Papers › Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

11 Feb 2015arXiv:1502.03167archive 2025-07-28

Sergey Ioffe, Christian Szegedy

Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates and careful parameter initialization, and makes it notoriously hard to train models with saturating nonlinearities. We refer to this phenomenon as internal covariate shift, and address the problem by normalizing layer inputs. Our method draws its strength from making normalization a part of the model architecture and performing the normalization for each training mini-batch. Batch Normalization allows us to use much higher learning rates and be less careful about initialization. It also acts as a regularizer, in some cases eliminating the need for Dropout. Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin. Using an ensemble of batch-normalized networks, we improve upon the best published result on ImageNet classification: reaching 4.9% top-5 validation error (and 4.8% test error), exceeding the accuracy of human raters.

PaperPDFCodeCode 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 21 code samples harvested from 15 repositories linked to this paper: 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. Where Syntology's instrument failed: 4 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 21 samples from 15 repositories, 19 ran (14 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 11 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

Bersaelor/AAPLMetalImageRecognition mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
CPJKU/cca_layer mentioned on GitHubtfSyntology: not harvested report
ChuuyaZZZ/6787-Final-project mentioned on GitHubtfSyntology: not harvested report
GeekLiB/caffe-model mentioned on GitHubcaffe2Syntology: not harvested report
George091/CNN mentioned on GitHubSyntology: not harvested report
Gowti-AiboT/GAN-based-SISR-Keras mentioned on GitHubtfSyntology: not harvested report
LMaxence/Cifar10_Classification mentioned on GitHubpytorchnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
Liuyubao/transfer-learning mentioned on GitHubtfSyntology: not harvested report
LouisFoucard/StereoConvNet mentioned on GitHubSyntology: not harvested report
MrRiahi/Convolutional-Neural-Networks-Tensorflow mentioned on GitHubtfSyntology: not harvested report
Sakib1263/1DResNet-Builder-KERAS mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Aggregated Residual Transformations for Deep Neural Networks (arXiv:1611.05431; that paper's own run record: 51 ran (of which 7 constructed an object rather than computing a result; 31 with no instrument failure: 0 honoured, 0 violated, 31 with no contract checked; 20 where Syntology's instrument failed) · 29 unverified); nothing checks that they implement this paper's method. report
Sakib1263/1DResNet-KERAS mentioned on GitHubtfMITSyntology: not harvested report
Sakib1263/Inception-InceptionResNet-1D-2D-Tensorflow-Keras mentioned on GitHubtfSyntology: 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); nothing checks that they implement this paper's method. report
Sakib1263/Inception-Model-Builder-Tensorflow-Keras mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
Sakib1263/ResNet-Model-Builder-KERAS mentioned on GitHubtfMITSyntology: not harvested report
Sakib1263/ResNet-Model-Builder-Tensorflow-Keras mentioned on GitHubtfMITSyntology: not harvested report
Sakib1263/ResNet-ResNeXt-1D-2D-Tensorflow-Keras mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
Sakib1263/ResNet-ResNetv2-ResNeXt-1D-2D-Tensorflow-Keras mentioned on GitHubtfMITSyntology: not harvested report
Sakib1263/ResNet1D-Model-Builder-KERAS 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) and Aggregated Residual Transformations for Deep Neural Networks (arXiv:1611.05431; that paper's own run record: 51 ran (of which 7 constructed an object rather than computing a result; 31 with no instrument failure: 0 honoured, 0 violated, 31 with no contract checked; 20 where Syntology's instrument failed) · 29 unverified); nothing checks that they implement this paper's method. report
Sakib1263/VGG-1D-2D-Tensorflow-Keras mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
Sakib1263/VGG-Model-Builder-KERAS mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
Sakib1263/VGG-Model-Builder-Tensorflow-Keras mentioned on GitHubtfMITSyntology: not harvested report
Shantanu48114860/Handwritten-Character-Recognition mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
ThanasisMattas/smartflow 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
UrosOgrizovic/SimpleGoogleQuickdraw mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep... (arXiv:1602.07868; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
Xinyi6/CIFAR10-CNN-by-Keras mentioned on GitHubpytorchSyntology: not harvested report
