Papers › EfficientNetV2: Smaller Models and Faster Training

EfficientNetV2: Smaller Models and Faster Training

1 Apr 2021arXiv:2104.00298archive 2025-07-28

Mingxing Tan, Quoc V. Le

This paper introduces EfficientNetV2, a new family of convolutional networks that have faster training speed and better parameter efficiency than previous models. To develop this family of models, we use a combination of training-aware neural architecture search and scaling, to jointly optimize training speed and parameter efficiency. The models were searched from the search space enriched with new ops such as Fused-MBConv. Our experiments show that EfficientNetV2 models train much faster than state-of-the-art models while being up to 6.8x smaller. Our training can be further sped up by progressively increasing the image size during training, but it often causes a drop in accuracy. To compensate for this accuracy drop, we propose to adaptively adjust regularization (e.g., dropout and data augmentation) as well, such that we can achieve both fast training and good accuracy. With progressive learning, our EfficientNetV2 significantly outperforms previous models on ImageNet and CIFAR/Cars/Flowers datasets. By pretraining on the same ImageNet21k, our EfficientNetV2 achieves 87.3% top-1 accuracy on ImageNet ILSVRC2012, outperforming the recent ViT by 2.0% accuracy while training 5x-11x faster using the same computing resources. Code will be available at https://github.com/google/automl/tree/master/efficientnetv2.

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.

Syntology holds a reference implementation of EfficientNetV2, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). For this implementation, level 3 is recorded, but its report lists no property test that passed on both. No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='EfficientNetV2') (how to connect); the free check have('2104.00298') needs no token.

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

Code

Syntology 79 code samples harvested from 15 repositories linked to this paper: 55 ran (of which 14 constructed an object rather than computing a result; 43 with no instrument failure: 11 honoured, 0 violated, 32 with no contract checked; 12 where Syntology's instrument failed) · 24 unverified. Where Syntology's instrument failed: 8 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: official repository: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 76 samples from 13 repositories, 52 ran (42 with no instrument failure; 10 where Syntology's instrument failed); community: 2 samples from 1 repository, 2 ran (0 with no instrument failure; 2 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 6 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 5 of the 55 samples that ran have no recorded date.

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

google/automl officialtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
rwightman/pytorch-image-models mentioned in papermentioned 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
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
Klassikcat/project-NEXTLab-CNN-EfficientNet mentioned on GitHubtfSyntology: 9 samples, 6 ran (2 instrument-failed) · 3 unverified report
abhuse/pytorch-efficientnet mentioned on GitHubpytorchSyntology: 9 samples, 6 ran (1 instrument-failed) · 3 unverified report
ardeal/EfficientNetV2 mentioned on GitHubpytorchSyntology: not harvested report
d-li14/efficientnetv2.pytorch mentioned on GitHubpytorchSyntology: 5 samples, 0 ran · 5 unverified report
danstowell/insect_classifier_GDSC23_insecteffnet mentioned on GitHubpytorchMITSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
hankyul2/EfficientNetV2-pytorch mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
jahongir7174/EffcientNetV2 mentioned on GitHubpytorchApache-2.0Syntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
jahongir7174/EfficientNetV2 mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified 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
leondgarse/Keras_efficientnet_v2 mentioned on GitHubtfSyntology: 7 samples, 4 ran (3 instrument-failed) · 3 unverified report
lukemelas/EfficientNet-PyTorch mentioned on GitHubpytorchSyntology: 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
open-edge-platform/geti mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
phykn/film-defect-detection mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
seermer/TensorFlow2-EfficientNetV2 mentioned on GitHubtfSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
szq0214/fkd mentioned on GitHubpytorchSyntology: 8 samples, 7 ran (0 instrument-failed) · 1 unverified report
2023-MindSpore-1/ms-code-193 mindsporeSyntology: not harvested report
DavidLandup0/deepvision pytorchSyntology: 10 samples, 4 ran (1 instrument-failed) · 6 unverified report
hwzwx1190522/efficientnetv2 mindsporeApache-2.0Syntology: 7 samples, 7 ran (3 instrument-failed) · 0 unverified report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
mindspore-ecosystem/mindcv mindsporeSyntology: not harvested report
open-edge-platform/training_extensions pytorchApache-2.0Syntology: not harvested report
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
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

79 samples harvested: 55 ran (of which 14 constructed an object rather than computing a result; 43 with no instrument failure: 11 honoured, 0 violated, 32 with no contract checked; 12 where Syntology's instrument failed) · 24 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.

