Papers › MobileNetV2: Inverted Residuals and Linear Bottlenecks

MobileNetV2: Inverted Residuals and Linear Bottlenecks

13 Jan 2018CVPR 2018 6arXiv:1801.04381archive 2025-07-28

Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen

In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes. We also describe efficient ways of applying these mobile models to object detection in a novel framework we call SSDLite. Additionally, we demonstrate how to build mobile semantic segmentation models through a reduced form of DeepLabv3 which we call Mobile DeepLabv3. The MobileNetV2 architecture is based on an inverted residual structure where the input and output of the residual block are thin bottleneck layers opposite to traditional residual models which use expanded representations in the input an MobileNetV2 uses lightweight depthwise convolutions to filter features in the intermediate expansion layer. Additionally, we find that it is important to remove non-linearities in the narrow layers in order to maintain representational power. We demonstrate that this improves performance and provide an intuition that led to this design. Finally, our approach allows decoupling of the input/output domains from the expressiveness of the transformation, which provides a convenient framework for further analysis. We measure our performance on Imagenet classification, COCO object detection, VOC image segmentation. We evaluate the trade-offs between accuracy, and number of operations measured by multiply-adds (MAdd), as well as the number of parameters

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 111 code samples: 108 from 35 repositories linked to this paper, 3 identical to code harvested from another paper's repository. Across all 111: 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. Where Syntology's instrument failed: 17 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): 108 samples from 35 repositories, 82 ran (63 with no instrument failure; 19 where Syntology's instrument failed); 3 identical to code first harvested elsewhere. 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 31 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