altaga/Pytorch-Driving-Guardian mentioned on GitHubpytorchMITSyntology: not harvested report
amazon-research/long-short-term-transformer mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Long Short-Term Transformer for Online Action Detection (arXiv:2107.03377; that paper's own run record: 6 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; 0 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
amazon-science/long-short-term-transformer mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Long Short-Term Transformer for Online Action Detection (arXiv:2107.03377; that paper's own run record: 6 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; 0 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
ansrlm/ML_DCGAN mentioned on GitHubtfSyntology: not harvested report
apllolulu/StereoConvNet mentioned on GitHubSyntology: not harvested report
che9992/Batch_Normalization mentioned on GitHubtfMITSyntology: not harvested report
cyh1112/GraphNormalization mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Layer Normalization (arXiv:1607.06450; that paper's own run record: 7 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
dichotomies/proxy-nca mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
dodoproptit99/deep-speaker mentioned on GitHubSyntology: not harvested report
ducanhnguyen/batchnormalization mentioned on GitHubtfSyntology: not harvested report
fescobar96/Image-Noise-Removal mentioned on GitHubSyntology: not harvested report
gmouzella/Efective_TensorFlow mentioned on GitHubtfSyntology: not harvested report
harshit0511/Deep-Learning mentioned on GitHubtfSyntology: not harvested report
hoanghuy89/CNN-from-first-principle mentioned on GitHubpytorchSyntology: not harvested report
huybik/CNN-from-first-principle mentioned on GitHubpytorchSyntology: not harvested report
ibabbar/Traffic-Sign-Classifier mentioned on GitHubtfMITSyntology: not harvested report
karurb92/ldam_str_bn mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
koolhussain/Self-Driving-Car mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to End to End Learning for Self-Driving Cars (arXiv:1604.07316; that paper's own run record: 30 ran (of which 0 constructed an object rather than computing a result; 23 with no instrument failure: 0 honoured, 2 violated, 21 with no contract checked; 7 where Syntology's instrument failed) · 11 unverified); nothing checks that they implement this paper's method. report
lim0606/caffe-googlenet-bn mentioned on GitHubSyntology: not harvested report
marsala97/Reproducibility-Project-Deep-Learning mentioned on GitHubSyntology: not harvested report
minoring/batch-norm-visualize mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified 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
sameervk/BatchNorm_Mechanics mentioned on GitHubtfGPL-3.0Syntology: not harvested report
sayakpaul/Adaptive-Gradient-Clipping mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
shinpoi/pixiv_collector_old mentioned on GitHubGPL-3.0Syntology: not harvested report
simo-bat/Crack_detection mentioned on GitHubtfSyntology: not harvested report
simo23/tinyYOLOv2 mentioned on GitHubtfSyntology: not harvested report
sudhirk999/ResearchPapersLinks mentioned on GitHubSyntology: not harvested report
tanjeffreyz/batch-normalization mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
tanjeffreyz/deep-residual-learning 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); nothing checks that they implement this paper's method. report
tensorflow/models mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
tensorflow/models mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
tensorflow/models mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
tensorflow/models mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
tensorflow/models mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
utsawk/CarND-Traffic-Sign-Classifier-Project mentioned on GitHubMITSyntology: not harvested report
yzheng51/rl-dino-run mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
zjZSTU/GoogLeNet mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
Mind23-2/MindCode-3 mindsporeSyntology: not harvested report
labmlai/annotated_deep_learning_paper_implementations pytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
yangyucheng000/ssd_inception_v2 mindsporeApache-2.0Syntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified 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

21 samples harvested: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · our draft was wrong
1ran; the contract check could not run
14ran
2unverified

Licence: 5 of the 21 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 15 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample 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.