11ran · honoured contract
8ran · our draft was wrong
4ran; the contract check could not run
32ran
24unverified

Licence: 13 of the 79 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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 11 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

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

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

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

google/automl official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
round_filters in 47 papers efficientnetv2/effnetv2_model.py ran · honoured contract Apache-2.0 (permissive) · 5640ec0612debaea · report fixture: signature filters:int/0/int, mconfig:MockMConfig/0/?, skip:bool/0/bool · returned int · level recorded, date not recorded
Klassikcat/project-NEXTLab-CNN-EfficientNet community (archive-listed) 9 samples, 6 ran (2 instrument-failed) · 3 unverified
ConvKernalInitializer EfficientNet_codestates/model/model.py ran no licence file found · pointer only · 4727c94370c69e97 · report fixture: signature shape:tuple/1/int, dtype:DType/0/?, partition_info:NoneType/0/? · returned EagerTensor · level recorded 2026-09-24
MBConvBlock in 10 papers EfficientNet_codestates/model/model.py ran · our draft was wrong no licence file found · pointer only · cb2b257652e0c5cc · report fixture: signature block_args:BlockArgs/0/?, global_params:GlobalParams/0/?, drop_connect_rate:float/0/float · returned function · level recorded 2026-09-22
SEBlock in 14 papers EfficientNet_codestates/model/model.py ran · our draft was wrong no licence file found · pointer only · 020b78c721a6198e · report fixture: signature block_args:BlockArgs/0/?, global_params:GlobalParams/0/? · returned function · level recorded 2026-09-22
Swish in 30 papers
census: 22 implementations from 19 papers, 2 distinct outputs on one shared input
EfficientNet_codestates/model/model.py ran fingerprinted no licence file found · pointer only · d9cb72304c6ddff3 · report fixture: signature inputs:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-24
round_filters in 47 papers EfficientNet_codestates/model/model.py ran · honoured contract no licence file found · pointer only · 8c25eeaec4c91203 · report fixture: signature filters:int/0/int, global_params:GlobalParams/0/? · returned int · level recorded 2026-09-22
round_repeats in 39 papers EfficientNet_codestates/model/model.py ran · honoured contract no licence file found · pointer only · f93cb693ac8bb537 · report fixture: signature repeats:int/0/int, global_params:GlobalParams/0/? · returned int · level recorded 2026-09-22
DenseKernalInitializer EfficientNet_codestates/model/model.py unverified no licence file found · pointer only · e19de965ff30b13f · report
DropConnect EfficientNet_codestates/model/model.py unverified no licence file found · pointer only · 46312249974aad39 · report
EfficientNet in 7 papers EfficientNet_codestates/model/model.py unverified no licence file found · pointer only · 17727025309b999a · report
abhuse/pytorch-efficientnet community (archive-listed) 9 samples, 6 ran (1 instrument-failed) · 3 unverified
MBConvBlockV2 efficientnet_v2.py ran fingerprinted MIT (permissive) · f9ecf91bbb0df74d · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
SamePaddingConv2d efficientnet_v2.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · b7194f8c7b7e316c · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
_pair efficientnet_v2.py ran · honoured contract fingerprinted MIT (permissive) · 9bfd0b1a5faef873 · report fixture: signature x:int/0/int · returned tuple · level recorded 2026-09-22
round_filters in 47 papers efficientnet_v2.py ran · honoured contract fingerprinted MIT (permissive) · 6c7d046d7dd60b22 · report fixture: signature filters:int/0/int, width_coefficient:float/0/float, depth_divisor:int/0/int · returned int · level recorded 2026-09-22
round_repeats in 39 papers efficientnet_v2.py ran · honoured contract fingerprinted MIT (permissive) · 167f9f74323c7278 · report fixture: signature repeats:int/0/int, depth_coefficient:float/0/float · returned int · level recorded 2026-09-22
torch_conv_out_spatial_shape efficientnet_v2.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 97d77e37b5677cd8 · report fixture: signature in_spatial_shape:tuple/1/int, kernel_size:int/0/int, stride:int/0/int · returned tuple · level recorded 2026-09-22