tensorflow/models mentioned in papermentioned 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
0jason000/MobileNet_V2 mentioned on GitHubmindsporeSyntology: not harvested report
2manslkh/korean-food-classification-flask mentioned on GitHubtfSyntology: not harvested report
3P2S/arcface mentioned on GitHubtfSyntology: not harvested report
AD2605/Action-Recognition mentioned on GitHubpytorchSyntology: not harvested report
Amisha-here/Image-Classifier mentioned on GitHubtfSyntology: not harvested report
AndreiMoraru123/Hydra mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
Andrew-Qibin/ssdlite-pytorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Rethinking Bottleneck Structure for Efficient Mobile Network Design (arXiv:2007.02269; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
Arcady1/Doodle-Recognition-Web mentioned on GitHubtfSyntology: not harvested report
AutomatedAI/deeplab_inference mentioned on GitHubtfSyntology: not harvested report
AutomatedAI/deeplab_segmentation_example mentioned on GitHubtfSyntology: 4 samples, 3 ran (1 instrument-failed) · 1 unverified 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
EdwinAlegria/object_semantic_deeplabv3 mentioned on GitHubtfSyntology: not harvested report
Gideon0805/Tensorflow1.15-Model-Pruning mentioned on GitHubtfSyntology: 4 samples, 0 ran · 4 unverified report
Gideon0805/Tensorflow_Model_Pruning mentioned on GitHubtfSyntology: not harvested report
HaoJunNM/Unet-PretrainedMobilenetV2encoder-Flaskapp mentioned on GitHubtfSyntology: not harvested 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
JinyongJeong/DeeplabV3_Apolloscape_and_CityScape mentioned on GitHubtfSyntology: not harvested report
Marior87/Telegram_Bot mentioned on GitHubtfSyntology: not harvested report
Mayurji/Image-Classification-PyTorch mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (2 instrument-failed) · 0 unverified report
MioChiu/MobileNet_V2_TensorFlow mentioned on GitHubtfSyntology: 3 samples, 0 ran · 3 unverified report
MrD1360/Keras-implementation-of-MobileNetv3-with-L-RASSP mentioned on GitHubtfSyntology: not harvested report
MrRiahi/Convolutional-Neural-Networks-Tensorflow mentioned on GitHubtfSyntology: not harvested report
Nguyendat-bit/MobilenetV2 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
PolinaDruzhinina/mobilenet mentioned on GitHubpytorchSyntology: not harvested report
PolinaDruzhinina/modelnet mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
Robinatp/Deeplab_Tensorflow mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Rethinking Atrous Convolution for Semantic Image Segmentation (arXiv:1706.05587; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
Sakib1263/MobileNet-1D-2D-Tensorflow-Keras mentioned on GitHubtfSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified report
Syarujianai/deeplab-commented mentioned on GitHubtfSyntology: not harvested report
TTMRonald/MobileNet_Zoo mentioned on GitHubtfSyntology: not harvested report
TianyiZhang0315/CV_FinalProject mentioned on GitHubSyntology: not harvested report
Vignesh-95/cnn-semantic-segmentation-satellite-images mentioned on GitHubtfSyntology: not harvested report
Wordbe/MobileNetV2 mentioned on GitHubtfSyntology: not harvested report
XavierCHEN34/ClickSEG mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
Yimin-Yuan/VeinProject mentioned on GitHubtfSyntology: not harvested report
ZXdatascience/TextDetectorAndroid mentioned on GitHubSyntology: not harvested report
achen353/face-mask-detector mentioned on GitHubtfSyntology: not harvested report
akrapukhin/MobileNetV3 mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
amitgupta223/Real-Time-Face-Mask-Detection-using-OpenCV-on-MacOS mentioned on GitHubtfSyntology: not harvested report
anjandeepsahni/face_classification mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
anjandeepsahni/face_recognition mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
aryanasadianuoit/MobileNet_V2 mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
ayoolaolafenwa/orangelib mentioned on GitHubtfSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
bhumigodiwala/Face-Mask-Detection mentioned on GitHubtfSyntology: not harvested report
canturan10/satellighte mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
ceesem/refid2bib mentioned on GitHubSyntology: not harvested report
chandrikadeb7/face-mask-detection mentioned on GitHubtfSyntology: not harvested report
chris-boson/fashion_mnist mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Searching for MobileNetV3 (arXiv:1905.02244; that paper's own run record: 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); nothing checks that they implement this paper's method. report
clairehester/face-mask-detector mentioned on GitHubtfSyntology: not harvested report
cpn/ShuffledVideoSorter mentioned on GitHubSyntology: 1 sample, 0 ran · 1 unverified report
ctuning/ck-mlperf mentioned on GitHubtfSyntology: not harvested report
cyrilminaeff/MobileNet mentioned on GitHubpytorchSyntology: not harvested report
d-li14/mobilenetv2.pytorch mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
deep-learning-algorithm/LightWeightCNN mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
duan-song/SATNet mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
eddiebarry/SingleShotDetector mentioned on GitHubtfSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
espressif/esp-who mentioned on GitHubSyntology: not harvested report
etrommer/dcsr mentioned on GitHubtfSyntology: 2 samples, 0 ran · 2 unverified report
eunki7/flask-deeplearning-service-demo mentioned on GitHubtfSyntology: not harvested report
gittar/tensorflow_transfer mentioned on GitHubtfSyntology: not harvested report
heidongxianhau/deeplab2 mentioned on GitHubtfSyntology: not harvested report
hott-j/face-mask-detection mentioned on GitHubtfSyntology: not harvested report
ikigai-aa/Face-Mask-Detector-using-MobileNetV2 mentioned on GitHubtfSyntology: not harvested report
isakdiaz/PlantNet_MobileNetV2 mentioned on GitHubSyntology: not harvested report
jainabhishek/mnetv2 mentioned on GitHubpytorchSyntology: not harvested report
james77777778/keras-image-models mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to GhostNetV3: Exploring the Training Strategies for Compact Models (arXiv:2404.11202; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
jinbac/PlantNet mentioned on GitHubtfSyntology: not harvested report
jmjeon94/MobileNet-Pytorch mentioned on GitHubpytorchSyntology: 5 samples, 5 ran (3 instrument-failed) · 0 unverified report
jmysu/ESP32CAM-FaceDetect-Line-Notify mentioned on GitHubSyntology: not harvested report
kekeller/semantic_soy_deeplabv3plus mentioned on GitHubtfSyntology: not harvested report
kingcong/mobilenetv2 mentioned on GitHubmindsporeSyntology: not harvested report
kshitij1489/object-tracking mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Simple Online and Realtime Tracking with a Deep Association Metric (arXiv:1703.07402; that paper's own run record: 29 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 4 honoured, 3 violated, 17 with no contract checked; 5 where Syntology's instrument failed) · 11 unverified); nothing checks that they implement this paper's method. report
kwantommy/fgvc6-kaggle-cassava-classification mentioned on GitHubSyntology: not harvested report
liangfu/mxnet-mobilenet-v2 mentioned on GitHubmxnetSyntology: not harvested report
