Home › Code › conv_3x3_bn

conv_3x3_bn

Syntologyentry name in harvested coderead from the graph 2026-09-24

conv_3x3_bn appears in the code Syntology harvested for 21 papers, as 10 distinct code bodies found in 27 places (a place is one code body under one paper). At least one of them ran in 19 of the papers; 0 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named conv_3x3_bn do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 3 of the 10 distinct code bodies named conv_3x3_bn; 7 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
3ran · our draft was wrong
0ran · fixture could not drive it
0ran
7unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 5 of the 27 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

21 papers shown of 21, newest first; 27 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 2 papers added by Syntology; 5 papers have no page here and are shown by arXiv id only. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256, Syntology's identity for that exact code: an agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
Rethinking Dataset Distillation for Classification: Do Distilled Sets Outperform Coresets? added by Syntology 2026-06 (from id) lin-zhao-resoLve/D3HR/validation/models/mobilenet_v2.py 408e747e0425a594 ran · our draft was wrong no licence file found · pointer only
DeepRed: an architecture for redshift estimation added by Syntology 2026-02 (from id) identical code first harvested elsewhere c825b672e6f0b3bc ran · our draft was wrong licence of this copy not recorded
arXiv:2507.06482 2025-07 (from id) hwang52/FedDifRC/model/mobilenetv2.py 408e747e0425a594 ran · our draft was wrong Apache-2.0 (permissive)
arXiv:2507.06482 2025-07 (from id) hwang52/FedDifRC/model/mobilenetv3.py 5221887077e3fb54 ran · our draft was wrong Apache-2.0 (permissive)
Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch 21 Mar 2024 xidongwu/autotrainonce/imgnet_models/mobilenetv2_custom.py 408e747e0425a594 ran · our draft was wrong no licence file found · pointer only
SBCFormer: Lightweight Network Capable of Full-size ImageNet Classification at 1 FPS on Single Board Computers 7 Nov 2023 xyonglu/sbcformer/models/mobilenetv2.py 408e747e0425a594 ran · our draft was wrong MIT (permissive)
Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler 1 Jul 2023 osilly/kdfs/model/pruned_model/MobileNetV2_pruned.py 408e747e0425a594 ran · our draft was wrong MIT (permissive)
Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better Transferability 10 Mar 2022 CVMI-Lab/KDEP/src/mobilenet.py 408e747e0425a594 ran · our draft was wrong Apache-2.0 (permissive)
CoAtNet: Marrying Convolution and Attention for All Data Sizes 9 Jun 2021 chinhsuanwu/coatnet-pytorch/coatnet.py c825b672e6f0b3bc ran · our draft was wrong MIT (permissive)
EfficientNetV2: Smaller Models and Faster Training 1 Apr 2021 d-li14/efficientnetv2.pytorch/effnetv2.py 70ced89b3b23f051 unverified MIT (permissive)
Rethinking Bottleneck Structure for Efficient Mobile Network Design 5 Jul 2020 zhoudaquan/rethinking_bottleneck_design/mobile_deployment/pytorch/InvBlock/models/imagenet/i2rnet.py 408e747e0425a594 ran · our draft was wrong licence not identified · pointer only
Rethinking Bottleneck Structure for Efficient Mobile Network Design 5 Jul 2020 Andrew-Qibin/ssdlite-pytorch/ssd/modeling/backbone/mobilenext.py 141234d4962cebd2 unverified MIT (permissive)
Pixel-in-Pixel Net: Towards Efficient Facial Landmark Detection in the Wild 8 Mar 2020 jhb86253817/PIPNet/lib/mobilenetv3.py 5221887077e3fb54 ran · our draft was wrong MIT (permissive)
GhostNet: More Features from Cheap Operations 27 Nov 2019 ozora-ogino/efficient_backbones/efficient_backbones/efficientnet_v2.py 3d6f0eda22ace06f unverified MIT (permissive)
Neural Network Pruning with Residual-Connections and Limited-Data 19 Nov 2019 Roll920/CURL/ImageNet/CURL/1_evaluate_filter_importance/mobilenetv2.py 408e747e0425a594 ran · our draft was wrong MIT (permissive)
Searching for MobileNetV3 6 May 2019 wang-zidu/3ddfa-v3/model/mb_v3_networks.py 5221887077e3fb54 ran · our draft was wrong MIT (permissive)
Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression 16 Apr 2019 affromero/SMILE/metrics/mobilenetv2.py 408e747e0425a594 ran · our draft was wrong MIT (permissive)
MobileNetV2: Inverted Residuals and Linear Bottlenecks 13 Jan 2018 identical code first harvested elsewhere 408e747e0425a594 ran · our draft was wrong licence of this copy not recorded
SSD: Single Shot MultiBox Detector 8 Dec 2015 lufficc/SSD/ssd/modeling/backbone/mobilenetv3.py 5221887077e3fb54 ran · our draft was wrong MIT (permissive)
arXiv:aaai_6622 ouc-ocean-group/LDPS/lib/backbone/mobile_net.py 408e747e0425a594 ran · our draft was wrong MIT (permissive)
arXiv:Wang_3D_Face_Reconstruction_with_the_Geometric_Guidance_of_Facial_Part_CVPR_2024_paper wang-zidu/3DDFA-V3/model/mb_v3_networks.py 5221887077e3fb54 ran · our draft was wrong MIT (permissive)
arXiv:Cai_IIEU_Rethinking_Neural_Feature_Activation_from_Decision-Making_ICCV_2023_paper SudongCAI/IIEU/MODELS/raw_mobilenetv2_0dot17.py 408e747e0425a594 ran · our draft was wrong Apache-2.0 (permissive)
arXiv:Cai_IIEU_Rethinking_Neural_Feature_Activation_from_Decision-Making_ICCV_2023_paper SudongCAI/IIEU/MODELS/gelu_mobilenetv2_0dot17.py 133a176d7f8c0c67 unverified Apache-2.0 (permissive)
arXiv:Cai_IIEU_Rethinking_Neural_Feature_Activation_from_Decision-Making_ICCV_2023_paper SudongCAI/IIEU/MODELS/iieub_mobilenetv2_0dot17.py 734c2ccd66786225 unverified Apache-2.0 (permissive)
arXiv:Cai_IIEU_Rethinking_Neural_Feature_Activation_from_Decision-Making_ICCV_2023_paper SudongCAI/IIEU/MODELS/mish_mobilenetv2_0dot17.py f306d4a8b1a1b6af unverified Apache-2.0 (permissive)
arXiv:2023.acl-long.803 Shwai-He/PAD-Net/dyconv/model/mobilenetv2_dcd_pad.py 408e747e0425a594 ran · our draft was wrong MIT (permissive)
arXiv:2023.acl-long.803 Shwai-He/PAD-Net/dyconv/model/mobilenetv2_dyconv_pad.py b743f1920f93d232 unverified MIT (permissive)

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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 cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

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