras-implementation-of-MobileNetv3-with-L-RASSP mentioned on GitHubtfSyntology: not harvested report
PolinaDruzhinina/mobilenet mentioned on GitHubpytorchSyntology: not harvested report
PolinaDruzhinina/modelnet mentioned on GitHubpytorchSyntology: 5 samples, 5 ran (1 instrument-failed) · 0 unverified report
RamposhPidrov/waifu2face mentioned on GitHubpytorchSyntology: not harvested report
Randl/MobileNetV3-pytorch mentioned on GitHubpytorchSyntology: 11 samples, 9 ran (1 instrument-failed) · 2 unverified report
Sakib1263/MobileNet-1D-2D-Tensorflow-Keras mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications (arXiv:1704.04861; that paper's own run record: 53 ran (of which 28 constructed an object rather than computing a result; 44 with no instrument failure: 4 honoured, 0 violated, 40 with no contract checked; 9 where Syntology's instrument failed) · 30 unverified) and MobileNetV2: Inverted Residuals and Linear Bottlenecks (arXiv:1801.04381; that paper's own run record: 85 ran (of which 40 constructed an object rather than computing a result; 64 with no instrument failure: 8 honoured, 0 violated, 56 with no contract checked; 21 where Syntology's instrument failed) · 26 unverified); nothing checks that they implement this paper's method. report
SpikeKing/mobilenet_v3 mentioned on GitHubpytorchSyntology: 7 samples, 5 ran (0 instrument-failed) · 2 unverified report
Syavaprd/mobilenet_v3 mentioned on GitHubpytorchSyntology: not harvested report
TheConstant3/MobileNetV3-Keras mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
akrapukhin/MobileNetV3 mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications (arXiv:1704.04861; that paper's own run record: 53 ran (of which 28 constructed an object rather than computing a result; 44 with no instrument failure: 4 honoured, 0 violated, 40 with no contract checked; 9 where Syntology's instrument failed) · 30 unverified) and MobileNetV2: Inverted Residuals and Linear Bottlenecks (arXiv:1801.04381; that paper's own run record: 85 ran (of which 40 constructed an object rather than computing a result; 64 with no instrument failure: 8 honoured, 0 violated, 56 with no contract checked; 21 where Syntology's instrument failed) · 26 unverified); nothing checks that they implement this paper's method. report
atregret/mobilenetv3 mentioned on GitHubmindsporeMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
chris-boson/fashion_mnist mentioned on GitHubpytorchSyntology: 9 samples, 9 ran (2 instrument-failed) · 0 unverified report
ckyrkou/EmergencyNet mentioned on GitHubtfSyntology: 4 samples, 3 ran (2 instrument-failed) · 1 unverified report
cyrilminaeff/MobileNet mentioned on GitHubpytorchSyntology: not harvested report
d-li14/mobilenetv3.pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
diasirish/mobilenetv3 mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications (arXiv:1704.04861; that paper's own run record: 53 ran (of which 28 constructed an object rather than computing a result; 44 with no instrument failure: 4 honoured, 0 violated, 40 with no contract checked; 9 where Syntology's instrument failed) · 30 unverified); nothing checks that they implement this paper's method. report
ekzhang/fastseg mentioned on GitHubpytorchMITSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
emilianavt/OpenSeeFace mentioned on GitHubtfBSD-2-ClauseSyntology: 15 samples, 11 ran (0 instrument-failed) · 4 unverified report
idealo/imagededup mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications (arXiv:1704.04861; that paper's own run record: 53 ran (of which 28 constructed an object rather than computing a result; 44 with no instrument failure: 4 honoured, 0 violated, 40 with no contract checked; 9 where Syntology's instrument failed) · 30 unverified); nothing checks that they implement this paper's method. report
jerry73204/mobilenet-v3-rs mentioned on GitHubpytorchMITSyntology: not harvested report
jmjeon94/MobileNet-Pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications (arXiv:1704.04861; that paper's own run record: 53 ran (of which 28 constructed an object rather than computing a result; 44 with no instrument failure: 4 honoured, 0 violated, 40 with no contract checked; 9 where Syntology's instrument failed) · 30 unverified) and MobileNetV2: Inverted Residuals and Linear Bottlenecks (arXiv:1801.04381; that paper's own run record: 85 ran (of which 40 constructed an object rather than computing a result; 64 with no instrument failure: 8 honoured, 0 violated, 56 with no contract checked; 21 where Syntology's instrument failed) · 26 unverified); nothing checks that they implement this paper's method. report
kuan-wang/pytorch-mobilenet-v3 mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
open-edge-platform/geti mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
osmr/imgclsmob mentioned on GitHubmxnetMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ResNeSt: Split-Attention Networks (arXiv:2004.08955; that paper's own run record: 28 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 7 where Syntology's instrument failed) · 20 unverified); nothing checks that they implement this paper's method. report
pengboxiangshang/mobilenetv3_pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
rwightman/efficientnet-jax mentioned on GitHubjaxSyntology: 5 samples, 4 ran (2 instrument-failed) · 1 unverified report
rwightman/genmobilenet-pytorch mentioned on GitHubpytorchApache-2.0Syntology: 11 samples, 6 ran (0 instrument-failed) · 5 unverified report