EfficientNetV2 efficientnet_v2.py unverified MIT (permissive) · 2d5bb8dbdbfbf4d1 · report
FusedMBConvBlockV2 efficientnet_v2.py unverified MIT (permissive) · 1473a64f191e86c2 · report
get_activation in 218 papers efficientnet_v2.py unverified MIT (permissive) · d9d9a4a8f00a818e · report
d-li14/efficientnetv2.pytorch community (archive-listed) 5 samples, 0 ran · 5 unverified
EffNetV2 effnetv2.py unverified MIT (permissive) · cead257166f9875e · report
MBConv in 10 papers effnetv2.py unverified MIT (permissive) · 2ae034e0700fa114 · report
SELayer in 12 papers effnetv2.py unverified MIT (permissive) · ce725cd28eee3383 · report
conv_1x1_bn in 59 papers effnetv2.py unverified MIT (permissive) · 15be99ad0bcca709 · report
conv_3x3_bn in 21 papers effnetv2.py unverified MIT (permissive) · 70ced89b3b23f051 · report
danstowell/insect_classifier_GDSC23_insecteffnet community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
collate_fn in 500 papers src/custom/data.py ran MIT (permissive) · 428d01f7470ad87b · report fixture: signature batch:list/1/dict · returned dict · level recorded 2026-09-24
get_max_amplitude_window_index src/custom/utils.py ran MIT (permissive) · f905c37ee28fdfb6 · report fixture: signature path:str/0/str, waveform:Tensor/2/float, samplerate:int/0/int, window_length_sec:int/0/int, scan_param:int/0/int, verbose:bool/0/bool · returned int · level recorded 2026-09-24
get_min_max src/custom/utils.py ran MIT (permissive) · 19efbee201b88cff · report fixture: signature cfg:MockConfig/0/?, dm:callable/0/?, model:callable/0/? · returned tuple · level recorded 2026-09-24
min_max_norm in 19 papers
census: 3 implementations from 6 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
src/custom/utils.py ran fingerprinted MIT (permissive) · 5c88df91221a8d8c · report fixture: signature x:Tensor/2/float, min_val:float/0/float, max_val:float/0/float · returned Tensor · level recorded 2026-09-24
upload_to_s3 src/gdsc_utils.py unverified MIT (permissive) · 615b8fc6facd6894 · report
hankyul2/EfficientNetV2-pytorch community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
ConvBNAct in 5 papers efficientnetv2/efficientnet_v2.py ran fingerprinted Apache-2.0 (permissive) · 2a8679c295eca86e · report fixture: returned ConvBNAct · level recorded 2026-09-22
MBConv in 10 papers efficientnetv2/efficientnet_v2.py ran fingerprinted Apache-2.0 (permissive) · 5c4ec70828e49d68 · report fixture: returned MBConv · level recorded 2026-09-22
SEUnit efficientnetv2/efficientnet_v2.py ran Apache-2.0 (permissive) · 2a6675c2cebf02ab · report fixture: returned SEUnit · level recorded 2026-09-22
StochasticDepth efficientnetv2/efficientnet_v2.py ran fingerprinted Apache-2.0 (permissive) · eacbe6ee4a26a27f · report fixture: returned StochasticDepth · level recorded 2026-09-22
EfficientNetV2 efficientnetv2/efficientnet_v2.py unverified Apache-2.0 (permissive) · 317a74053ff408d2 · report
jahongir7174/EffcientNetV2 community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
utils/util.py ran Apache-2.0 (permissive) · 279ab9885f76b013 · report fixture: signature output:Tensor/2/float, target:Tensor/1/int, top_k:list/1/int · returned list · level recorded 2026-09-24
rotate in 56 papers utils/util.py ran Apache-2.0 (permissive) · 8d9311e021af04d6 · report fixture: signature image:Image/0/?, magnitude:float/0/float · returned Image · level recorded 2026-09-24
weight_decay utils/util.py ran Apache-2.0 (permissive) · 3e49c5fa4dfff12e · report fixture: signature model:callable/0/?, decay:float/0/float · returned list · level recorded 2026-09-24
jahongir7174/EfficientNetV2 community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
Conv in 30 papers
census: 8 implementations from 8 papers, 8 distinct outputs across 2 buckets, one shared input per bucket
nets/nn.py ran fingerprinted Apache-2.0 (permissive) · 9354545acc375b1b · report fixture: returned Conv · level recorded 2026-09-22
EfficientNet in 7 papers nets/nn.py ran fingerprinted Apache-2.0 (permissive) · 4f25eeb823c2de8b · report fixture: returned EfficientNet · level recorded 2026-09-22
Residual in 24 papers nets/nn.py ran fingerprinted Apache-2.0 (permissive) · acb059769b4a4327 · report fixture: returned Residual · level recorded 2026-09-22