libiseller/MobileNetV2-dynamicFPN mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Feature Pyramid Networks for Object Detection (arXiv:1612.03144; that paper's own run record: 33 ran (of which 9 constructed an object rather than computing a result; 28 with no instrument failure: 4 honoured, 0 violated, 24 with no contract checked; 5 where Syntology's instrument failed) · 18 unverified); nothing checks that they implement this paper's method. report
lpirola13/flower-recognizer mentioned on GitHubtfSyntology: not harvested report
lpirola13/flower_recognizer mentioned on GitHubtfSyntology: not harvested report
malin9402/2020-0221 mentioned on GitHubtfSyntology: not harvested report
marload/ConvNets-TensorFlow2 mentioned on GitHubtfSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
mathildor/DeepLab-v3 mentioned on GitHubtfSyntology: not harvested report
meijieru/yet_another_mobilenet_series mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
mingxingtan/mnasnet mentioned on GitHubtfSyntology: not harvested report
modelhub-ai/mobilenet mentioned on GitHubmxnetSyntology: not harvested report
moelgendy/mobileNetV2 mentioned on GitHubtfSyntology: not harvested report
motlabs/dont-be-turtle mentioned on GitHubtfSyntology: not harvested report
mssung94/intel-image-classification mentioned on GitHubtfSyntology: not harvested report
neuleaf/MobileNetV2 mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
nolanliou/PeopleSegmentationDemo mentioned on GitHubtfSyntology: 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
pacharadanait/MobileNet_V2 mentioned on GitHubtfSyntology: not harvested report
parachutel/deeplabv3plus_on_Mapillary_Vistas mentioned on GitHubtfSyntology: not harvested report
peteryuX/arcface-tf2 mentioned on GitHubtfSyntology: 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); nothing checks that they implement this paper's method. report
raisinglc/object_detection_SSD mentioned on GitHubtfSyntology: 6 samples, 5 ran (5 instrument-failed) · 1 unverified report
richmondvan/melanoma-detection mentioned on GitHubApache-2.0Syntology: not harvested 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
rybread1/lego-minifigure-classification mentioned on GitHubtfSyntology: not harvested report
sagar-barapatre/Image-Classifier mentioned on GitHubtfSyntology: not harvested report
saunack/MobileNetv2-SSD mentioned on GitHubtfSyntology: not harvested report
setharram/facenet mentioned on GitHubtfMITSyntology: 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
sevakon/mobilenetv2 mentioned on GitHubtfSyntology: 4 samples, 1 ran (1 instrument-failed) · 3 unverified report
shicai/MobileNet-Caffe mentioned on GitHubcaffe2Syntology: not harvested report
stevensmiley1989/MrRobot mentioned on GitHubtfSyntology: not harvested report
sunnyahlawat1713/face-mask-detector-python mentioned on GitHubtfSyntology: not harvested report
tamnil/esp32-xtensa-study mentioned on GitHubSyntology: not harvested report
tantara/JejuNet mentioned on GitHubtfSyntology: not harvested 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
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/tpu mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It (arXiv:2403.14715; that paper's own run record: 9 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
titu1994/MobileNetworks mentioned on GitHubtfSyntology: not harvested report
tonylins/pytorch-mobilenet-v2 mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
trachpro/arcface-tf2 mentioned on GitHubtfSyntology: 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); nothing checks that they implement this paper's method. report
truskovskiyk/nima.pytorch mentioned on GitHubpytorchSyntology: not harvested report
w5688414/Keras-MobileNetV2-Image-classification mentioned on GitHubtfSyntology: not harvested report
wangvation/torch-mobilenet mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
xTRam1/Object-Detection-on-Custom-Dataset mentioned on GitHubtfSyntology: not harvested report
xiaochus/MobileNetV2 mentioned on GitHubtfSyntology: 5 samples, 1 ran (1 instrument-failed) · 4 unverified report
xxradon/IGCV3-pytorch mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
yakhyo/gaze-estimation mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
yakhyo/head-pose-estimation mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
yakhyo/retinaface-pytorch mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
yumaloop/mobilenetV2-cifar mentioned on GitHubtfSyntology: 2 samples, 0 ran · 2 unverified report
zjZSTU/LightWeightCNN mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design (arXiv:1807.11164; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 16 unverified); nothing checks that they implement this paper's method. report
zym1119/MobileNetV2_pytorch_cifar mentioned on GitHubpytorchSyntology: not harvested report
0jason000/MobilleNetV3 mindsporeSyntology: not harvested report
2023-MindSpore-1/ms-code-217 mindsporeSyntology: not harvested report
2023-MindSpore-1/ms-code-217 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code7 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code7 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
KaFaiFai/MobileNet-PyTorch pytorchSyntology: not harvested report
KaFaiFai/MobileNet-PyTorch-Converter pytorchSyntology: 6 samples, 6 ran (0 instrument-failed) · 0 unverified report
MS-Mind/MS-Code-02 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications (arXiv:2206.10589; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
Mind23-2/MindCode-101 mindsporeSyntology: not harvested report
Mind23-2/MindCode-168 mindsporeSyntology: not harvested report
Mind23-2/MindCode-3 mindsporeSyntology: not harvested report
MindSpore-paper-code-2/code3 mindsporeSyntology: not harvested report
MindSpore-paper-code-2/code400 mindsporeSyntology: not harvested 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
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
megvii-research/basecls Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ResMLP: Feedforward networks for image classification with data-efficient training (arXiv:2105.03404; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 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-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-courses/External-Attention-MindSpore mindsporeSyntology: not harvested report
mindspore-ecosystem/mindcv mindsporeSyntology: 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
pwc-1/Paper-5 mindsporeSyntology: not harvested report
pwc-1/Paper-5 mindsporeSyntology: not harvested report
pwc-1/Paper-9 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RandAugment: Practical automated data augmentation with a reduced search space (arXiv:1909.13719; that paper's own run record: 58 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 51 where Syntology's instrument failed) · 7 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/papers_with_examples mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Lite-HRNet: A Lightweight High-Resolution Network (arXiv:2104.06403; that paper's own run record: 13 ran (of which 2 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 16 unverified); nothing checks that they implement this paper's method. report
xiuyu0000/tutorials mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to YOLOv4: Optimal Speed and Accuracy of Object Detection (arXiv:2004.10934; that paper's own run record: 142 ran (of which 0 constructed an object rather than computing a result; 128 with no instrument failure: 8 honoured, 0 violated, 120 with no contract checked; 14 where Syntology's instrument failed) · 42 unverified); 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
yangyucheng000/mobilenet_v2 mindsporeSyntology: not harvested 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