rwightman/pytorch-image-models mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights (arXiv:2006.08217; that paper's own run record: 4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
showlo/mobilenetv3 mentioned on GitHubpytorchSyntology: 6 samples, 6 ran (0 instrument-failed) · 0 unverified report
t-hanya/kuzushiji-recognition mentioned on GitHubMITSyntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified report
tensorflow/models mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
tensorflow/models mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
tiagoCuervo/JapaNet mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
ttruty/facial-feature-mouse-control mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications (arXiv:1704.04861; that paper's own run record: 53 ran (of which 28 constructed an object rather than computing a result; 44 with no instrument failure: 4 honoured, 0 violated, 40 with no contract checked; 9 where Syntology's instrument failed) · 30 unverified); nothing checks that they implement this paper's method. report
ujsyehao/mobilenetv3-ssd mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
wang-zidu/3ddfa-v3 mentioned on GitHubpytorchMITSyntology: 4 samples, 4 ran (2 instrument-failed) · 0 unverified report
xiaochus/MobileNetV3 mentioned on GitHubtfMITSyntology: 1 sample, 0 ran · 1 unverified report
xiaolai-sqlai/mobilenetv3 mentioned on GitHubpytorchMITSyntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report
xwu6614555/MobileNetV3-Mxnet mentioned on GitHubmxnetSyntology: not harvested report
yakhyo/head-pose-estimation mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Fine-Grained Head Pose Estimation Without Keypoints (arXiv:1710.00925; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified) and MobileNetV2: Inverted Residuals and Linear Bottlenecks (arXiv:1801.04381; that paper's own run record: 85 ran (of which 40 constructed an object rather than computing a result; 64 with no instrument failure: 8 honoured, 0 violated, 56 with no contract checked; 21 where Syntology's instrument failed) · 26 unverified); nothing checks that they implement this paper's method. report
2023-MindSpore-4/Code-5 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code-5 mindsporeSyntology: not harvested report
2024-MindSpore-1/Code4 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DeepTextMark: A Deep Learning-Driven Text Watermarking Approach for Identifying Large... (arXiv:2305.05773; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
MS-Mind/MS-Code-08 mindsporeSyntology: not harvested report
MS-Mind/MS-Code-08 mindsporeSyntology: not harvested report
Mind23-2/MindCode-101 mindsporeSyntology: not harvested report
Mind23-2/MindCode-101 mindsporeSyntology: not harvested report
Mind23-2/MindCode-102 mindsporeSyntology: not harvested report
Mind23-2/MindCode-3 mindsporeSyntology: not harvested report
OniroAI/Instance-segmentation-with-MobileNetV3 tfSyntology: 5 samples, 5 ran (1 instrument-failed) · 0 unverified report
PaddlePaddle/PaddleClas paddleApache-2.0Syntology: not harvested report
PaddlePaddle/PaddleDetection paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PP-YOLOE: An evolved version of YOLO (arXiv:2203.16250; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 0 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
PaddlePaddle/PaddleOCR paddleApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to KRETA: A Benchmark for Korean Reading and Reasoning in Text-Rich VQA Attuned to... (arXiv:2508.19944; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
dmlc/gluon-cv tfApache-2.0Syntology: not harvested report
gouthamvgk/coreml_conversion_hub pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (arXiv:1905.11946; that paper's own run record: 198 ran (of which 73 constructed an object rather than computing a result; 157 with no instrument failure: 26 honoured, 2 violated, 129 with no contract checked; 41 where Syntology's instrument failed) · 104 unverified); nothing checks that they implement this paper's method. report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
mindspore-ecosystem/mindcv mindsporeSyntology: not harvested report
open-edge-platform/training_extensions pytorchApache-2.0Syntology: not harvested report
open-mmlab/mmclassification pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Reversible Vision Transformers (arXiv:2302.04869; that paper's own run record: 24 ran (of which 5 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
open-mmlab/mmpose pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation (arXiv:2312.07526; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
pytorch/vision pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Going Deeper with Convolutions (arXiv:1409.4842; that paper's own run record: 34 ran (of which 19 constructed an object rather than computing a result; 30 with no instrument failure: 1 honoured, 0 violated, 29 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Deep Networks with Stochastic Depth (arXiv:1603.09382; that paper's own run record: 8 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified) and 7 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
xiuyu0000/vision mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (arXiv:1905.11946; that paper's own run record: 198 ran (of which 73 constructed an object rather than computing a result; 157 with no instrument failure: 26 honoured, 2 violated, 129 with no contract checked; 41 where Syntology's instrument failed) · 104 unverified); nothing checks that they implement this paper's method. report
gitlab.com/birder/birder pytorchSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