SE in 13 papers nets/nn.py ran Apache-2.0 (permissive) · 57a73cdb3469e654 · report fixture: returned SE · level recorded 2026-09-22
init_weight in 5 papers nets/nn.py unverified Apache-2.0 (permissive) · af3379144cf17adc · report
leondgarse/Keras_efficientnet_v2 community (archive-listed) 7 samples, 4 ran (3 instrument-failed) · 3 unverified
_make_divisible in 9 papers keras_efficientnet_v2/efficientnet_v2.py ran · honoured contract Apache-2.0 (permissive) · 29f99c375893c0a7 · report fixture: signature v:int/0/int, divisor:int/0/int, min_value:NoneType/0/? · returned int · level recorded 2026-09-22
batchnorm_with_activation keras_efficientnet_v2/efficientnet_v2.py ran · our draft was wrong Apache-2.0 (permissive) · e9ed9f7ced6189ee · report fixture: signature inputs:KerasTensor/0/float, activation:str/0/str, use_torch_eps:bool/0/bool, name:str/0/str · returned KerasTensor · level recorded 2026-09-22
conv2d_no_bias keras_efficientnet_v2/efficientnet_v2.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 96248e1c8a073860 · report fixture: signature inputs:EagerTensor/4/float, filters:int/0/int, kernel_size:int/0/int, strides:int/0/int, padding:str/0/str, use_torch_padding:bool/0/bool, name:str/0/str · returned EagerTensor · level recorded 2026-09-22
se_module keras_efficientnet_v2/efficientnet_v2.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · b43c2e4c5402cf83 · report fixture: signature inputs:EagerTensor/4/float, se_ratio:int/0/int, name:str/0/str · returned EagerTensor · level recorded 2026-09-22
EfficientNetV2 keras_efficientnet_v2/efficientnet_v2.py unverified Apache-2.0 (permissive) · b5e6a1fcfb844a2d · report
MBConv in 10 papers keras_efficientnet_v2/efficientnet_v2.py unverified Apache-2.0 (permissive) · 82eb14986b238976 · report
reload_model_weights keras_efficientnet_v2/efficientnet_v2.py unverified Apache-2.0 (permissive) · f734bb6fe9d256d2 · report
phykn/film-defect-detection community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
CLF_MODEL module/model.py ran fingerprinted no licence file found · pointer only · 87eea03ed82a58bb · report fixture: returned CLF_MODEL · level recorded 2026-09-22
seermer/TensorFlow2-EfficientNetV2 community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
round_filters in 47 papers efficientnetV2.py ran · honoured contract fingerprinted MIT (permissive) · e60387e9529f63ff · report fixture: signature filters:int/0/int, multiplier:float/0/float · returned int · level recorded, date not recorded
round_repeats in 39 papers efficientnetV2.py ran · honoured contract fingerprinted MIT (permissive) · 1a9d7e65e0a9fbc9 · report fixture: signature repeats:int/0/int, multiplier:float/0/float · returned int · level recorded, date not recorded
szq0214/fkd community (archive-listed) 8 samples, 7 ran (0 instrument-failed) · 1 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
FKD/FKD_ViT/SReT.py ran MIT (permissive) · e3021018c5f52aca · report fixture: signature x:Tensor/3/float, recursive_index:bool/0/bool · returned Tensor · level recorded 2026-09-24
LearnableCoefficient FKD/FKD_ViT/SReT.py ran fingerprinted MIT (permissive) · 70b3286546cf6d44 · report fixture: returned LearnableCoefficient · level recorded 2026-09-22
Non_proj FKD/FKD_ViT/SReT.py ran MIT (permissive) · 311f34cd673ace61 · report fixture: returned Non_proj · level recorded 2026-09-22
Transformer in 173 papers FKD/FKD_ViT/SReT.py ran MIT (permissive) · 8ecbf3a8e9175884 · report fixture: returned Transformer · level recorded 2026-09-22
Transformer_Block FKD/FKD_ViT/SReT.py ran MIT (permissive) · 547d2d46045ba04f · report fixture: returned Transformer_Block · level recorded 2026-09-22
conv_embedding FKD/FKD_ViT/SReT.py ran fingerprinted MIT (permissive) · 3b89a9e5b46d66cf · report fixture: returned conv_embedding · level recorded 2026-09-22
conv_head_pooling FKD/FKD_ViT/SReT.py ran MIT (permissive) · 82db52dd557154d5 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
SReT FKD/FKD_ViT/SReT.py unverified MIT (permissive) · e13c85dfb8576aa4 · report
DavidLandup0/deepvision community (archive-listed) 10 samples, 4 ran (1 instrument-failed) · 6 unverified