111 samples harvested: 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. “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.

8ran · honoured contract
17ran · our draft was wrong
4ran; the contract check could not run
56ran
26unverified

Licence: 64 of the 111 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 35 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. 3 samples are listed last, in a group without a repository. “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 32 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.

AndreiMoraru123/Hydra community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
MobileNetv2 MultiTask/indoor/MobileNetV2.py ran fingerprinted no licence file found · pointer only · 86c3bd4815926a41 · report fixture: signature x:Tensor/4/float · returned list · level recorded 2026-09-24
InvertedResidualBlock MultiTask/indoor/MobileNetV2.py unverified no licence file found · pointer only · 696cf12ac039b708 · report
AutomatedAI/deeplab_segmentation_example community (archive-listed) 4 samples, 3 ran (1 instrument-failed) · 1 unverified
create_pascal_label_colormap prediction_support.py ran no licence file found · pointer only · 13739be826a37bbf · report fixture: returned ndarray · level recorded 2026-09-22
label_to_color_image_coco prediction_support.py ran · honoured contract no licence file found · pointer only · 11b6b2eb8b6db3b6 · report fixture: signature label:ndarray/2/int · returned ndarray · level recorded 2026-09-22
make_sending_seg prediction_support.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 6f13241c9a92bca4 · report fixture: signature image:ndarray/3/int, seg_map:ndarray/2/int · returned ndarray · level recorded 2026-09-22
DeepLabModel prediction_support.py unverified no licence file found · pointer only · e77d4f235bf2384f · report
Gideon0805/Tensorflow1.15-Model-Pruning community (archive-listed) 4 samples, 0 ran · 4 unverified
get_pretrained_model_saver src/train_pruning_class.py unverified no licence file found · pointer only · 20494df3c1676eeb · report
load_for_estimator src/train_pruning_class.py unverified no licence file found · pointer only · 245efa3670172970 · report
model_fn in 10 papers src/train_pruning_class.py unverified no licence file found · pointer only · 6ff0b95bc2b81704 · report
train_op src/train_pruning_class.py unverified no licence file found · pointer only · 8398b2d7c7e9b0cc · report
Mayurji/Image-Classification-PyTorch community (archive-listed) 4 samples, 4 ran (2 instrument-failed) · 0 unverified
InvertedResidual in 9 papers MobileNetV2.py ran · metamorphic tier: invariant GPL-3.0 (copyleft) · pointer only · 702a817f5219eb77 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
MobileNetV2 in 6 papers MobileNetV2.py ran · metamorphic tier: invariant fingerprinted GPL-3.0 (copyleft) · pointer only · 9807161a393336a6 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
conv1x1 in 691 papers MobileNetV2.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · b274b5edfa237985 · report fixture: signature input_channel:int/0/int, output_channel:int/0/int · returned Sequential · level recorded 2026-09-22
conv3x3 in 1,376 papers MobileNetV2.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 211377a478024586 · report fixture: signature input_channel:int/0/int, output_channel:int/0/int, stride:int/0/int · returned Sequential · level recorded 2026-09-22
MioChiu/MobileNet_V2_TensorFlow community (archive-listed) 3 samples, 0 ran · 3 unverified
MobileNetV2 in 6 papers mobilenet.py unverified no licence file found · pointer only · f44ae1a347d79be8 · report
_conv_bn_relu mobilenet.py unverified no licence file found · pointer only · 4c2ec1b763cc9e39 · report
_inverted_residual mobilenet.py unverified no licence file found · pointer only · 6acec70b7dbf9220 · report
PolinaDruzhinina/modelnet community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
Bottleneck in 98 papers models/mobilenetv2.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 723634d7ddcbd75d · report fixture: signature X:Tensor/4/float · returned Tensor · level recorded 2026-09-22
MobileNetV2 in 6 papers models/mobilenetv2.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 74273a5969bc5ad0 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Sakib1263/MobileNet-1D-2D-Tensorflow-Keras community (archive-listed) 3 samples, 3 ran (3 instrument-failed) · 0 unverified
Conv_2D_block Codes/MobileNet_2DCNN.py ran · our draft was wrong Apache-2.0 (permissive) · 2465629a9c52a4b8 · report fixture: signature inputs:KerasTensor/0/float, model_width:int/0/int, kernel:int/0/int, strides:int/0/int · returned KerasTensor · level recorded 2026-09-22
bottleneck_block in 6 papers Codes/MobileNet_2DCNN.py ran · our draft was wrong Apache-2.0 (permissive) · 0f2935bb581f1f41 · report fixture: signature inputs:EagerTensor/4/float, filters:int/0/int, kernel:int/0/int, t:int/0/int, alpha:float/0/float, strides:int/0/int, r:bool/0/bool · returned EagerTensor · level recorded 2026-09-22
inverted_residual_block Codes/MobileNet_2DCNN.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 2e9c7011f728364a · report fixture: signature inputs:EagerTensor/4/float, filters:int/0/int, kernel:int/0/int, t:int/0/int, alpha:float/0/float, strides:int/0/int, n:int/0/int · returned EagerTensor · level recorded 2026-09-22
XavierCHEN34/ClickSEG community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
InvertedResidual in 9 papers isegm/model/modeling/mobilenet/mobilenetv2_backbone.py ran fingerprinted Apache-2.0 (permissive) · e340453d472d8572 · report fixture: returned InvertedResidual · level recorded 2026-09-22
MobileNetV2 in 6 papers isegm/model/modeling/mobilenet/mobilenetv2_backbone.py ran Apache-2.0 (permissive) · 8e4927d20eeba27f · report fixture: returned MobileNetV2 · level recorded 2026-09-22
_ConvBNReLU isegm/model/modeling/mobilenet/mobilenetv2_backbone.py ran fingerprinted Apache-2.0 (permissive) · d71a716209b51dfa · report fixture: returned _ConvBNReLU · level recorded 2026-09-22
akrapukhin/MobileNetV3 community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
Bneck models.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · b2f94ecedfc82416 · report fixture: returned Bneck · level recorded 2026-09-22
Hsigmoid models.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 246daf568100d6f4 · report fixture: returned Hsigmoid · level recorded 2026-09-22
Squeeze_excite models.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 6bb39ebbf0be4cfe · report fixture: returned Squeeze_excite · level recorded 2026-09-22
anjandeepsahni/face_classification community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
MobileNetV2_v1 Code/model.py ran MIT (permissive) · 1b8a9f52faa25846 · report fixture: returned MobileNetV2_v1 · level recorded 2026-09-22
anjandeepsahni/face_recognition community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
InvResBottleneck Code/model.py ran MIT (permissive) · 2d877e5c6f9de34b · report fixture: returned InvResBottleneck · level recorded 2026-09-22
MobileNetV2_v3 Code/model.py ran MIT (permissive) · 8e22853464ac90cd · report fixture: returned MobileNetV2_v3 · level recorded 2026-09-22
aryanasadianuoit/MobileNet_V2 community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
Inverted_residual_Block MobileNet-V2.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · f2c6bd9bc1908c17 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
MobileNetV2 in 6 papers MobileNet-V2.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 8cdb6008f0706758 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
ayoolaolafenwa/orangelib community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
relu6 in 14 papers orangelib/orangelib/net.py ran · honoured contract fingerprinted MIT (permissive) · db5c06ceda32e963 · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22
LinearBottleNeck orangelib/orangelib/net.py unverified MIT (permissive) · e7fafffdc58ec03e · report
MobileNetV2 in 6 papers orangelib/orangelib/net.py unverified MIT (permissive) · 48b103807df090f7 · report