105 samples harvested: 86 ran (of which 22 constructed an object rather than computing a result; 75 with no instrument failure: 9 honoured, 2 violated, 64 with no contract checked; 11 where Syntology's instrument failed) · 19 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

9ran · honoured contract
2ran · violated contract
7ran · our draft was wrong
4ran; the contract check could not run
64ran
19unverified

Licence: 46 of the 105 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 22 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 11 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

PolinaDruzhinina/modelnet community (archive-listed) 5 samples, 5 ran (1 instrument-failed) · 0 unverified
BottleneckSE models/mobilenetv3.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 9e476824ce6c9115 · report fixture: returned BottleneckSE · level recorded 2026-09-22
MobileNetV3 models/mobilenetv3.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · dd0eb9bdaecad128 · report fixture: returned MobileNetV3 · level recorded 2026-09-22
SE in 13 papers models/mobilenetv3.py ran · metamorphic tier: deterministic no licence file found · pointer only · 2d9873a3665e1dd9 · report fixture: returned SE · level recorded 2026-09-22
h_sigmoid in 5 papers models/mobilenetv3.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 47cebc13301c1e23 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
hswish models/mobilenetv3.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · ecb1dac2f3a2944a · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
Randl/MobileNetV3-pytorch community (archive-listed) 11 samples, 9 ran (1 instrument-failed) · 2 unverified
DropBlock2D MobileNetV3.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · eea0d2df8bb7cbe4 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
DropBlockScheduled MobileNetV3.py ran fingerprinted MIT (permissive) · d44d7e19fe65cbc2 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
HardSigmoid MobileNetV3.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · fda5ccaf76461ba5 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
HardSwish MobileNetV3.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 0ae7cf2c14285d34 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
LastBlockLarge MobileNetV3.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 3b87793a966b3e95 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
LastBlockSmall MobileNetV3.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · ace014323d335247 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
LinearBottleneck MobileNetV3.py ran fingerprinted MIT (permissive) · e1bd359a8a7b96b2 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
SqEx MobileNetV3.py ran · metamorphic tier: invariant MIT (permissive) · 544e406c29c4e4cb · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
hard_swish MobileNetV3.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 7bcd0f441e3a0c6f · report fixture: signature x:Tensor/2/float, inplace:bool/0/bool · returned Tensor · level recorded 2026-09-22
MobileNetV3 MobileNetV3.py unverified MIT (permissive) · 5733827ea6ca2df0 · report
hard_sigmoid in 15 papers MobileNetV3.py unverified MIT (permissive) · ad6446d870a72a89 · report
SpikeKing/mobilenet_v3 community (archive-listed) 7 samples, 5 ran (0 instrument-failed) · 2 unverified
MobileBlock mn3_model.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 9e8d7789c4c389a6 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
SqueezeBlock mn3_model.py ran · metamorphic tier: invariant no licence file found · pointer only · 3ba84df153cca41e · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
_make_divisible in 9 papers mn3_model.py ran · honoured contract no licence file found · pointer only · 03eee59192d9c54e · report fixture: signature v:int/0/int, divisor:int/0/int, min_value:NoneType/0/? · returned int · level recorded 2026-09-22
h_sigmoid in 5 papers mn3_model.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 74b185a45e459a10 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
h_swish mn3_model.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · a9a67906bc9afd8a · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
MobileNetV3 mn3_model.py unverified no licence file found · pointer only · 271746eae93de918 · report
_weights_init in 7 papers mn3_model.py unverified no licence file found · pointer only · 5d99159796ececdc · report
TheConstant3/MobileNetV3-Keras community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
MobileNetV3Small src/mobilenetV3.py ran no licence file found · pointer only · 0c9f35bd6df82dc7 · report fixture: returned MobileNetV3Small · level recorded 2026-09-22
atregret/mobilenetv3 community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
get_lr in 91 papers src/lr_generator.py ran MIT (permissive) · bcab367eb4c6388e · report fixture: signature global_step:int/0/int, lr_init:float/0/float, lr_end:float/0/float, lr_max:float/0/float, warmup_epochs:int/0/int, total_epochs:int/0/int, steps_per_epoch:int/0/int · returned ndarray · level recorded 2026-09-24
chris-boson/fashion_mnist community (archive-listed) 9 samples, 9 ran (2 instrument-failed) · 0 unverified
Hsigmoid trainer/models/mobilenetv3.py ran fingerprinted no licence file found · pointer only · 4a269a6484171c4e · report fixture: returned Hsigmoid · level recorded 2026-09-22
Hswish trainer/models/mobilenetv3.py ran fingerprinted no licence file found · pointer only · d276d941f05c6062 · report fixture: returned Hswish · level recorded 2026-09-22
Identity in 49 papers