Sakib1263/Inception-Model-Builder-Tensorflow-Keras community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
Conv_1D_Block Codes/Inception_ResNet_1DCNN.py ran · our draft was wrong MIT (permissive) · 977f839ae1b772a6 · report fixture: signature x:KerasTensor/0/float, model_width:int/0/int, kernel:int/0/int, strides:int/0/int, padding:str/0/str · returned KerasTensor · level recorded 2026-09-22
Sakib1263/ResNet-ResNeXt-1D-2D-Tensorflow-Keras community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
Conv_1D_Block Codes/ResNet_1DCNN.py ran · our draft was wrong MIT (permissive) · fa041da57fc2fe89 · report fixture: signature x:KerasTensor/3/float, model_width:int/0/int, kernel:int/0/int, strides:int/0/int · returned KerasTensor · level recorded 2026-09-22
Sakib1263/VGG-1D-2D-Tensorflow-Keras community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
Conv_1D_Block Codes/VGG_1DCNN.py ran · our draft was wrong MIT (permissive) · 4f854d75a8d26231 · report fixture: signature x:KerasTensor/0/float, model_width:int/0/int, kernel:int/0/int · returned KerasTensor · level recorded 2026-09-22
Sakib1263/VGG-Model-Builder-KERAS community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
Conv_2D_Block in 5 papers Codes/VGG_2DCNN.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 12a688d4588443d2 · report fixture: signature inputs:EagerTensor/4/float, model_width:int/0/int, kernel:int/0/int · returned EagerTensor · level recorded 2026-09-22
Shantanu48114860/Handwritten-Character-Recognition community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Network in 40 papers Handwritten-Character-Recognition/CNN.py ran no licence file found · pointer only · 2ba90697099f8cca · report fixture: returned Network · level recorded 2026-09-22
dichotomies/proxy-nca community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
BNInception net/bn_inception.py ran · metamorphic tier: deterministic MIT (permissive) · dcefb760e5798c17 · report fixture: returned BNInception · level recorded 2026-09-22
karurb92/ldam_str_bn community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
res_net_block models/resnet.py ran · our draft was wrong no licence file found · pointer only · a542810366586242 · report fixture: signature input_data:KerasTensor/0/float, filters:int/0/int, conv_size:int/0/int · returned KerasTensor · level recorded 2026-09-22
minoring/batch-norm-visualize community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
mnist_model_bn model.py ran no licence file found · pointer only · 17bcce71dd6805e5 · report fixture: returned Functional · level recorded 2026-09-22
sayakpaul/Adaptive-Gradient-Clipping community (archive-listed) 1 sample, 0 ran · 1 unverified
conv_block_bn models.py unverified MIT (permissive) · b68ffa76fbfa3320 · report
tanjeffreyz/batch-normalization community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
BatchNorm in 19 papers models.py ran fingerprinted no licence file found · pointer only · fd8f4df6039d46b0 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
tensorflow/models community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
FreezableBatchNorm research/object_detection/core/freezable_batch_norm.py ran licence not identified · pointer only · d6503cf479ae48ea · report fixture: returned FreezableBatchNorm · level recorded 2026-09-22
yzheng51/rl-dino-run community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
ConvNet in 13 papers model.py ran · metamorphic tier: invariant MIT (permissive) · 275928042f41cfff · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
zjZSTU/GoogLeNet community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
BasicConv2d in 12 papers py/models/googlenet_bn.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · 363095e135affba2 · report fixture: returned Tensor · level recorded 2026-09-22
labmlai/annotated_deep_learning_paper_implementations community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
BatchNorm in 19 papers labml_nn/normalization/batch_norm/mnist.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 629771a2e32edf83 · report fixture: returned BatchNorm · level recorded 2026-09-22
Model in 227 papers labml_nn/normalization/batch_norm/mnist.py ran · metamorphic tier: deterministic MIT (permissive) · 84ac6eb3495fd518 · report fixture: returned Model · level recorded 2026-09-22
yangyucheng000/ssd_inception_v2 community (archive-listed) 6 samples, 5 ran (0 instrument-failed) · 1 unverified
apply_nms src/eval_utils.py ran Apache-2.0 (permissive) · 9a71632baa853b8a · report fixture: signature all_boxes:ndarray/2/float, all_scores:ndarray/1/float, thres:float/0/float, max_boxes:int/0/int · returned list · level recorded 2026-09-26
get_depth_fn src/feature_map_generators.py ran Apache-2.0 (permissive) · 0946825bd8511f99 · report fixture: signature depth_multipler:float/0/float, min_depth:int/0/int · returned function · level recorded 2026-09-26
get_imageId_from_fileName src/dataset.py ran fingerprinted Apache-2.0 (permissive) · 80eae5f06649b1e2 · report fixture: signature filename:str/0/str, id_iter:int/0/int · returned int · level recorded 2026-09-26
get_lr in 91 papers src/lr_schedule.py ran Apache-2.0 (permissive) · 1bab04258df1af4e · report fixture: signature global_step:int/0/int, lr_init:float/0/float, lr_end:float/0/float, lr_max:float/0/float, warmup_epochs:int/0/int, total_epochs:int/0/int, steps_per_epoch:int/0/int · returned ndarray · level recorded 2026-09-26
intersect in 33 papers src/box_utils.py ran fingerprinted Apache-2.0 (permissive) · f4aebce5f37270c3 · report fixture: signature box_a:ndarray/2/float, box_b:ndarray/1/float · returned ndarray · level recorded 2026-09-26
random_sample_crop src/dataset.py unverified Apache-2.0 (permissive) · f50e9b77fc01e9c8 · report