canturan10/satellighte community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
ConvBNReLU in 16 papers satellighte/archs/mobilenetv2/module.py ran fingerprinted MIT (permissive) · 030ac159ba75736b · report fixture: returned ConvBNReLU · level recorded 2026-09-22
ConvNormActivation in 5 papers satellighte/archs/mobilenetv2/module.py ran fingerprinted MIT (permissive) · 11eb981649d15e02 · report fixture: returned ConvNormActivation · level recorded 2026-09-22
InvertedResidual in 9 papers satellighte/archs/mobilenetv2/module.py ran MIT (permissive) · a0826c5a6426674e · report fixture: returned InvertedResidual · level recorded 2026-09-22
MobileNet_V2 satellighte/archs/mobilenetv2/module.py ran fingerprinted MIT (permissive) · a4a06f8548b59d91 · report fixture: returned MobileNet_V2 · level recorded 2026-09-22
MobileNetV2 in 6 papers satellighte/archs/mobilenetv2/module.py unverified MIT (permissive) · 20851557c2fcb3f6 · report
cpn/ShuffledVideoSorter community (archive-listed) 1 sample, 0 ran · 1 unverified
CNNModel models.py unverified no licence file found · pointer only · 4047a19386bf6261 · report
d-li14/mobilenetv2.pytorch community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
InvertedResidual in 9 papers models/imagenet/mobilenetv2.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 7c0486e261e94df5 · report fixture: returned InvertedResidual · level recorded 2026-09-22
MobileNetV2 in 6 papers models/imagenet/mobilenetv2.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 1a45a550e15122eb · report fixture: returned MobileNetV2 · level recorded 2026-09-22
deep-learning-algorithm/LightWeightCNN community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
ConvBNReLU in 16 papers py/lib/models/mobilenet_v2/mobilenet_v2.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 7bbf9113c42008a7 · report fixture: returned ConvBNReLU · level recorded 2026-09-22
InvertedResidual in 9 papers py/lib/models/mobilenet_v2/mobilenet_v2.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · f83fdb7a7809c0a5 · report fixture: returned InvertedResidual · level recorded 2026-09-22
MobileNetV2 in 6 papers py/lib/models/mobilenet_v2/mobilenet_v2.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · f9e3d193b25dc617 · report fixture: returned MobileNetV2 · level recorded 2026-09-22
_make_divisible in 9 papers py/lib/models/mobilenet_v2/mobilenet_v2.py ran · honoured contract Apache-2.0 (permissive) · 13f1c8e878ee2013 · report fixture: signature v:int/0/int, divisor:int/0/int, min_value:NoneType/0/? · returned int · level recorded 2026-09-22
duan-song/SATNet community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
ConvBNReLU in 16 papers models/MobileNetV2.py ran fingerprinted no licence file found · pointer only · e13e89a59e74d402 · report fixture: returned ConvBNReLU · level recorded 2026-09-22
InvertedResidual in 9 papers models/MobileNetV2.py ran fingerprinted no licence file found · pointer only · 9d6ee08207532162 · report fixture: returned InvertedResidual · level recorded 2026-09-22
MobileNetV2 in 6 papers models/MobileNetV2.py ran fingerprinted no licence file found · pointer only · f0b3bcd1c4db2a17 · report fixture: returned MobileNetV2 · level recorded 2026-09-22
eddiebarry/SingleShotDetector community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
correct_pad in 6 papers model_utils.py ran · honoured contract no licence file found · pointer only · ece60167804c303e · report fixture: signature inputs:KerasTensor/0/float, kernel_size:int/0/int · returned tuple · level recorded 2026-09-22
inverted_res_block model_utils.py ran · our draft was wrong no licence file found · pointer only · d36d6762cd40103c · report fixture: signature inputs:EagerTensor/4/float, expansion:int/0/int, stride:int/0/int, alpha:float/0/float, filters:int/0/int, block_id:int/0/int · returned EagerTensor · level recorded 2026-09-22
make_divisible in 76 papers model_utils.py ran · honoured contract fingerprinted no licence file found · pointer only · 5fe5fba885840647 · report fixture: signature v:int/0/int, divisor:int/0/int, min_value:int/0/int · returned int · level recorded 2026-09-22
etrommer/dcsr community (archive-listed) 2 samples, 0 ran · 2 unverified
insert_layer_nonseq src/dcsr/models/mnetv2.py unverified GPL-3.0 (copyleft) · pointer only · 837dbdd1de4118a9 · report
model in 13 papers src/dcsr/models/mnetv2.py unverified GPL-3.0 (copyleft) · pointer only · c15a1fe2a5eec419 · report
jmjeon94/MobileNet-Pytorch community (archive-listed) 5 samples, 5 ran (3 instrument-failed) · 0 unverified
InvertedBlock MobileNetV2.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 09fc5b7a5b351c09 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
MobileNetV2 in 6 papers MobileNetV2.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · ad0320cd5a636ddb · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
conv1x1 in 691 papers MobileNetV2.py ran · our draft was wrong no licence file found · pointer only · 2e6cb8019c3c8479 · report fixture: signature ch_in:int/0/int, ch_out:int/0/int · returned Sequential · level recorded 2026-09-22
conv3x3 in 1,376 papers MobileNetV2.py ran · our draft was wrong no licence file found · pointer only · 23f65ef554d738eb · report fixture: signature ch_in:int/0/int, ch_out:int/0/int, stride:int/0/int · returned Sequential · level recorded 2026-09-22
dwise_conv MobileNetV2.py ran · our draft was wrong no licence file found · pointer only · 123b3f3c0dba0ceb · report fixture: signature ch_in:int/0/int, stride:int/0/int · returned Sequential · level recorded 2026-09-22
marload/ConvNets-TensorFlow2 community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
LinearBottleNeck models/MobileNetV2.py ran Apache-2.0 (permissive) · 72b68826b24e7fee · report fixture: returned LinearBottleNeck · level recorded 2026-09-22
MobileNetV2 in 6 papers models/MobileNetV2.py ran Apache-2.0 (permissive) · 2f1e17c3f9375298 · report fixture: returned MobileNetV2 · level recorded 2026-09-22
ReLU6 models/MobileNetV2.py ran Apache-2.0 (permissive) · 0fc214ef5fd972cc · report fixture: returned Lambda · level recorded 2026-09-22
meijieru/yet_another_mobilenet_series community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
ConvBNReLU in 16 papers models/mobilenet_base.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · ac463ce4dee9e114 · report fixture: returned ConvBNReLU · level recorded 2026-09-22
InvertedResidualChannels models/mobilenet_base.py ran · metamorphic tier: deterministic licence not identified · pointer only · f63b39923e6eef80 · report fixture: returned InvertedResidualChannels · level recorded 2026-09-22
add_prefix in 20 papers models/mobilenet_base.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 9318cf2ca90a8c6a · report fixture: signature name:str/0/str, prefix:str/0/str, split:str/0/str · returned str · level recorded 2026-09-22
neuleaf/MobileNetV2 community (archive-listed) 1 sample, 0 ran · 1 unverified
mobilenetv2 in 7 papers mobilenet_v2.py unverified no licence file found · pointer only · 4fa072419436992a · report
raisinglc/object_detection_SSD community (archive-listed) 6 samples, 5 ran (5 instrument-failed) · 1 unverified
DPWConv2D_Layer_s1 ssd.py ran · our draft was wrong no licence file found · pointer only · 84ef9ca2fcc90014 · report fixture: signature input_x:EagerTensor/4/float, num_filters:int/0/int, multiplier:int/0/int, block_id:int/0/int · returned EagerTensor · level recorded 2026-09-22
DPWConv2D_Layer_s2 ssd.py ran · our draft was wrong fingerprinted no licence file found · pointer only · dedecb5be1feb068 · report fixture: signature input_x:EagerTensor/4/float, num_filters:int/0/int, multiplier:int/0/int, block_id:int/0/int · returned EagerTensor · level recorded 2026-09-22
DPWConv2D_layer_Conv2D ssd.py ran · our draft was wrong fingerprinted no licence file found · pointer only · f9748f7520aeded2 · report fixture: signature input_x:EagerTensor/4/float, num_filters:int/0/int, block_id:int/0/int · returned tuple · level recorded 2026-09-22