census: 10 implementations from 13 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
trainer/models/mobilenetv3.py ran fingerprinted no licence file found · pointer only · 9942e2eaf6ad275b · report fixture: returned Identity · level recorded 2026-09-22
MobileBottleneck trainer/models/mobilenetv3.py ran no licence file found · pointer only · 2d8a3aa3bbd7b78a · report fixture: returned MobileBottleneck · level recorded 2026-09-22
MobileNetV3 trainer/models/mobilenetv3.py ran no licence file found · pointer only · f54f64d3a22943e8 · report fixture: returned MobileNetV3 · level recorded 2026-09-22
SEModule in 7 papers trainer/models/mobilenetv3.py ran no licence file found · pointer only · be1d6e0d4c7fbed8 · report fixture: returned SEModule · level recorded 2026-09-22
conv_1x1_bn in 59 papers trainer/models/mobilenetv3.py ran · our draft was wrong no licence file found · pointer only · db82a4013a44fb42 · report fixture: signature inp:int/0/int, oup:int/0/int, conv_layer:callable/0/?, norm_layer:callable/0/?, nlin_layer:callable/0/? · returned Sequential · level recorded 2026-09-22
conv_bn in 88 papers trainer/models/mobilenetv3.py ran · our draft was wrong no licence file found · pointer only · 84a4cf301e929085 · report fixture: signature inp:int/0/int, oup:int/0/int, stride:int/0/int, conv_layer:callable/0/?, norm_layer:callable/0/?, nlin_layer:callable/0/? · returned Sequential · level recorded 2026-09-22
make_divisible in 76 papers trainer/models/mobilenetv3.py ran · honoured contract fingerprinted no licence file found · pointer only · 63ec083689f80f47 · report fixture: signature x:int/0/int, divisible_by:int/0/int · returned int · level recorded 2026-09-22
ckyrkou/EmergencyNet community (archive-listed) 4 samples, 3 ran (2 instrument-failed) · 1 unverified
activation in 30 papers code/model.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · d04dc47c293a9646 · report fixture: signature x:EagerTensor/4/float, ind:int/0/int, t:str/0/str, n:int/0/int · returned EagerTensor · level recorded 2026-09-22
fusion_block code/model.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 927b92925cff89c3 · report fixture: signature tensors:list/1/EagerTensor, name:str/0/str, type:str/0/str · returned EagerTensor · level recorded 2026-09-22
mish in 95 papers
census: 5 implementations from 8 papers, 1 distinct output on one shared input
code/model.py ran · honoured contract fingerprinted no licence file found · pointer only · 5426806a2db402eb · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22
atrous_block code/model.py unverified no licence file found · pointer only · b82827563bc7975b · report
d-li14/mobilenetv3.pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
SELayer in 12 papers mobilenetv3.py ran · metamorphic tier: deterministic MIT (permissive) · 3a744d625048086e · report fixture: returned SELayer · level recorded 2026-09-22
ekzhang/fastseg community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
blend in 12 papers fastseg/image/colorize.py ran MIT (permissive) · a27dd3605bd35022 · report fixture: signature input_img:Image/0/?, seg_img:Image/0/? · returned Image · level recorded 2026-09-24
colorize in 60 papers fastseg/image/colorize.py unverified MIT (permissive) · 5528da7e34b0c499 · report
get_trunk fastseg/model/utils.py unverified MIT (permissive) · ed8b51c771d7b05f · report
emilianavt/OpenSeeFace community (archive-listed) 15 samples, 11 ran (0 instrument-failed) · 4 unverified
clamp_to_im tracker.py ran BSD-2-Clause (permissive) · 812a03560e02d125 · report fixture: signature pt:list/1/float, w:int/0/int, h:int/0/int · returned tuple · level recorded 2026-09-24
decode in 57 papers retinaface.py ran fingerprinted BSD-2-Clause (permissive) · 24e984c89fc9c4d5 · report fixture: signature loc:ndarray/2/float, priors:ndarray/2/float, variances:ndarray/1/float · returned ndarray · level recorded 2026-09-24
get_bound_method_class similaritytransform.py ran BSD-2-Clause (permissive) · 04e390b8fa4ddf5b · report fixture: signature m:callable/0/? · returned type · level recorded 2026-09-24
logit_arr model.py ran fingerprinted BSD-2-Clause (permissive) · df8e996291f19181 · report fixture: signature p:Tensor/2/float, factor:float/0/float · returned Tensor · level recorded 2026-09-24
median in 9 papers remedian.py ran BSD-2-Clause (permissive) · 4cbeebb0d2fd1171 · report fixture: signature lst:list/1/int, ordered:bool/0/bool · returned float · level recorded 2026-09-24
py_cpu_nms in 13 papers retinaface.py ran fingerprinted BSD-2-Clause (permissive) · 1cbae9505b4428d7 · report fixture: signature dets:ndarray/2/float, thresh:float/0/float · returned list · level recorded 2026-09-24
resolve in 15 papers dshowcapture.py ran BSD-2-Clause (permissive) · a3f3322fd8b895ef · report fixture: returned str · level recorded 2026-09-24
rotate in 56 papers tracker.py ran BSD-2-Clause (permissive) · 424f887a9c6c2078 · report fixture: signature origin:tuple/1/float, point:tuple/1/float, a:float/0/float · returned tuple · level recorded 2026-09-24
safe_as_int similaritytransform.py ran BSD-2-Clause (permissive) · 67137622a1231779 · report fixture: signature val:float/0/float, atol:float/0/float · returned int64 · level recorded 2026-09-24
test_reader input_reader.py ran BSD-2-Clause (permissive) · 5344df98353e9f50 · report fixture: signature reader:MockReader/0/? · returned bool · level recorded 2026-09-24
try_int input_reader.py ran fingerprinted BSD-2-Clause (permissive) · 944db263a2d0cf75 · report fixture: signature s:str/0/str · returned int · level recorded 2026-09-24
AdapWingLoss model.py unverified BSD-2-Clause (permissive) · d0eb453f4721591c · report