__FusedMBConvTF deepvision/models/classification/efficientnet/efficientnetv2.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 3c00e00b9c6c998f · report fixture: signature inputs:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-22
_make_divisible in 9 papers deepvision/models/classification/efficientnet/efficientnetv2.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 933cca1f8110f0cc · report fixture: signature filter_num:int/0/int, width_coefficient:float/0/float, depth_divisor:int/0/int, min_depth:int/0/int · returned int · level recorded 2026-09-24
parse_model_inputs deepvision/models/classification/efficientnet/efficientnetv2.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · d2941723ae4cc495 · report fixture: signature backend:str/0/str, input_shape:tuple/1/int, input_tensor:NoneType/0/? · returned KerasTensor · level recorded 2026-09-22
same_padding in 10 papers deepvision/models/classification/efficientnet/efficientnetv2.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · ec08335b5c6ecfc3 · report fixture: signature kernel_size:int/0/int, stride:int/0/int, dilation:int/0/int · returned int · level recorded 2026-09-22
EfficientNetV2B0 deepvision/models/classification/efficientnet/efficientnetv2.py unverified Apache-2.0 (permissive) · aa534eb3198967f2 · report
EfficientNetV2PT deepvision/models/classification/efficientnet/efficientnetv2.py unverified Apache-2.0 (permissive) · 4d580d4938dce187 · report
EfficientNetV2TF deepvision/models/classification/efficientnet/efficientnetv2.py unverified Apache-2.0 (permissive) · c9682cc2131f0a47 · report
FusedMBConv deepvision/models/classification/efficientnet/efficientnetv2.py unverified Apache-2.0 (permissive) · 5e2c67378c46d21d · report
MBConv in 10 papers deepvision/models/classification/efficientnet/efficientnetv2.py unverified Apache-2.0 (permissive) · dea1a4dc9a146df6 · report
__FusedMBConvPT deepvision/models/classification/efficientnet/efficientnetv2.py unverified Apache-2.0 (permissive) · 3fa8caaf6d69f294 · report
hwzwx1190522/efficientnetv2 community (archive-listed) 7 samples, 7 ran (3 instrument-failed) · 0 unverified
arg_to_varname in 10 papers efficientnetv2/src/configs/parser.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 177a4abf40724f6e · report fixture: signature st:str/0/str · returned str · level recorded 2026-09-25
argv_to_vars in 10 papers efficientnetv2/src/configs/parser.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · ffc9d7cced6f71fb · report fixture: signature argv:list/1/str · returned list · level recorded 2026-09-25
assignment efficientnetv2/src/models/var_init.py ran Apache-2.0 (permissive) · 615dd6b5188585cd · report fixture: signature arr:ndarray/0/float, num:float/0/float · returned ndarray · level recorded 2026-09-24
calcul_acc in 6 papers efficientnetv2/postprocess.py ran fingerprinted Apache-2.0 (permissive) · 5af3c724a0f8260c · report fixture: signature lab:list/1/int, preds:list/1/int · returned float · level recorded 2026-09-24
calculate_gain in 14 papers efficientnetv2/src/models/var_init.py ran Apache-2.0 (permissive) · e460868d0e106ef7 · report fixture: signature nonlinearity:str/0/str, param:NoneType/0/? · returned float · level recorded 2026-09-24
kaiming_uniform_ in 7 papers efficientnetv2/src/models/var_init.py ran Apache-2.0 (permissive) · f3e2d15712198ce4 · report fixture: signature arr:ndarray/2/float, a:float/0/float, mode:str/0/str, nonlinearity:str/0/str · returned ndarray · level recorded 2026-09-24
trim_preceding_hyphens in 10 papers efficientnetv2/src/configs/parser.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · a99f170ebd682af5 · report fixture: signature st:str/0/str · returned str · level recorded 2026-09-25
JohnnyHopp/PaDiM-EfficientNetV2 community 2 samples, 2 ran (2 instrument-failed) · 0 unverified
compute_pca in 5 papers utils.py ran · our draft was wrong Apache-2.0 (permissive) · 4b11257d79964d87 · report fixture: signature args:Args/0/?, features:list/1/Tensor, variance_threshold:float/0/float · returned tuple · level recorded, date not recorded
pca_reduction utils.py ran · our draft was wrong Apache-2.0 (permissive) · 56c266222ed70de4 · report fixture: signature features:Tensor/4/float, pca_mean:Tensor/1/float, pca_components:Tensor/2/float, device:device/0/? · returned Tensor · level recorded, date not recorded