DPWConv2D_layer_Conv2D_nonpad ssd.py ran · our draft was wrong fingerprinted no licence file found · pointer only · c39ba7506e5c95e6 · report fixture: signature input_x:EagerTensor/4/float, num_filters:int/0/int, block_id:int/0/int · returned tuple · level recorded 2026-09-22
Prediction_Conv ssd.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · c9abc3cfafc4392a · report fixture: signature input_x:EagerTensor/4/float, NUM_ANCHOR:int/0/int, NUM_CLASSES:int/0/int, feature_shape:tuple/1/int · returned tuple · level recorded 2026-09-22
SSD ssd.py unverified no licence file found · pointer only · 54b61d2d0a5fd66d · report
sevakon/mobilenetv2 community (archive-listed) 4 samples, 1 ran (1 instrument-failed) · 3 unverified
_conv_block tensorflow/mobilenetv2.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 8bc80ab96e3155ac · report fixture: signature inputs:EagerTensor/4/float, filters:int/0/int, kernel:int/0/int, strides:int/0/int · returned EagerTensor · level recorded 2026-09-22
MobileNetV2 in 6 papers tensorflow/mobilenetv2.py unverified MIT (permissive) · 97e2e59ed341cea3 · report
_bottleneck tensorflow/mobilenetv2.py unverified MIT (permissive) · 725c084c03fc4aa8 · report
_inverted_residual_block tensorflow/mobilenetv2.py unverified MIT (permissive) · c1b1dd17c519b7e2 · report
tonylins/pytorch-mobilenet-v2 community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
InvertedResidual in 9 papers MobileNetV2.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · c274b979ea14e492 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
MobileNetV2 in 6 papers MobileNetV2.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · dffe5498c28d40f0 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
wangvation/torch-mobilenet community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
InvertedResblock module/mobilenet.py ran · metamorphic tier: invariant licence not identified · pointer only · 7cf1e2ebd46dd49b · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
MobileNetV2 in 6 papers module/mobilenet.py ran licence not identified · pointer only · 5eba228538a68b19 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
xiaochus/MobileNetV2 community (archive-listed) 5 samples, 1 ran (1 instrument-failed) · 4 unverified
_conv_block mobilenet_v2.py ran · our draft was wrong MIT (permissive) · c962118416fd7faf · report fixture: signature inputs:KerasTensor/0/float, filters:int/0/int, kernel:int/0/int, strides:int/0/int · returned KerasTensor · level recorded 2026-09-22
MobileNetv2 mobilenet_v2.py unverified MIT (permissive) · ea0a45b5db72ee3f · report
_bottleneck mobilenet_v2.py unverified MIT (permissive) · d1cb5eb77aac4fe6 · report
_inverted_residual_block mobilenet_v2.py unverified MIT (permissive) · 7973edb6af5ed41f · report
relu6 in 14 papers mobilenet_v2.py unverified MIT (permissive) · d51adc9e749c6f92 · report
xxradon/IGCV3-pytorch community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
InvertedResidual in 9 papers MobileNetV2.py ran fingerprinted no licence file found · pointer only · b2f8c6e9ac014cbf · report fixture: returned InvertedResidual · level recorded 2026-09-22
MobileNetV2 in 6 papers MobileNetV2.py ran no licence file found · pointer only · eb8e6ee65ca5e05b · report fixture: returned MobileNetV2 · level recorded 2026-09-22
conv_bn in 88 papers MobileNetV2.py ran · our draft was wrong no licence file found · pointer only · 0788d6ed8a5fec8b · report fixture: signature inp:int/0/int, oup:int/0/int, stride:int/0/int · returned Sequential · level recorded 2026-09-22
yakhyo/gaze-estimation community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
Conv2dNormActivation in 6 papers models/mobilenet.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · e8eaf387ed9bbae3 · report fixture: returned Conv2dNormActivation · level recorded 2026-09-22
InvertedResidual in 9 papers models/mobilenet.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · d31047e543134708 · report fixture: returned InvertedResidual · level recorded 2026-09-22
MobileNetV2 in 6 papers models/mobilenet.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · a9e9994d954bba16 · report fixture: returned MobileNetV2 · level recorded 2026-09-22
_make_divisible in 9 papers models/mobilenet.py ran · honoured contract MIT (permissive) · 13980381792aff88 · report fixture: signature v:float/0/float, divisor:int/0/int · returned int · level recorded 2026-09-22
yakhyo/head-pose-estimation community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
Conv2dNormActivation in 6 papers models/mobilenetv2.py ran fingerprinted MIT (permissive) · fbd137f6996c013e · report fixture: returned Conv2dNormActivation · level recorded 2026-09-22
InvertedResidual in 9 papers models/mobilenetv2.py ran fingerprinted MIT (permissive) · 5a66446bb107c9f0 · report fixture: returned InvertedResidual · level recorded 2026-09-22
MobileNetV2 in 6 papers models/mobilenetv2.py ran fingerprinted MIT (permissive) · de80b20f9d7db516 · report fixture: returned MobileNetV2 · level recorded 2026-09-22
yakhyo/retinaface-pytorch community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
Conv2dNormActivation in 6 papers models/backbones/mobilenetv2.py ran fingerprinted MIT (permissive) · 79e46d9ea751e031 · report fixture: returned Conv2dNormActivation · level recorded 2026-09-22
InvertedResidual in 9 papers models/backbones/mobilenetv2.py ran fingerprinted MIT (permissive) · 737503d3b1394539 · report fixture: returned InvertedResidual · level recorded 2026-09-22
MobileNetV2 in 6 papers models/backbones/mobilenetv2.py ran fingerprinted MIT (permissive) · 0a83961a1f4c2895 · report fixture: returned MobileNetV2 · level recorded 2026-09-22
yumaloop/mobilenetV2-cifar community (archive-listed) 2 samples, 0 ran · 2 unverified
MobileNetV2 in 6 papers models/mobilenet_v2.py unverified no licence file found · pointer only · a1c58af148b4567a · report
_inverted_res_block models/mobilenet_v2.py unverified no licence file found · pointer only · 526ff090ec554d78 · report
KaFaiFai/MobileNet-PyTorch-Converter community (archive-listed) 6 samples, 6 ran (0 instrument-failed) · 0 unverified
Bottleneck in 98 papers model/mobile_net_v2.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · da6b7b615ed04f09 · report fixture: returned Bottleneck · level recorded 2026-09-22
DepthWiseConv model/mobile_net_v2.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 93e2e1d515dfb960 · report fixture: returned DepthWiseConv · level recorded 2026-09-22
InvertedResidualConv model/mobile_net_v2.py ran fingerprinted no licence file found · pointer only · 52aa9eae5dfe66f7 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
MobileNetV2 in 6 papers model/mobile_net_v2.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 58a90005ecc73ce6 · report fixture: returned MobileNetV2 · level recorded 2026-09-22
PointWiseConv model/mobile_net_v2.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · d2a779e294b881d3 · report fixture: returned PointWiseConv · level recorded 2026-09-22
to_nearest_multiple_of model/mobile_net_v2.py ran · honoured contract fingerprinted no licence file found · pointer only · 15950935f515b902 · report fixture: signature num:int/0/int, multiple:int/0/int · returned int · level recorded 2026-09-22
Repository not located 3 samples, 3 ran (2 instrument-failed) · 0 unverified
3 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
conv_1x1_bn in 59 papers repository not located ran · our draft was wrong licence of this copy not recorded · 0db9f814cdec6488 · report fixture: signature inp:int/0/int, oup:int/0/int · returned Sequential · level recorded 2026-09-22
conv_3x3_bn in 21 papers repository not located ran · our draft was wrong licence of this copy not recorded · 408e747e0425a594 · report fixture: signature inp:int/0/int, oup:int/0/int, stride:int/0/int · returned Sequential · level recorded 2026-09-22
make_divisible in 76 papers repository not located ran · honoured contract fingerprinted licence of this copy not recorded · 9be8ab7ac48636e7 · report fixture: signature x:int/0/int, divisible_by:int/0/int · returned int · 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.