create_frame_buffer dshowcapture.py unverified BSD-2-Clause (permissive) · bc162101f2b2253f · report
device_name escapi.py unverified BSD-2-Clause (permissive) · 4f22ad4d050b6b59 · report
estimate_transform similaritytransform.py unverified BSD-2-Clause (permissive) · d55431cb0ee73cd8 · report
kuan-wang/pytorch-mobilenet-v3 community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
MobileNetV3 mobilenetv3.py ran fingerprinted Apache-2.0 (permissive) · 6278668ba6ef59f3 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
pengboxiangshang/mobilenetv3_pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
MobileNetV3 MobileNetV3.py ran fingerprinted no licence file found · pointer only · a0eb27e3a8ffc484 · report fixture: returned MobileNetV3 · level recorded 2026-09-22
rwightman/efficientnet-jax community (archive-listed) 5 samples, 4 ran (2 instrument-failed) · 1 unverified
EfficientHead jeffnet/linen/blocks_linen.py ran Apache-2.0 (permissive) · fae9673025e2a220 · report fixture: returned EfficientHead · level recorded 2026-09-22
conv2d in 119 papers jeffnet/linen/blocks_linen.py ran · our draft was wrong Apache-2.0 (permissive) · 704704cc698dd1a4 · report fixture: signature features:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:str/0/str, dilation:int/0/int, groups:int/0/int, bias:bool/0/bool, dtype:callable/0/?, precision:NoneType/0/?, name:str/0/str, kernel_init:callable/0/?, bias_init:callable/0/? · returned Conv · level recorded 2026-09-22
linear in 88 papers jeffnet/linen/blocks_linen.py ran · our draft was wrong Apache-2.0 (permissive) · 9f9ace2e0eb7c4fe · report fixture: signature features:int/0/int, bias:bool/0/bool, dtype:callable/0/?, name:str/0/str, kernel_init:callable/0/?, bias_init:callable/0/? · returned Dense · level recorded 2026-09-22
to_tuple in 6 papers jeffnet/linen/blocks_linen.py ran · violated contract fingerprinted Apache-2.0 (permissive) · bc3a3914c7eee220 · report fixture: signature v:tuple/1/int, n:int/0/int · returned tuple · level recorded 2026-09-22
Dropout in 8 papers jeffnet/linen/blocks_linen.py unverified Apache-2.0 (permissive) · bb95cb930e46eee0 · report
rwightman/genmobilenet-pytorch community (archive-listed) 11 samples, 6 ran (0 instrument-failed) · 5 unverified
accuracy_np caffe2_validate.py ran · honoured contract Apache-2.0 (permissive) · ce856d9e51a3df05 · report fixture: signature output:ndarray/2/float, target:ndarray/1/int · returned tuple · level recorded 2026-09-24
conv2d_same in 8 papers geffnet/conv2d_layers.py ran Apache-2.0 (permissive) · 4ec99f9f08732346 · report fixture: signature x:Tensor/4/float, weight:Tensor/4/float, bias:Tensor/1/float, stride:tuple/1/int, padding:tuple/1/int, dilation:tuple/1/int, groups:int/0/int · returned Tensor · level recorded 2026-09-24
create_conv2d_pad in 6 papers geffnet/conv2d_layers.py ran Apache-2.0 (permissive) · d97a5cf595717b21 · report fixture: signature in_chs:int/0/int, out_chs:int/0/int, kernel_size:int/0/int · returned Conv2d · level recorded 2026-09-24
get_padding_value in 7 papers geffnet/conv2d_layers.py ran Apache-2.0 (permissive) · a5c3c9ce1a8998c4 · report fixture: signature padding:str/0/str, kernel_size:int/0/int, stride:int/0/int, dilation:int/0/int · returned tuple · level recorded 2026-09-24
layer_config_kwargs geffnet/config.py ran Apache-2.0 (permissive) · eed594a74863387a · report fixture: signature kwargs:dict/0/? · returned set_layer_config · level recorded 2026-09-24
resolve_bn_args geffnet/efficientnet_builder.py ran Apache-2.0 (permissive) · 7468ea92c204fba0 · report fixture: signature kwargs:dict/0/? · returned dict · level recorded 2026-09-24
create_model in 163 papers geffnet/model_factory.py unverified Apache-2.0 (permissive) · d842549186ebc802 · report
mnasnet_050 geffnet/gen_efficientnet.py unverified Apache-2.0 (permissive) · f630f3f49e01f56f · report
mnasnet_075 geffnet/gen_efficientnet.py unverified Apache-2.0 (permissive) · f196628d978e9c99 · report
mnasnet_100 geffnet/gen_efficientnet.py unverified Apache-2.0 (permissive) · 453e3b4fdec6b005 · report
resolve_act_layer geffnet/efficientnet_builder.py unverified Apache-2.0 (permissive) · 44867397fdc5b044 · report
showlo/mobilenetv3 community (archive-listed) 6 samples, 6 ran (0 instrument-failed) · 0 unverified
Bottleneck in 98 papers mobileNetV3.py ran · metamorphic tier: deterministic no licence file found · pointer only · 9a228be8d95a8267 · report fixture: returned Bottleneck · level recorded 2026-09-22
H_sigmoid mobileNetV3.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 557fa0210dc2d24b · report fixture: returned H_sigmoid · level recorded 2026-09-22
H_swish mobileNetV3.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 0d8cfba511f31324 · report fixture: returned H_swish · level recorded 2026-09-22
MobileNetV3 mobileNetV3.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 7f869bd47b2a9653 · report fixture: returned MobileNetV3 · level recorded 2026-09-22
SEModule in 7 papers mobileNetV3.py ran · metamorphic tier: deterministic no licence file found · pointer only · c89b0dcd2fc64746 · report fixture: returned SEModule · level recorded 2026-09-22
_ensure_divisible mobileNetV3.py ran · honoured contract fingerprinted no licence file found · pointer only · 06ed09c8c4a05763 · report fixture: signature number:int/0/int, divisor:int/0/int, min_value:int/0/int · returned int · level recorded 2026-09-22
t-hanya/kuzushiji-recognition community (archive-listed) 6 samples, 5 ran (0 instrument-failed) · 1 unverified