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.

16 assemblies on this paper: 16 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

16 sibling assemblies for Batch Normalization (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 16 sibling assemblies; the other 4 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for Batch Normalization (graph method: Batch Normalization). 1 brick; 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) · 0 unverified. The assembly has not been run end-to-end.

one of 16 siblings

  1. Conv_1D_Block entry · level 1 · ran · our draft was wrong · 977f839ae1b772a6

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

one of 16 siblings

  1. FreezableBatchNorm entry · level 1 · ran · d6503cf479ae48ea

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

one of 16 siblings

  1. BNInception entry · level 1 · ran · dcefb760e5798c17

harvested Assembly for Batch Normalization (graph method: Batch Normalization). 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.

one of 16 siblings

  1. Model entry · level 1 · ran · 84ac6eb3495fd518
  2. BatchNorm helper · level 1 · ran · 629771a2e32edf83

harvested Assembly for Batch Normalization (graph method: Batch Normalization). 1 brick; 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) · 0 unverified. The assembly has not been run end-to-end.

one of 16 siblings

  1. Conv_2D_Block entry · level 1 · ran · our draft was wrong · b6f21090a082496d

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

one of 16 siblings

  1. Network entry · level 1 · ran · 2ba90697099f8cca

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

one of 16 siblings

  1. BatchNorm entry · level 1 · ran · fd8f4df6039d46b0

harvested Assembly for Batch Normalization (graph method: Batch Normalization). 1 brick; 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) · 0 unverified. The assembly has not been run end-to-end.

one of 16 siblings

  1. Conv_1D_Block entry · level 1 · ran · our draft was wrong · fa041da57fc2fe89

harvested Assembly for Batch Normalization (graph method: Batch Normalization). 1 brick; 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) · 0 unverified. The assembly has not been run end-to-end.

one of 16 siblings

  1. Conv_1D_Block entry · level 1 · ran · our draft was wrong · 4f854d75a8d26231

harvested Assembly for Batch Normalization (graph method: Batch Normalization). 2 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) · 1 unverified. The assembly has not been run end-to-end.

one of 16 siblings

  1. conv2d_bn entry · level 0 · unverified · c125a80b2014c456
  2. residual_layer helper · level 1 · ran; the contract check could not run · a7e2bd8326ffef0f

harvested Assembly for Batch Normalization (graph method: Batch Normalization). 1 brick; 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) · 0 unverified. The assembly has not been run end-to-end.

one of 16 siblings

  1. res_net_block entry · level 1 · ran · our draft was wrong · a542810366586242

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

one of 16 siblings

  1. conv_block_bn entry · level 0 · unverified · b68ffa76fbfa3320
  1. BasicConv2d · e37b5d06143f6033 · 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
  2. mnist_model_bn · e62092ae0cefe613 · 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
  3. ConvNet · ecd46bd39b55f6ff · 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
  4. Conv_2D_Block · ee9c55f86560d2a6 · 1 brick; 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) · 0 unverified · The assembly has not been run end-to-end · assemblies[15] in the JSON twin

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1502.03167") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

General ClassificationImage Classificationimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: Inception v2

1x1 ConvolutionAuxiliary ClassifierBatch NormalizationConvolutionDense ConnectionsDropoutExponential DecayInception ModuleInception v2Max PoolingRandom Horizontal FlipRandom Resized CropReLUSGD with MomentumSoftmaxWeight 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