35 assemblies on this paper: 35 harvested, 0 generated, listed in 2 groups (siblings lifted in one batch form one group).

34 sibling assemblies for MobileNetV2 (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 34 sibling assemblies; the other 22 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for MobileNetV2 (graph method: MobileNetV2). 4 bricks; individually on a fixture: 4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 34 siblings

  1. MobileNetV2 entry · level 1 · ran · a9e9994d954bba16
  2. Conv2dNormActivation model · level 1 · ran · e8eaf387ed9bbae3
  3. InvertedResidual model · level 1 · ran · d31047e543134708
  4. _make_divisible helper · level 1 · ran · honoured contract · 13980381792aff88

harvested Assembly for MobileNetV2 (graph method: MobileNetV2). 6 bricks; individually on a fixture: 6 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; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 34 siblings

  1. MobileNetV2 entry · level 1 · ran · 58a90005ecc73ce6
  2. Bottleneck model · level 1 · ran · da6b7b615ed04f09
  3. PointWiseConv helper · level 1 · ran · d2a779e294b881d3
  4. to_nearest_multiple_of helper · level 1 · ran · honoured contract · 15950935f515b902
  5. InvertedResidualConv model · level 1 · ran · 52aa9eae5dfe66f7
  6. DepthWiseConv helper · level 1 · ran · 93e2e1d515dfb960

harvested Assembly for MobileNetV2 (graph method: MobileNetV2). 3 bricks; individually on a fixture: 3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 34 siblings

  1. MobileNetV2 entry · level 1 · ran · 2f1e17c3f9375298
  2. LinearBottleNeck model · level 1 · ran · 72b68826b24e7fee
  3. ReLU6 helper · level 1 · ran · 0fc214ef5fd972cc

harvested Assembly for MobileNetV2 (graph method: MobileNetV2). 4 bricks; individually on a fixture: 0 ran · 4 unverified. The assembly has not been run end-to-end.

one of 34 siblings

  1. model_fn entry · level 0 · unverified · 6ff0b95bc2b81704
  2. get_pretrained_model_saver helper · level 0 · unverified · 20494df3c1676eeb
  3. load_for_estimator helper · level 0 · unverified · 245efa3670172970
  4. train_op helper · level 0 · unverified · 8398b2d7c7e9b0cc

harvested Assembly for MobileNetV2 (graph method: MobileNetV2). 4 bricks; individually on a fixture: 4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 34 siblings

  1. MobileNetV2 entry · level 1 · ran · f9e3d193b25dc617
  2. ConvBNReLU model · level 1 · ran · 7bbf9113c42008a7
  3. InvertedResidual model · level 1 · ran · f83fdb7a7809c0a5
  4. _make_divisible helper · level 1 · ran · honoured contract · 13f1c8e878ee2013

harvested Assembly for MobileNetV2 (graph method: MobileNetV2). 3 bricks; individually on a fixture: 3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 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 34 siblings

  1. InvertedResidualChannels entry · level 1 · ran · f63b39923e6eef80
  2. ConvBNReLU model · level 1 · ran · ac463ce4dee9e114
  3. add_prefix helper · level 1 · ran · our draft was wrong · 9318cf2ca90a8c6a

harvested Assembly for MobileNetV2 (graph method: MobileNetV2). 6 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 34 siblings

  1. SSD entry · level 0 · unverified · 54b61d2d0a5fd66d
  2. DPWConv2D_Layer_s1 model · level 1 · ran · our draft was wrong · 84ef9ca2fcc90014
  3. DPWConv2D_Layer_s2 model · level 1 · ran · our draft was wrong · dedecb5be1feb068
  4. DPWConv2D_layer_Conv2D model · level 1 · ran · our draft was wrong · f9748f7520aeded2
  5. DPWConv2D_layer_Conv2D_nonpad model · level 1 · ran · our draft was wrong · c39ba7506e5c95e6
  6. Prediction_Conv model · level 1 · ran; the contract check could not run (RAISES) · c9abc3cfafc4392a

harvested Assembly for MobileNetV2 (graph method: MobileNetV2). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 34 siblings

  1. mobilenetv2 entry · level 0 · unverified · 4fa072419436992a

harvested Assembly for MobileNetV2 (graph method: MobileNetV2). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 34 siblings

  1. CNNModel entry · level 0 · unverified · 4047a19386bf6261

harvested Assembly for MobileNetV2 (graph method: MobileNetV2). 5 bricks; individually on a fixture: 5 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; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 34 siblings

  1. MobileNetV2 entry · level 1 · ran · 1a45a550e15122eb
  2. InvertedResidual model · level 1 · ran · 7c0486e261e94df5
  3. _make_divisible helper · level 1 · ran · honoured contract · 13f1c8e878ee2013
  4. conv_1x1_bn helper · level 1 · ran · our draft was wrong · a0131fb70c267a9e
  5. conv_3x3_bn helper · level 1 · ran · our draft was wrong · 408e747e0425a594

harvested Assembly for MobileNetV2 (graph method: MobileNetV2). 3 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 34 siblings