calc_f1_score kr/evaluation.py ran fingerprinted MIT (permissive) · ecdc06194e69eea3 · report fixture: signature n_tp:int/0/int, n_fp:int/0/int, n_fn:int/0/int · returned float · level recorded 2026-09-24
calc_iou_mat kr/detector/bbox_voting.py ran fingerprinted MIT (permissive) · 2049f6182035adfb · report fixture: signature bboxes1:ndarray/2/float, bboxes2:ndarray/2/float · returned ndarray · level recorded 2026-09-24
compare_with_ground_truth kr/evaluation.py ran MIT (permissive) · fd81c5c2c0790a12 · report fixture: signature pred_labels:list/1/dict, gt_labels:list/1/dict · returned tuple · level recorded 2026-09-24
evaluate_kuzushiji_recognition kr/evaluation.py ran MIT (permissive) · 4e6344480f924830 · report fixture: signature all_pred_labels:list/1/list, all_gt_labels:list/1/list · returned tuple · level recorded 2026-09-24
gaussian_radius in 25 papers kr/detector/centernet/heatmap.py ran MIT (permissive) · 4d72a8990678d08d · report fixture: signature bbox_size:tuple/1/int, min_overlap:float/0/float · returned float64 · level recorded 2026-09-24
generate_heatmap in 9 papers kr/detector/centernet/heatmap.py unverified MIT (permissive) · f1abace867b0c498 · report
tiagoCuervo/JapaNet community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
MobileNetV3 model.py ran no licence file found · pointer only · ddd66ea3aa2a3a65 · report fixture: signature x:ndarray/4/float · returned ndarray · level recorded 2026-09-24
ujsyehao/mobilenetv3-ssd community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
SeModule pytorch_model/mobilenetv3.py ran no licence file found · pointer only · 518da7f7fc849e72 · report fixture: returned SeModule · level recorded 2026-09-22
hsigmoid pytorch_model/mobilenetv3.py ran fingerprinted no licence file found · pointer only · ad3e66a9d6a27e29 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
wang-zidu/3ddfa-v3 community (archive-listed) 4 samples, 4 ran (2 instrument-failed) · 0 unverified
InvertedResidual in 9 papers model/mb_v3_networks.py ran · metamorphic tier: deterministic MIT (permissive) · 708f8102eea91f9e · report fixture: returned InvertedResidual · level recorded 2026-09-22
MobileNetV3 model/mb_v3_networks.py ran fingerprinted MIT (permissive) · 561f7b0eb338927a · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
conv_1x1_bn in 59 papers model/mb_v3_networks.py ran · our draft was wrong MIT (permissive) · 4e90491a30c2dc28 · report fixture: signature inp:int/0/int, oup:int/0/int · returned Sequential · level recorded 2026-09-22
conv_3x3_bn in 21 papers model/mb_v3_networks.py ran · our draft was wrong MIT (permissive) · 5221887077e3fb54 · report fixture: signature inp:int/0/int, oup:int/0/int, stride:int/0/int · returned Sequential · level recorded 2026-09-22
xiaochus/MobileNetV3 community (archive-listed) 1 sample, 0 ran · 1 unverified
resize_images_bilinear model/layers/bilinear_upsampling.py unverified MIT (permissive) · 059dddf26b4004e7 · report
xiaolai-sqlai/mobilenetv3 community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
build_transform in 170 papers datasets.py ran MIT recorded; this copy not marked cleared · pointer only · 6a0317bfd6be9557 · report fixture: signature is_train:bool/0/bool, args:Namespace/0/? · returned Compose · level recorded 2026-09-24
check_bn in 9 papers utils.py ran · violated contract MIT recorded; this copy not marked cleared · pointer only · 6e59364a7cf6008f · report fixture: signature model:callable/0/? · returned bool · level recorded 2026-09-22
cosine_scheduler in 74 papers utils.py ran · honoured contract MIT recorded; this copy not marked cleared · pointer only · b700fb0a3496b255 · report fixture: signature base_value:float/0/float, final_value:float/0/float, epochs:int/0/int, niter_per_ep:int/0/int, warmup_epochs:int/0/int, start_warmup_value:float/0/float, warmup_steps:int/0/int · returned ndarray · level recorded 2026-09-25
get_num_layer_for_convnext in 13 papers optim_factory.py ran · honoured contract fingerprinted MIT recorded; this copy not marked cleared · pointer only · 199223de2f9704cf · report fixture: signature var_name:str/0/str · returned int · level recorded 2026-09-25
get_parameter_groups in 30 papers optim_factory.py ran MIT recorded; this copy not marked cleared · pointer only · 0ef0019514eaaa09 · report fixture: signature model:callable/0/?, weight_decay:float/0/float, skip_list:tuple/1/empty, get_num_layer:callable/0/?, get_layer_scale:callable/0/? · returned list · level recorded 2026-09-25
OniroAI/Instance-segmentation-with-MobileNetV3 community (archive-listed) 5 samples, 5 ran (1 instrument-failed) · 0 unverified
ConvBlock in 61 papers
census: 8 implementations from 8 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
modules/keras_models.py ran GPL-3.0 (copyleft) · pointer only · 379eb0ad4b8f3ec3 · report fixture: returned ConvBlock · level recorded 2026-09-22
LiteRASSP modules/keras_models.py ran GPL-3.0 (copyleft) · pointer only · 8725aa67394a59c0 · report fixture: returned LiteRASSP · level recorded 2026-09-22
hard_swish modules/keras_models.py ran · honoured contract fingerprinted GPL-3.0 (copyleft) · pointer only · da02b7e3f57b5d87 · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22
relu6 in 14 papers modules/keras_models.py ran · honoured contract fingerprinted GPL-3.0 (copyleft) · pointer only · 02cff13546af958b · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22
return_activation modules/keras_models.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted GPL-3.0 (copyleft) · pointer only · 91abe93c3f37f65f · report fixture: signature x:EagerTensor/4/float, nl:str/0/str · returned EagerTensor · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