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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. 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. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". 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. Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

9 assemblies on this paper: 8 harvested, 1 generated, listed in 2 groups (siblings lifted in one batch form one group).

generated Assembly for EfficientNetV2 (graph method: EfficientNetV2), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer; level 3 is recorded, but its report lists no property test that passed on both.

label matches by construction: the code was generated for this method (not judged by a model)

  1. compute_progressive_schedule entry · level 3 · ran · violated contract · a6f47b7943712df36efe42707b62de93efb8b00f029a7593cf532dbb779e684a

8 sibling assemblies for EfficientNetV2 (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for EfficientNetV2 (graph method: EfficientNetV2). 9 bricks; individually on a fixture: 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. EfficientNet entry · level 0 · unverified · 17727025309b999a
  2. ConvKernalInitializer helper · level 1 · ran · 4727c94370c69e97
  3. DenseKernalInitializer helper · level 0 · unverified · e19de965ff30b13f
  4. MBConvBlock model · level 1 · ran · our draft was wrong · cb2b257652e0c5cc
  5. Swish helper · level 1 · ran · d9cb72304c6ddff3
  6. round_filters helper · level 1 · ran · honoured contract · 8c25eeaec4c91203
  7. round_repeats helper · level 1 · ran · honoured contract · f93cb693ac8bb537
  8. DropConnect helper · level 0 · unverified · 46312249974aad39
  9. SEBlock model · level 1 · ran · our draft was wrong · 020b78c721a6198e

harvested Assembly for EfficientNetV2 (graph method: EfficientNetV2). 7 bricks; individually on a fixture: 4 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; 3 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. EfficientNetV2 entry · level 0 · unverified · b5e6a1fcfb844a2d
  2. MBConv model · level 0 · unverified · 82eb14986b238976
  3. _make_divisible helper · level 1 · ran · honoured contract · 29f99c375893c0a7
  4. batchnorm_with_activation model · level 1 · ran · our draft was wrong · e9ed9f7ced6189ee
  5. conv2d_no_bias helper · level 1 · ran; the contract check could not run (RAISES) · 96248e1c8a073860
  6. reload_model_weights helper · level 0 · unverified · f734bb6fe9d256d2
  7. se_module model · level 1 · ran; the contract check could not run (RAISES) · b43c2e4c5402cf83

harvested Assembly for EfficientNetV2 (graph method: EfficientNetV2). 6 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) · 5 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. EffNetV2 entry · level 0 · unverified · cead257166f9875e
  2. MBConv helper · level 0 · unverified · 2ae034e0700fa114
  3. _make_divisible helper · level 1 · ran · honoured contract · 13f1c8e878ee2013
  4. conv_1x1_bn helper · level 0 · unverified · 15be99ad0bcca709
  5. conv_3x3_bn helper · level 0 · unverified · 70ced89b3b23f051
  6. SELayer helper · level 0 · unverified · ce725cd28eee3383

harvested Assembly for EfficientNetV2 (graph method: EfficientNetV2). 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 8 siblings

  1. CLF_MODEL entry · level 1 · ran · 87eea03ed82a58bb

harvested Assembly for EfficientNetV2 (graph method: EfficientNetV2). 5 bricks; individually on a fixture: 4 ran (of which 4 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; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 8 siblings

  1. EfficientNetV2 entry · level 0 · unverified · 317a74053ff408d2
  2. ConvBNAct helper · level 1 · ran · 2a8679c295eca86e
  3. MBConv model · level 1 · ran · 5c4ec70828e49d68
  4. SEUnit helper · level 1 · ran · 2a6675c2cebf02ab
  5. StochasticDepth helper · level 1 · ran · eacbe6ee4a26a27f

harvested Assembly for EfficientNetV2 (graph method: EfficientNetV2). 5 bricks; individually on a fixture: 4 ran (of which 4 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; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 8 siblings

  1. EfficientNet entry · level 1 · ran · 4f25eeb823c2de8b
  2. Conv model · level 1 · ran · 9354545acc375b1b
  3. Residual model · level 1 · ran · acb059769b4a4327
  4. SE model · level 1 · ran · 57a73cdb3469e654
  5. init_weight helper · level 0 · unverified · af3379144cf17adc

harvested Assembly for EfficientNetV2 (graph method: EfficientNetV2). 11 bricks; individually on a fixture: 8 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. EfficientNetV2 entry · level 0 · unverified · 2d5bb8dbdbfbf4d1
  2. FusedMBConvBlockV2 model · level 0 · unverified · 1473a64f191e86c2
  3. MBConvBlockV2 model · level 1 · ran · f9ecf91bbb0df74d
  4. SamePaddingConv2d model · level 1 · ran · b7194f8c7b7e316c
  5. get_activation helper · level 0 · unverified · d9d9a4a8f00a818e
  6. round_filters helper · level 1 · ran · honoured contract · 6c7d046d7dd60b22
  7. round_repeats helper · level 1 · ran · honoured contract · 167f9f74323c7278
  8. DropConnect helper · level 1 · ran · 022a04f9d9946e65
  9. SqueezeExcitate model · level 1 · ran · 2dd850153bf41407
  10. torch_conv_out_spatial_shape helper · level 1 · ran; the contract check could not run (RAISES) · 97d77e37b5677cd8
  11. _pair helper · level 1 · ran · honoured contract · 9bfd0b1a5faef873

harvested Assembly for EfficientNetV2 (graph method: EfficientNetV2). 10 bricks; individually on a fixture: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. EfficientNetV2B0 entry · level 0 · unverified · aa534eb3198967f2
  2. EfficientNetV2PT helper · level 0 · unverified · 4d580d4938dce187
  3. EfficientNetV2TF helper · level 0 · unverified · c9682cc2131f0a47
  4. FusedMBConv helper · level 0 · unverified · 5e2c67378c46d21d
  5. MBConv helper · level 0 · unverified · dea1a4dc9a146df6
  6. __FusedMBConvPT helper · level 0 · unverified · 3fa8caaf6d69f294
  7. __FusedMBConvTF helper · level 1 · ran · 3c00e00b9c6c998f
  8. _make_divisible helper · level 1 · ran · honoured contract · 933cca1f8110f0cc
  9. parse_model_inputs helper · level 1 · ran; the contract check could not run (RAISES) · d2941723ae4cc495
  10. same_padding helper · level 1 · ran · honoured contract · ec08335b5c6ecfc3

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="2104.00298") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

AutoMLClassificationData AugmentationImage ClassificationNeural Architecture Search

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification CIFAR-10 EfficientNetV2-L Percentage correct 99.1 #17 of 265 Archive leaderboard report
Image Classification CIFAR-10 EfficientNetV2-M Percentage correct 99.0 #24 of 265 Archive leaderboard report
Image Classification CIFAR-10 EfficientNetV2-S Percentage correct 98.7 #31 of 265 Archive leaderboard report
Image Classification CIFAR-100 EfficientNetV2-L Percentage correct 92.3 #13 of 211 Archive leaderboard report
Image Classification CIFAR-100 EfficientNetV2-M Percentage correct 92.2 #14 of 211 Archive leaderboard report
Image Classification CIFAR-100 EfficientNetV2-S Percentage correct 91.5 #19 of 211 Archive leaderboard report
Image Classification Flowers-102 EfficientNetV2-L Accuracy 98.8 #19 of 52 Archive leaderboard report
Image Classification Flowers-102 EfficientNetV2-M Accuracy 98.5 #23 of 52 Archive leaderboard report
Image Classification Flowers-102 EfficientNetV2-S Accuracy 97.9 #31 of 52 Archive leaderboard report
Image Classification ImageNet EfficientNetV2-XL (21k) GFLOPs 94 #97 of 1060 Archive leaderboard report
Image Classification ImageNet EfficientNetV2-XL (21k) Number of params 208M #97 of 1060 Archive leaderboard report
Image Classification ImageNet EfficientNetV2-XL (21k) Top 1 Accuracy 87.3% #97 of 1060 Archive leaderboard report
Image Classification ImageNet EfficientNetV2-L (21k) GFLOPs 53 #122 of 1060 Archive leaderboard report
Image Classification ImageNet EfficientNetV2-L (21k) Number of params 120M #122 of 1060 Archive leaderboard report
Image Classification ImageNet EfficientNetV2-L (21k) Top 1 Accuracy 86.8% #122 of 1060 Archive leaderboard report
Image Classification ImageNet EfficientNetV2-M (21k) GFLOPs 24 #167 of 1060 Archive leaderboard report
Image Classification ImageNet EfficientNetV2-M (21k) Number of params 54M #167 of 1060 Archive leaderboard report
Image Classification ImageNet EfficientNetV2-M (21k) Top 1 Accuracy 86.2% #167 of 1060 Archive leaderboard report
Image Classification ImageNet EfficientNetV2-L GFLOPs 53 #205 of 1060 Archive leaderboard report
Image Classification ImageNet EfficientNetV2-L Top 1 Accuracy 85.7% #205 of 1060 Archive leaderboard report
Image Classification ImageNet EfficientNetV2-M Top 1 Accuracy 85.1% #253 of 1060 Archive leaderboard report
Image Classification ImageNet EfficientNetV2-S (21k) GFLOPs 8.8 #278 of 1060 Archive leaderboard report
Image Classification ImageNet EfficientNetV2-S (21k) Number of params 22M #278 of 1060 Archive leaderboard report
Image Classification ImageNet EfficientNetV2-S (21k) Top 1 Accuracy 84.9% #278 of 1060 Archive leaderboard report
Image Classification ImageNet EfficientNetV2-S Top 1 Accuracy 83.9% #372 of 1060 Archive leaderboard report
Image Classification Stanford Cars EfficientNetV2-L Accuracy 95.1 #3 of 24 Archive leaderboard report
Image Classification Stanford Cars EfficientNetV2-M Accuracy 94.6 #4 of 24 Archive leaderboard report
Image Classification Stanford Cars EfficientNetV2-S Accuracy 93.8 #8 of 24 Archive leaderboard report

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

Methods

Introduced by this paper: EfficientNetV2

1x1 ConvolutionBatch NormalizationDepthwise ConvolutionDepthwise Separable ConvolutionDropoutEfficientNetV2Inverted Residual BlockPointwise Convolution

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