  1. Bneck entry · level 1 · ran · b2f94ecedfc82416
  2. Squeeze_excite helper · level 1 · ran · 6bb39ebbf0be4cfe
  3. Hsigmoid helper · level 1 · ran · 246daf568100d6f4

harvested Assembly for MobileNetV2 (graph method: MobileNetV2). 4 bricks; individually on a fixture: 4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 34 siblings

  1. MobileNetV2 entry · level 1 · ran · eb8e6ee65ca5e05b
  2. InvertedResidual model · level 1 · ran · b2f8c6e9ac014cbf
  3. conv_1x1_bn helper · level 1 · ran · our draft was wrong · 0db9f814cdec6488
  4. conv_bn helper · level 1 · ran · our draft was wrong · 0788d6ed8a5fec8b
  1. MobileNetV2_v3 · 72d06ac2a2ed65b1 · 2 bricks; individually on a fixture: 2 ran (of which 2 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; every one of the 2 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
  2. MobileNetV2 · 80f371c3d075da36 · 7 bricks; individually on a fixture: 7 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
  3. model · 862d9b3f3561b2e2 · 2 bricks; individually on a fixture: 0 ran · 2 unverified · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
  4. MobileNetV2 · 94cd9885fad488ce · 3 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[15] in the JSON twin
  5. MobileNetV2 · 95d323e0f09a6e96 · 4 bricks; individually on a fixture: 4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[16] in the JSON twin
  6. MobileNetV2 · a1b8ab2def3faa1e · 3 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[17] in the JSON twin
  7. inverted_residual_block · a42a08a5a0fb1a1a · 3 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[18] in the JSON twin
  8. MobileNetv2 · a61df7456a5567b8 · 6 bricks; individually on a fixture: 2 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; 1 where Syntology's instrument failed) · 4 unverified · The assembly has not been run end-to-end · assemblies[19] in the JSON twin
  9. MobileNetV2 · a82c424c6741dad9 · 6 bricks; individually on a fixture: 5 ran (of which 4 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) · 1 unverified · The assembly has not been run end-to-end · assemblies[20] in the JSON twin
  10. MobileNetV2_v1 · b36136f020f28e33 · 2 bricks; individually on a fixture: 2 ran (of which 2 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; every one of the 2 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[21] in the JSON twin
  11. MobileNetV2 · bb1da8b44466e450 · 4 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified · The assembly has not been run end-to-end · assemblies[22] in the JSON twin
  12. MobileNetV2 · c1a8d70f6c282d00 · 4 bricks; individually on a fixture: 1 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; 0 where Syntology's instrument failed) · 3 unverified · The assembly has not been run end-to-end · assemblies[23] in the JSON twin
  13. MobileNetV2 · c7af1e6307b424bd · 2 bricks; individually on a fixture: 2 ran (of which 0 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 · assemblies[25] in the JSON twin
  14. inverted_res_block · ce976d12bf38d86e · 3 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[26] in the JSON twin
  15. MobileNetV2 · db67726c45a8331e · 5 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[27] in the JSON twin
  16. MobileNetV2 · de601a33ec52a0ed · 2 bricks; individually on a fixture: 2 ran (of which 0 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 · assemblies[28] in the JSON twin
  17. MobileNetV2 · eba6ac680b731d87 · 3 bricks; individually on a fixture: 3 ran (of which 0 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 · assemblies[29] in the JSON twin
  18. MobileNetV2 · ee774e1b4a2fb640 · 5 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[30] in the JSON twin
  19. MobileNetV2 · ee98d92430bd436f · 3 bricks; individually on a fixture: 1 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; 0 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[31] in the JSON twin
  20. MobileNetV2 · f4b6713feb27844e · 5 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[32] in the JSON twin
  21. MobileNetv2 · f5be818e286ba434 · 2 bricks; 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) · 1 unverified · The assembly has not been run end-to-end · assemblies[33] in the JSON twin
  22. MobileNetV2 · f86f68922cc9feea · 3 bricks; individually on a fixture: 1 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; 0 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[34] in the JSON twin

harvested Assembly for Mobile DeepLabv3 (graph method: Mobile DeepLabv3). 4 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

  1. DeepLabModel entry · level 0 · unverified · e77d4f235bf2384f
  2. make_sending_seg helper · level 1 · ran; the contract check could not run (RAISES) · 6f13241c9a92bca4
  3. label_to_color_image_coco helper · level 1 · ran · honoured contract · 11b6b2eb8b6db3b6
  4. create_pascal_label_colormap helper · level 1 · ran · 13739be826a37bbf

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="1801.04381") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image ClassificationImage SegmentationObject DetectionPerson Re-IdentificationRetinal OCT Disease ClassificationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification CIFAR-10 Mobile Net_Sam Percentage correct 95.50 #133 of 265 Archive leaderboard report
Image Classification ImageNet MobileNetV2 (1.4) GFLOPs 1.170 #972 of 1060 Archive leaderboard report
Image Classification ImageNet MobileNetV2 (1.4) Number of params 6.9M #972 of 1060 Archive leaderboard report
Image Classification ImageNet MobileNetV2 (1.4) Top 1 Accuracy 74.7% #972 of 1060 Archive leaderboard report
Image Classification ImageNet MobileNetV2 GFLOPs 0.600 #1002 of 1060 Archive leaderboard report
Image Classification ImageNet MobileNetV2 Number of params 3.4M #1002 of 1060 Archive leaderboard report
Image Classification ImageNet MobileNetV2 Top 1 Accuracy 72% #1002 of 1060 Archive leaderboard report
Retinal OCT Disease Classification OCT2017 MobileNet-v2 Acc 98.5 #8 of 16 Archive leaderboard report
Retinal OCT Disease Classification OCT2017 MobileNet-v2 Sensitivity 99.4 #8 of 16 Archive leaderboard report
Retinal OCT Disease Classification Srinivasan2014 MobileNet-v2 Acc 97.46 #7 of 14 Archive leaderboard report
Semantic Segmentation DADA-seg MobileNetV2 mIoU 16.05 #27 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

1x1 ConvolutionASPPAverage PoolingBatch NormalizationConvolutionDeepLabv3Depthwise ConvolutionDepthwise Separable ConvolutionDilated ConvolutionDropoutInverted Residual BlockPointwise ConvolutionRMSPropReLUReLU6Residual BlockResidual ConnectionSpatial Pyramid PoolingWeight 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