15 assemblies on this paper: 15 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

15 sibling assemblies for Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another. Bricks printed for 12 of 15 sibling assemblies; the other 3 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP) (graph method: Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP)). 6 bricks; individually on a fixture: 6 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 15 siblings

  1. MobileNetV3 entry · level 1 · ran · 7f869bd47b2a9653
  2. Bottleneck model · level 1 · ran · 9a228be8d95a8267
  3. H_swish helper · level 1 · ran · 0d8cfba511f31324
  4. _ensure_divisible helper · level 1 · ran · honoured contract · 06ed09c8c4a05763
  5. SEModule helper · level 1 · ran · c89b0dcd2fc64746
  6. H_sigmoid helper · level 1 · ran · 557fa0210dc2d24b

harvested Assembly for Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP) (graph method: Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP)). 5 bricks; individually on a fixture: 5 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 15 siblings

  1. LiteRASSP entry · level 1 · ran · 8725aa67394a59c0
  2. ConvBlock helper · level 1 · ran · 379eb0ad4b8f3ec3
  3. return_activation helper · level 1 · ran; the contract check could not run (RAISES) · 91abe93c3f37f65f
  4. hard_swish helper · level 1 · ran · honoured contract · da02b7e3f57b5d87
  5. relu6 helper · level 1 · ran · honoured contract · 02cff13546af958b

harvested Assembly for Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP) (graph method: Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP)). 3 bricks; individually on a fixture: 3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 15 siblings

  1. SELayer entry · level 1 · ran · 3a744d625048086e
  2. _make_divisible helper · level 1 · ran · honoured contract · 13f1c8e878ee2013
  3. h_sigmoid helper · level 1 · ran · 7e179a91bb50201f

harvested Assembly for Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP) (graph method: Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP)). 8 bricks; individually on a fixture: 8 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 15 siblings

  1. MobileNetV3 entry · level 1 · ran · 561f7b0eb338927a
  2. InvertedResidual model · level 1 · ran · 708f8102eea91f9e
  3. _make_divisible helper · level 1 · ran · honoured contract · 13f1c8e878ee2013
  4. conv_1x1_bn model · level 1 · ran · our draft was wrong · 4e90491a30c2dc28
  5. conv_3x3_bn model · level 1 · ran · our draft was wrong · 5221887077e3fb54
  6. h_swish helper · level 1 · ran · 5e356c9d5f8f95df
  7. SELayer model · level 1 · ran · 3a744d625048086e
  8. h_sigmoid helper · level 1 · ran · 7e179a91bb50201f

harvested Assembly for Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP) (graph method: Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP)). 5 bricks; individually on a fixture: 5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 15 siblings

  1. MobileNetV3 entry · level 1 · ran · dd0eb9bdaecad128
  2. BottleneckSE model · level 1 · ran · 9e476824ce6c9115
  3. SE model · level 1 · ran · 2d9873a3665e1dd9
  4. hswish helper · level 1 · ran · ecb1dac2f3a2944a
  5. h_sigmoid helper · level 1 · ran · our draft was wrong · 47cebc13301c1e23

harvested Assembly for Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP) (graph method: Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP)). 4 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 15 siblings

  1. atrous_block entry · level 0 · unverified · b82827563bc7975b
  2. activation helper · level 1 · ran; the contract check could not run (RAISES) · d04dc47c293a9646
  3. fusion_block helper · level 1 · ran; the contract check could not run (RAISES) · 927b92925cff89c3
  4. mish helper · level 1 · ran · honoured contract · 5426806a2db402eb

harvested Assembly for Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP) (graph method: Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP)). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 15 siblings

  1. MobileNetV3Small entry · level 1 · ran · 0c9f35bd6df82dc7

harvested Assembly for Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP) (graph method: Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP)). 9 bricks; individually on a fixture: 9 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 15 siblings

  1. MobileNetV3 entry · level 1 · ran · f54f64d3a22943e8
  2. Hswish helper · level 1 · ran · d276d941f05c6062
  3. MobileBottleneck model · level 1 · ran · 2d8a3aa3bbd7b78a
  4. conv_1x1_bn helper · level 1 · ran · our draft was wrong · db82a4013a44fb42
  5. conv_bn helper · level 1 · ran · our draft was wrong · 84a4cf301e929085
  6. make_divisible helper · level 1 · ran · honoured contract · 63ec083689f80f47
  7. Identity model · level 1 · ran · 9942e2eaf6ad275b
  8. SEModule model · level 1 · ran · be1d6e0d4c7fbed8
  9. Hsigmoid helper · level 1 · ran · 4a269a6484171c4e

harvested Assembly for Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP) (graph method: Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP)). 5 bricks; individually on a fixture: 4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 15 siblings

  1. EfficientHead entry · level 1 · ran · fae9673025e2a220
  2. Dropout helper · level 0 · unverified · bb95cb930e46eee0
  3. conv2d helper · level 1 · ran · our draft was wrong · 704704cc698dd1a4
  4. linear helper · level 1 · ran · our draft was wrong · 9f9ace2e0eb7c4fe
  5. to_tuple helper · level 1 · ran · violated contract · bc3a3914c7eee220

harvested Assembly for Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP) (graph method: Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP)). 9 bricks; individually on a fixture: 9 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 15 siblings

  1. MobileNetV3 entry · level 1 · ran · a0eb27e3a8ffc484
  2. Hswish helper · level 1 · ran · d276d941f05c6062
  3. MobileBottleneck model · level 1 · ran · 2d8a3aa3bbd7b78a
  4. SEModule helper · level 1 · ran · be1d6e0d4c7fbed8
  5. conv_1x1_bn helper · level 1 · ran · our draft was wrong · db82a4013a44fb42
  6. conv_bn helper · level 1 · ran · our draft was wrong · 84a4cf301e929085
  7. make_divisible helper · level 1 · ran · honoured contract · 63ec083689f80f47
  8. Identity helper · level 1 · ran · 9942e2eaf6ad275b
  9. Hsigmoid helper · level 1 · ran · 4a269a6484171c4e

harvested Assembly for Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP) (graph method: Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP)). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 15 siblings

  1. SeModule entry · level 1 · ran · 518da7f7fc849e72
  2. hsigmoid helper · level 1 · ran · ad3e66a9d6a27e29

harvested Assembly for Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP) (graph method: Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP)). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 15 siblings

  1. MobileNetV3 entry · level 1 · ran · ddd66ea3aa2a3a65
  1. MobileNetV3 · cd317eb01928f2af · 7 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
  2. MobileNetV3 · e3712526867bf300 · 9 bricks; individually on a fixture: 9 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
  3. MobileNetV3 · ea29d8eb9b2af33a · 12 bricks; individually on a fixture: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[14] in the JSON twin

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1905.02244") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

ClassificationDecoderDichotomous Image SegmentationImage ClassificationNeural Architecture SearchObject DetectionSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Classification InDL MobileNetV3 Average Recall 84.28% #9 of 9 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 MBV3 E-measure 0.818 #10 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 MBV3 HCE 274 #10 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 MBV3 MAE 0.083 #10 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 MBV3 S-Measure 0.740 #10 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 MBV3 max F-Measure 0.669 #10 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 MBV3 weighted F-measure 0.595 #10 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 MBV3 E-measure 0.856 #11 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 MBV3 HCE 600 #11 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 MBV3 MAE 0.083 #11 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 MBV3 S-Measure 0.777 #11 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 MBV3 max F-Measure 0.743 #11 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 MBV3 weighted F-measure 0.672 #11 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 MBV3 E-measure 0.880 #11 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 MBV3 HCE 1136 #11 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 MBV3 MAE 0.078 #11 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 MBV3 S-Measure 0.764 #11 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 MBV3 max F-Measure 0.772 #11 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 MBV3 weighted F-measure 0.702 #11 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 MBV3 E-measure 0.848 #13 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 MBV3 HCE 3817 #13 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 MBV3 MAE 0.098 #13 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 MBV3 S-Measure 0.770 #13 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 MBV3 max F-Measure 0.736 #13 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 MBV3 weighted F-measure 0.664 #13 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD MBV3 E-measure 0.841 #13 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD MBV3 HCE 1625 #13 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD MBV3 MAE 0.092 #13 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD MBV3 S-Measure 0.758 #13 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD MBV3 max F-Measure 0.714 #13 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD MBV3 weighted F-measure 0.642 #13 of 24 Archive leaderboard report
Image Classification ImageNet MobileNet V3-Large 1.0 GFLOPs 0.438 #956 of 1060 Archive leaderboard report
Image Classification ImageNet MobileNet V3-Large 1.0 Number of params 5.4M #956 of 1060 Archive leaderboard report
Image Classification ImageNet MobileNet V3-Large 1.0 Top 1 Accuracy 75.2% #956 of 1060 Archive leaderboard report
Semantic Segmentation Cityscapes test MobileNet V3-Large 1.0 Mean IoU (class) 72.6% #68 of 105 Archive leaderboard report
Semantic Segmentation DADA-seg MobileNetV3 (MobileNetV3small) mIoU 18.2 #25 of 28 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: Hard Swish

Dense ConnectionsDropoutGlobal Average PoolingHard SwishNetAdaptRMSPropRandom Horizontal FlipRandom Resized CropReLUReLU6Sigmoid ActivationSqueeze-and-Excitation BlockStep DecayWeight Decay

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections