Papers › EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Mingxing Tan, Quoc V. Le
Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available. In this paper, we systematically study model scaling and identify that carefully balancing network depth, width, and resolution can lead to better performance. Based on this observation, we propose a new scaling method that uniformly scales all dimensions of depth/width/resolution using a simple yet highly effective compound coefficient. We demonstrate the effectiveness of this method on scaling up MobileNets and ResNet. To go even further, we use neural architecture search to design a new baseline network and scale it up to obtain a family of models, called EfficientNets, which achieve much better accuracy and efficiency than previous ConvNets. In particular, our EfficientNet-B7 achieves state-of-the-art 84.3% top-1 accuracy on ImageNet, while being 8.4x smaller and 6.1x faster on inference than the best existing ConvNet. Our EfficientNets also transfer well and achieve state-of-the-art accuracy on CIFAR-100 (91.7%), Flowers (98.8%), and 3 other transfer learning datasets, with an order of magnitude fewer parameters. Source code is at https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet.
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):
get_harvested_code_for_paper(arxiv_id="1905.11946")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1905.11946", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1905.11946")
Code
No sample from the archive's official repository (tensorflow/tpu) is linked to this paper; the 301 samples below come from 46 community repositories, and 1 more is identical to code Syntology harvested from another paper's repository. Syntology harvested code from tensorflow/tpu for another paper.
tensorflow/tpu: Syntology's graph links these samples to Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It (arXiv:2403.14715; that paper's own run record: 9 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method.
Syntology 302 code samples: 301 from 46 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 302: 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. Where Syntology's instrument failed: 29 where our contract draft was wrong; 12 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: community (archive-listed): 301 samples from 46 repositories, 197 ran (157 with no instrument failure; 40 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
No sample is linked to this paper from 21 of its repositories that Syntology harvested for other papers:
- tensorflow/tpu, official repository: harvested for another paper, listed under the repository
- Deci-AI/super-gradients, community (archive-listed): harvested for 4 other papers, listed under the repository
- IMvision12/keras-vision-models, community (archive-listed): harvested for another paper, listed under the repository
- Jmak12/Iris1, community (archive-listed): harvested for 2 other papers, listed under the repository
- ckyrkou/EmergencyNet, community (archive-listed): harvested for another paper, listed under the repository
- federicopozzi33/MobileOne-PyTorch, community (archive-listed): harvested for another paper, listed under the repository
- gomezzz/MSMatch, community (archive-listed): harvested for another paper, listed under the repository
- gomezzz/distmsmatch, community (archive-listed): harvested for 2 other papers, listed under the repository
- jaketae/mlp-mixer, community (archive-listed): harvested for another paper, listed under the repository
- james77777778/keras-image-models, community (archive-listed): harvested for another paper, listed under the repository
- kdha0727/lung-opacity-and-covid-chest-x-ray-detection, community (archive-listed): harvested for another paper, listed under the repository
- maxwelltsai/DeepGalaxy, community (archive-listed): harvested for another paper, listed under the repository
- osmr/imgclsmob, community (archive-listed): harvested for another paper, listed under the repository
- rwightman/efficientnet-jax, community (archive-listed): harvested for another paper, listed under the repository
- rwightman/pytorch-image-models, community (archive-listed): harvested for another paper, listed under the repository
- ultralytics/yolov5, community (archive-listed): harvested for another paper, listed under the repository
- NVIDIA/DeepLearningExamples, community (archive-listed): harvested for 2 other papers, listed under the repository
- PaddlePaddle/PaddleDetection, community (archive-listed): harvested for another paper, listed under the repository
- megvii-research/basecls, community (archive-listed): harvested for another paper, listed under the repository
- mindspore-ai/models, community (archive-listed): harvested for another paper, listed under the repository
- open-mmlab/mmdetection, community (archive-listed): harvested for another paper, listed under the repository
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.
144 repositories listed; official and paper-mentioned ones first.
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
302 samples harvested: 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. “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.
Licence: 113 of the 302 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 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 46 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. 1 sample is listed last, in a group without a repository. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 47 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.
266ad4c0f203ffd9 · report
fixture: returned Conv2dDynamicSamePadding · level recorded 2026-09-22 24f0722801d6e750 · report
fixture: returned Conv2dStaticSamePadding · level recorded 2026-09-22 census: 10 implementations from 13 papers, 4 distinct outputs across 4 buckets, one shared input per bucket utils/efficientnet_pytorch/model.py ran fingerprinted MIT (permissive) ·
59c76d4ae50a8e09 · report
fixture: returned Identity · level recorded 2026-09-22 04c2b7413de3c583 · report
fixture: returned MBConvBlock · level recorded 2026-09-22 3e40010da2a5d8d4 · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24 census: 9 implementations from 7 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32 utils/efficientnet_pytorch/model.py ran; the contract check could not run (RAISES) MIT (permissive) ·
1667bcdf49534735 · report
fixture: signature inputs:Tensor/4/float, p:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22 c606c2bc4ee20581 · report
fixture: signature image_size:NoneType/0/? · returned type · level recorded 2026-09-22 f3de0fad4310032a · report
1ec716db2a067c4e · report
eec6dd2ad88dd583 · report
66fc31c225f5c1c8 · report
6bc82d121dc8f384 · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22 6d3b29dc187fc600 · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24 90d110db1ebe4a9f · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22 875775154df6e047 · report
fixture: signature w:int/0/int, w_factor:float/0/float · returned int · level recorded 2026-09-22 68480773e7901b00 · report
baa8031be7eeeb3f · report
49ebeee8958767b6 · report
fixture: signature model_name:str/0/str · returned tuple · level recorded 2026-09-22 67acf017bbbcc709 · report
1d0937ae17281862 · report
dda6eef82d7f7b1d · report
cfa3ae101a95697f · report
104350774512d05a · report
fixture: returned PSMClassifier2 · level recorded 2026-09-22 564f745d92b1336d · report
fixture: returned MBConv · level recorded 2026-09-22 27a4b6f92536df23 · report
fixture: returned SqueezeAndExcitation · level recorded 2026-09-22 census: 22 implementations from 19 papers, 2 distinct outputs on one shared input BB.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only ·
e6a10ca15fc11ae2 · report
fixture: returned Swish · level recorded 2026-09-22 1ce08d7e524c806f · report
fixture: returned Conv2dBNSwish · level recorded 2026-09-22 84c75ea5c4c6ccab · report
fixture: returned Conv2dStaticSamePadding · level recorded 2026-09-22 e5992e8fc871080e · report
fixture: signature inputs:Tensor/4/float · returned Tensor · level recorded 2026-09-25 census: 22 implementations from 19 papers, 2 distinct outputs on one shared input models/efficientnet.py ran fingerprinted Apache-2.0 (permissive) ·
66dc70278ea09595 · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24 census: 9 implementations from 7 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32 models/efficientnet.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) ·
53d13d88994382df · report
fixture: signature x:Tensor/4/float, drop_p:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22 ce78adffe6b7cfbf · report
fixture: signature in_size:int/0/int, kernel_size:int/0/int, stride:int/0/int · returned tuple · level recorded 2026-09-22 2897ef9945b295ae · report
ccb82a7bb4dc4e76 · report
fixture: signature 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, lr_decay_mode:str/0/str · returned ndarray · level recorded 2026-09-24 4ec0cd472dab11e6 · report
fixture: returned MBConvBlock · level recorded 2026-09-22 f1830b3a69e26f9a · report
fixture: returned SqueezeAndExcitation · level recorded 2026-09-22 census: 22 implementations from 19 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 EfficientNet.py ran · metamorphic tier: invariant fingerprinted GPL-3.0 (copyleft) · pointer only ·
1339ce8e95475b4f · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22 b33a4227f2459d0c · report
fixture: signature channels:int/0/int, eps:float/0/float, momentum:float/0/float · returned BatchNorm2d · level recorded 2026-09-22 81d0bda15f4ce563 · report
fixture: signature in_channel:int/0/int, out_channels:int/0/int · returned Sequential · level recorded 2026-09-22 09ba7db4c4aa871f · report
fixture: signature in_channel:int/0/int, out_channels:int/0/int, stride:int/0/int · returned Sequential · level recorded 2026-09-22 324996b4be32112d · report
fixture: signature x:Tensor/4/float, drop_probability:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22 044f863afcf6ac45 · report
fixture: signature c:int/0/int, divisor:int/0/int, min_value:NoneType/0/? · returned int · level recorded 2026-09-22 ccc7b40f69cc138c · report
fixture: signature r:float/0/float · returned int · level recorded 2026-09-22 294237129c3be0de · report
2f0b96c7b0363f14 · report
fixture: signature input_size:tuple/1/int, num_classess:int/0/int, pretrained_model:callable/0/?, lr_rate:float/0/float, print_trainable_layers:bool/0/bool, print_model_summary:bool/0/bool · returned Sequential · level recorded 2026-09-22 e5d7394f702bce4f · report
fixture: returned ConvBNAct · level recorded 2026-09-22 022a04f9d9946e65 · report
fixture: returned DropConnect · level recorded 2026-09-22 83e6b8c7711100ba · report
fixture: returned SamePaddingConv2d · level recorded 2026-09-22 2dd850153bf41407 · report
fixture: returned SqueezeExcitate · level recorded 2026-09-22 census: 22 implementations from 19 papers, 2 distinct outputs on one shared input efficientnet.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) ·
162b59d598cf2b8d · report
fixture: returned Swish · level recorded 2026-09-22 b9a0d4810abb3ba2 · report
fixture: signature x:tuple/1/int · returned tuple · level recorded 2026-09-22 c02cf42f58d8ba47 · report
fixture: signature filters:int/0/int, width_coefficient:float/0/float, depth_divisor:int/0/int · returned int · level recorded 2026-09-22 0bacadac82be1cf1 · report
fixture: signature repeats:int/0/int, depth_coefficient:float/0/float · returned int · level recorded 2026-09-22 98c03ea9dd00a6d4 · report
fixture: signature filename:str/0/str, extensions:tuple/1/str · returned bool · level recorded 2026-09-24 54d4745a566d733c · report
fixture: signature filename:str/0/str · returned bool · level recorded 2026-09-24 a589a6dc02fcf46a · report
fixture: signature dir:str/0/str, class_to_idx:dict/0/?, extensions:tuple/1/str, is_valid_file:NoneType/0/? · returned list · level recorded 2026-09-24 6c89d2fc1db6b9b3 · report
fixture: returned ConvNormActivation · level recorded 2026-09-22 ce15b235b406b179 · report
fixture: returned SqueezeExcitation · level recorded 2026-09-22 9326f2905cb9ca12 · report
fixture: returned StochasticDepth · level recorded 2026-09-22 71a8c46d263c01df · report
fixture: returned _MBConvConfig · level recorded 2026-09-22 c0621a0616046823 · report
fixture: signature v:int/0/int, divisor:int/0/int, min_value:NoneType/0/? · returned int · level recorded 2026-09-22 326c8379ce627360 · report
fixture: signature input:Tensor/4/float, p:float/0/float, mode:str/0/str, training:bool/0/bool · returned Tensor · level recorded 2026-09-22 09a35fc3459f078c · report
295b2c0d91581363 · report
461b7bb4f0934e47 · report
96cb6ea5181b5b58 · report
eb0c08d7cb7b4e65 · report
fixture: signature variant:str/0/str, num_classes:int/0/int, in_channels:int/0/int, dropout:float/0/float · returned EfficientNet · level recorded 2026-09-22 d2d7c8a380d03958 · report
fixture: signature num_classes:int/0/int, in_channels:int/0/int, dropout:float/0/float · returned EfficientNet · level recorded 2026-09-22 ffeacdf965f2b5e1 · report
fixture: returned Arcface · level recorded 2026-09-22 998f5b8d1f852446 · report
fixture: returned ConvBNReLU · level recorded 2026-09-22 bf45f9808b476931 · report
fixture: returned EfficientNet · level recorded 2026-09-22 8094ed61838ecd75 · report
fixture: returned L2norm · level recorded 2026-09-22 6eb3c2113f675e0d · report
fixture: returned MBConvBlock · level recorded 2026-09-22 a03ef768d6f14956 · report
fixture: returned SqueezeExcitation · level recorded 2026-09-22 census: 22 implementations from 19 papers, 2 distinct outputs on one shared input models/efficientnet.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) ·
75f27b8c7fec5a95 · report
fixture: returned Swish · level recorded 2026-09-22 98d68ff672dd2414 · report
fixture: signature value:int/0/int, divisor:int/0/int · returned int · level recorded 2026-09-22 0185d7ea7d47feea · report
fixture: signature filters:int/0/int, width_mult:float/0/float · returned int · level recorded 2026-09-22 a20ed96fe07da037 · report
fixture: signature repeats:int/0/int, depth_mult:float/0/float · returned int · level recorded 2026-09-22 bc3b3c76102b5db3 · report
fixture: returned LinearBottleneck · level recorded 2026-09-22 ea0fa69c250f0853 · report
fixture: returned ReXNetV1 · level recorded 2026-09-22 a2139a71a6db628d · report
fixture: returned SE · level recorded 2026-09-22 census: 5 implementations from 5 papers, 1 distinct output on one shared input rexnetv1.py ran MIT (permissive) ·
042c12e604840fe5 · report
fixture: returned SiLU · level recorded 2026-09-22 dc799498e0608db3 · report
fixture: returned BlockParams · level recorded 2026-09-22 504d27ed9a1c6e35 · report
fixture: returned ClassyBlock · level recorded 2026-09-22 3c769f926756099c · report
fixture: returned ClassyHead · level recorded 2026-09-22 b7d0531d672b00e4 · report
fixture: returned ClassyModelHeadExecutorWrapper · level recorded 2026-09-22 50680c5a4b27413d · report
fixture: returned ClassyModelWrapper · level recorded 2026-09-22 afdcbdb347bce946 · report
fixture: returned EfficientNetParams · level recorded 2026-09-22 5ccf8b0ea00c8551 · report
fixture: returned _ClassyModelMethod · level recorded 2026-09-22 census: 9 implementations from 7 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32 classy_vision/models/efficientnet.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) ·
01ef2c316f547d5d · report
fixture: signature inputs:Tensor/4/float, is_training:bool/0/bool, drop_connect_rate:float/0/float · returned Tensor · level recorded 2026-09-22 a9eb26de692dd5db · report
fixture: signature kernel_size:int/0/int · returned int · level recorded 2026-09-22 fc71d27f7272c011 · report
fixture: returned list · level recorded 2026-09-22 e2c0fb9163a8c931 · report
fixture: signature num_repeats:int/0/int, depth_coefficient:float/0/float · returned int · level recorded 2026-09-22 6d8fa73dcf4bf74d · report
fixture: signature num_filters:int/0/int, width_coefficient:float/0/float, width_divisor:int/0/int, min_width:int/0/int · returned int · level recorded 2026-09-22 census: 14 implementations from 37 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 classy_vision/models/efficientnet.py ran · honoured contract fingerprinted MIT (permissive) ·
0aeebcafcf0c595f · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22 0b6d8d6cabdcc17f · report
59722dac41b7de0c · report
577fe9205f975d68 · report
ccf63c8b1bf1df9b · report
75db8e91ea09dcba · report
b479311cbdb39c73 · report
da0d7f14befd42aa · report
a6c621cb376b2db5 · report
census: 5 implementations from 5 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 pycls/models/effnet.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) ·
ec1871ecab27eb74 · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22 census: 9 implementations from 7 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32 pycls/models/effnet.py ran · our draft was wrong fingerprinted MIT (permissive) ·
79583b4154444ddf · report
fixture: signature x:Tensor/4/float, drop_ratio:float/0/float · returned Tensor · level recorded 2026-09-22 6ec3d848be3b48bd · report
d994706109d01293 · report
fixture: returned Conv2dDynamicSamePadding · level recorded 2026-09-22 7bbfa8fbce414cdb · report
fixture: returned Conv2dStaticSamePadding · level recorded 2026-09-22 45c9c18b06c8bcb5 · report
fixture: returned MBConvBlock · level recorded 2026-09-22 18640da0a6568157 · report
fixture: signature model_name:str/0/str, override_params:NoneType/0/? · returned tuple · level recorded 2026-09-22 9c94891ae254ddba · report
fixture: signature image_size:NoneType/0/? · returned type · level recorded 2026-09-22 2f32f03864721673 · report
d44dfa0d14e7e4e2 · report
85a7eb99ccbb130c · report
fixture: signature spectrogram_tensor:Tensor/2/float, name:str/0/str · returned BytesIO · level recorded 2026-09-24 8f6f707ba0175577 · report
fixture: signature model:callable/0/?, config_pruning_structured:list/1/dict · returned Sequential · level recorded 2026-09-24 a77fd64675094dd0 · report
fixture: signature model:callable/0/?, config_pruning_unstructured:list/1/dict · returned Sequential · level recorded 2026-09-24 08352c8175b8893c · report
fixture: signature fname:PosixPath/0/? · returned OrderedDict · level recorded 2026-09-24 06323037fec4c414 · report
fixture: returned Conv2dSame · level recorded 2026-09-22 20b2eb990021c72b · report
fixture: returned MBConvBlock · level recorded 2026-09-22 2fc126caba9b65d8 · report
fixture: returned SeperableConv2d · level recorded 2026-09-22 3a89c82bf8719699 · report
fixture: returned _ConvNd · level recorded 2026-09-22 7db873e7bc29b164 · report
fixture: signature input:Tensor/4/float, weight:Tensor/4/float, bias:Tensor/1/float, stride:tuple/1/int, padding:int/0/int, dilation:tuple/1/int, groups:int/0/int · returned Tensor · level recorded 2026-09-22 24bda4b29a97ed5d · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22 5cc7cf3352391247 · report
fixture: signature filters:int/0/int, global_params:GlobalParams/1/float · returned int · level recorded 2026-09-22 a02458cc5b951e63 · report
fixture: signature repeats:int/0/int, global_params:GlobalParams/1/float · returned int · level recorded 2026-09-22 census: 14 implementations from 37 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 efficientnet/model.py ran · honoured contract fingerprinted GPL-3.0 (copyleft) · pointer only ·
20fb7a08507b85ec · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22 da7004d73c684ef6 · report
7927c173c0f0ca71 · report
fixture: returned ConvBnAct2d · level recorded 2026-09-22 0ed1488c1c3e36ea · report
fixture: returned HeadNet · level recorded 2026-09-22 42356ee09c654508 · report
fixture: returned ResampleFeatureMap · level recorded 2026-09-22 f7475cb0c529d551 · report
fixture: returned SeparableConv2d · level recorded 2026-09-22 ac5713d4c65ee9d4 · report
fixture: returned DictConfig · level recorded 2026-09-22 3025270f9fc1fc52 · report
fixture: returned DictConfig · level recorded 2026-09-22 65f649cdb07ae59f · report
fixture: signature base_reduction:int/0/int · returned DictConfig · level recorded 2026-09-22 eb8f243998da7026 · report
fixture: signature fpn_name:str/0/str · returned DictConfig · level recorded 2026-09-22 d949698e78900f9b · report
bf06536a66d4ba7d · report
3292fd41883bc62e · report
a57f867a1c40ff43 · report
48214eb2b9f354d3 · report
10487e1a9c99c2ad · report
9bc44440c46faca6 · report
b62213f6ab8d5d94 · report
fixture: returned Final_Layer · level recorded 2026-09-22 c575f4a06415232c · report
fixture: returned LayerSuperBlock · level recorded 2026-09-22 355e6e1120d560a9 · report
fixture: returned MBConv · level recorded 2026-09-22 9848798a20cf7637 · report
fixture: returned Pool_Expand · level recorded 2026-09-22 1c78bc0ff1affcfa · report
fixture: returned Sequential · level recorded 2026-09-22 0aa29283f6dfba93 · report
fixture: signature image_bytes:bytes/0/? · returned Tensor · level recorded 2026-09-24 baf41a86c6340d29 · report
fixture: returned Conv2dStaticSamePadding · level recorded 2026-09-22 1413a9f89f3eba36 · report
fixture: signature image_size:NoneType/0/? · returned type · level recorded 2026-09-22 4d5b23e16b0810db · report
74e34b309f1b102a · report
cf490093d7f2e932 · report
e063e53fb12fc669 · report
04f39101f07909c0 · report
efc14c51253aa080 · report
fixture: signature backend:MockBackend/0/?, inputs:Tensor/4/float, kernel_size:int/0/int · returned tuple · level recorded 2026-09-22 a29c10730e448370 · report
fixture: signature kwargs:dict/0/? · returned tuple · level recorded 2026-09-22 ee3ddfb8b877c630 · report
3dd1a3bf20911c40 · report
4c2489abf5f3f26e · report
census: 14 implementations from 37 papers, 2 distinct outputs on one shared input net/efficientnet.py unverified no licence file found · pointer only ·
fb78bfa29ec2868d · report
b7a0bf27263bde3c · report
fixture: signature inputs:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-22 1150018650194f3d · report
d63a4a5b6867cace · report
8fdd37211c0c6646 · report
6b327bf48c63d1a2 · report
91e826511c79b394 · report
fixture: signature image:ndarray/3/int, image_size:int/0/int, crop_padding:int/0/int, interpolation:str/0/str · returned ndarray · level recorded 2026-09-24 00c946065068bd77 · report
fixture: signature filters:int/0/int, width_coefficient:float/0/float, depth_divisor:int/0/int · returned int · level recorded 2026-09-24 6cc796a8212b5586 · report
fixture: signature repeats:int/0/int, depth_coefficient:float/0/float · returned int · level recorded 2026-09-25 9e354d875b0e94e6 · report
fixture: signature model_name:str/0/str · returned tuple · level recorded 2026-09-22 378be63257f699b3 · report
657731396725618f · report
4efc79a49986fe84 · report
3428492d04f44096 · report
92f38ceb21745450 · report
a65db39ac3896281 · report
fixture: returned CondConv2d · level recorded 2026-09-22 8897f71021f4c878 · report
fixture: returned Conv2dSame · level recorded 2026-09-22 b7cc1f3027bf1ec5 · report
fixture: returned Conv2dSameExport · level recorded 2026-09-22 97c194d7b0388b28 · report
fixture: returned MixedConv2d · level recorded 2026-09-22 e30ededffe9676dd · report
fixture: signature i:int/0/int, k:int/0/int, s:int/0/int, d:int/0/int · returned int · level recorded 2026-09-22 91be8022b8d2891b · report
fixture: signature kernel_size:int/0/int, stride:int/0/int, dilation:int/0/int · returned int · level recorded 2026-09-22 e4eec881cd223a01 · report
fixture: signature kernel_size:int/0/int, stride:int/0/int, dilation:int/0/int · returned bool · level recorded 2026-09-22 38b714a51f0929d1 · report
fixture: signature input_size:tuple/1/int, kernel_size:tuple/1/int, stride:tuple/1/int, dilation:tuple/1/int · returned list · level recorded 2026-09-22 a991beae0b7b2c9b · report
fixture: signature x:Tensor/4/float, weight:Tensor/4/float, bias:Tensor/1/float, stride:tuple/1/int, padding:tuple/1/int, dilation:tuple/1/int, groups:int/0/int · returned Tensor · level recorded 2026-09-22 a4c55806bf0532cc · report
fixture: signature in_chs:int/0/int, out_chs:int/0/int, kernel_size:int/0/int, padding:str/0/str, stride:int/0/int, dilation:int/0/int, bias:bool/0/bool · returned Conv2d · level recorded 2026-09-22 1596e1e96e6f4e55 · report
fixture: signature padding:str/0/str, kernel_size:int/0/int, stride:int/0/int, dilation:int/0/int · returned tuple · level recorded 2026-09-22 5b54534e33abea82 · report
fixture: returned bool · level recorded 2026-09-22 2892b5323abd29b3 · report
fixture: returned bool · level recorded 2026-09-22 cb09a51574cc5390 · report
f6c9975be7030d36 · report
168fd8731445669d · report
fixture: signature image:ndarray/3/int, model:MockTFLiteInterpreter/0/?, clasify:MockClassifier/0/?, labels:ndarray/1/<U4 · returned tuple · level recorded 2026-09-24 6a74ab1f515ebce3 · report
fixture: signature dataset:MockDataset/0/? · returned tuple · level recorded 2026-09-24 009f493f3dfa109b · report
fixture: signature tf_path:str/0/str, cls_path:str/0/str · returned tuple · level recorded 2026-09-24 e8c2ddc644780538 · report
fixture: signature im:ndarray/2/float · returned ndarray · level recorded 2026-09-24 2b2d63252761e18c · report
4afd343c0c6753cb · report
fixture: signature string_list:list/1/str · returned list · level recorded 2026-09-24 46bcf7227b1c62a7 · report
fixture: returned Conv3dDynamicSamePadding · level recorded 2026-09-22 1e104a651d94f6c7 · report
fixture: returned Conv3dStaticSamePadding · level recorded 2026-09-22 census: 10 implementations from 13 papers, 4 distinct outputs across 4 buckets, one shared input per bucket efficientnet_pytorch_3d/model.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) ·
b308ef01620c79cd · report
fixture: returned Identity · level recorded 2026-09-22 d9104e773e32582e · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24 census: 22 implementations from 19 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 efficientnet_pytorch_3d/model.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) ·
252e1eae260cbe75 · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22 census: 9 implementations from 7 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 5, kind float, dtype float32 efficientnet_pytorch_3d/model.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) ·
4e82aac968b327d5 · report
fixture: signature inputs:Tensor/5/float, p:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22 82cccbe600b7d10e · report
fixture: signature width_coefficient:float/0/float, depth_coefficient:float/0/float, dropout_rate:float/0/float, drop_connect_rate:float/0/float, image_size:int/0/int, num_classes:int/0/int, include_top:bool/0/bool · returned tuple · level recorded 2026-09-22 320b5a90d92ede9f · report
fixture: signature model_name:str/0/str · returned tuple · level recorded 2026-09-22 fe7006f075113df2 · report
fixture: signature image_size:NoneType/0/? · returned type · level recorded 2026-09-22 468cd48d2ad92215 · report
57155ffea4bfd0dc · report
cec8456f1fb53df1 · report
8bec8aa4a16e9f20 · report
fixture: signature phi:float/0/float, max_cost:float/0/float · returned function · level recorded 2026-09-24 b6f8b648481faef8 · report
fixture: signature filters: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 93d5e9bbed1bbac6 · report
fixture: signature repeats:int/0/int, depth_coefficient:float/0/float · returned int · level recorded 2026-09-24 e67661090608f8c2 · report
6356571ff908158d · report
fixture: returned SEBlock · level recorded 2026-09-22 census: 22 implementations from 19 papers, 2 distinct outputs on one shared input model.py ran fingerprinted no licence file found · pointer only ·
056a3c50f2525d95 · report
fixture: signature inputs:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-24 32213b389c413189 · report
fixture: returned int · level recorded 2026-09-22 dd9cd5e8d423782a · report
3ff08876de703a2c · report
752ac97648764023 · report
1138d11e9960eaac · report
fe7d84b7019b5acb · report
fixture: signature dataset:SimpleDataset/0/?, val_pct:float/0/float, test_pct:float/0/float, seed:int/0/int · returned list · level recorded 2026-09-24 2cf595e420327af7 · report
fixture: signature pred:ndarray/2/int, gt:ndarray/2/int, epsilon:float/0/float · returned float64 · level recorded 2026-09-24 930444bef5b84a1a · report
fixture: signature pred:Tensor/3/int, gt:Tensor/3/int, epsilon:float/0/float · returned Tensor · level recorded 2026-09-24 6934311622c0b9ee · report
fixture: returned Conv_Bn_Act · level recorded 2026-09-22 d0a7c70cc6b4bc84 · report
fixture: returned DropConnect · level recorded 2026-09-22 caa7473dbc2ecc01 · report
fixture: returned MBBlock · level recorded 2026-09-22 87bb84ef873236e1 · report
fixture: returned MBConv · level recorded 2026-09-22 9a1c69d3423d4c53 · report
fixture: returned SEModule · level recorded 2026-09-22 8d49f7a6dd466a76 · report
fixture: signature w_in:int/0/int, w_out:int/0/int, k:int/0/int, stride:int/0/int, groups:int/0/int, bias:bool/0/bool · returned Conv2d · level recorded 2026-09-22 748aee49bbd751b5 · report
b54dcb0ff1ef33f6 · report
fixture: returned EfficientNet · level recorded 2026-09-22 census: 9 implementations from 9 papers, 2 distinct outputs across 2 buckets, one shared input per bucket models/effnet.py ran fingerprinted no licence file found · pointer only ·
c49413302c78006f · report
fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24 25f0b7a4b6a66e1b · report
fixture: returned MBBlock · level recorded 2026-09-22 733d26522c639130 · report
fixture: returned MBConv · level recorded 2026-09-22 8057aed3a16324a9 · report
fixture: returned SEModule · level recorded 2026-09-22 5d7f11210997edf7 · report
fixture: returned SamePadConv2d · level recorded 2026-09-22 census: 22 implementations from 19 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 models/effnet.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only ·
1b5e656b7306390c · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22 61a5c9dd36b9652b · report
fixture: signature in_:int/0/int, out_:int/0/int, kernel_size:int/0/int, stride:int/0/int, groups:int/0/int, bias:bool/0/bool, eps:float/0/float, momentum:float/0/float · returned Sequential · level recorded 2026-09-22 c7e2a34a498dc9c6 · report
fixture: signature inputs:EagerTensor/4/float, activation_fn:callable/0/?, drop_rate:float/0/float, name:str/0/str, filters_in:int/0/int, filters_out:int/0/int, kernel_size:int/0/int, strides:int/0/int, expand_ratio:int/0/int, se_ratio:float/0/float, id_skip:bool/0/bool · returned EagerTensor · level recorded 2026-09-22 6119fa8a2cf9da60 · report
fixture: signature inputs:EagerTensor/4/float, kernel_size:int/0/int · returned tuple · level recorded 2026-09-22 5af3c724a0f8260c · report
fixture: signature lab:list/1/int, preds:list/1/int · returned float · level recorded 2026-09-24 d5c96845cfdedd0d · report
fixture: signature inp:ndarray/2/float, target:ndarray/1/float, classes:list/1/int, n_support:int/0/int, n_query:int/0/int, n_class:int/0/int, is_train:bool/0/bool · returned float32 · level recorded 2026-09-24 31a3eec30eadf89e · report
fixture: signature inpbool:ndarray/1/bool · returned ndarray · level recorded 2026-09-24 207a71e0949c8a8a · report
ae52bcdc3abf692f · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24 35d8014909ff76e9 · report
fixture: signature image_size:NoneType/0/? · returned type · level recorded 2026-09-22 51bba380030144c6 · report
8d56be7c0c811019 · report
f6c64e599cf1e5ec · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22 7ad03c68b6d88fbb · report
1eb95486a498bc00 · report
07fdad800f0f9e80 · report
5dff8aa1e58ce66a · report
fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-22 1db1211e94ba0542 · report
fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-22 cc0fad14de2a1db2 · report
fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-22 5d02b2d3887edbb5 · report
fixture: signature v:float/0/float, divisor:int/0/int, min_value:int/0/int · returned int · level recorded 2026-09-22 c7e8ddab9526912d · report
fixture: signature x:int/0/int, n:int/0/int · returned tuple · level recorded 2026-09-22 6010c21fa9b1def9 · report
fixture: signature input:Tensor/4/float, p:float/0/float, mode:str/0/str, training:bool/0/bool · returned Tensor · level recorded 2026-09-22 ab6dc48c7d59f65d · report
0dbeb0f5401c92c0 · report
76f2b07edb56e630 · report
fea90a6ba56fad7f · report
cff7317fe4842ee0 · report
15970bd2e8e1eab0 · report
cc2abd9e2b417d3e · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22 6f74cddc6f639ed0 · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24 e0d1e58cc21f79d6 · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24 4743aa1ff46fd656 · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22 census: 22 implementations from 19 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 tvmodels/models/blocks/effnet_blocks.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) ·
6a1c7184e78e8517 · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22 ee281d3bc3eb95ea · report
fixture: signature m:callable/0/?, func:callable/0/? · returned SimpleModule · level recorded 2026-09-24 2d524bf7f14118d5 · report
fixture: signature ni:int/0/int, nf:int/0/int, ksz:int/0/int, stride:int/0/int, pad:int/0/int, dilation:int/0/int, groups:int/0/int, bias:bool/0/bool, spectr:bool/0/bool · returned Conv2d · level recorded 2026-09-22 70cd615b99e8fc27 · report
fixture: signature ni:int/0/int, nf:int/0/int, ksz:int/0/int, stride:int/0/int, pad:int/0/int, dilation:int/0/int, groups:int/0/int, bn:bool/0/bool, spectr:bool/0/bool · returned list · level recorded 2026-09-22 5487b2812e719962 · report
fixture: signature ni:int/0/int, nf:int/0/int, ksz:int/0/int, stride:int/0/int, groups:int/0/int, swish:bool/0/bool · returned list · level recorded 2026-09-22 census: 8 implementations from 11 papers, 4 distinct outputs across 2 buckets, one shared input per bucket tvmodels/models/blocks/effnet_blocks.py ran · our draft was wrong MIT (permissive) ·
9461188086a155ec · report
fixture: signature leaky:float/0/float · returned ReLU · level recorded 2026-09-22 85b74fda877bab0e · report
293dab24489b41d1 · report
fixture: signature arg_value:int/0/int, arg_type:callable/0/?, arg_name:str/0/str, prim_name:str/0/str · returned int · level recorded 2026-09-24 e9ab9c1dbf475949 · report
814a8b32f5a29924 · report
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
census: 17 implementations from 25 papers, 8 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 2, kind float, dtype float32 repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded ·
c54fea429589425d · report
fixture: signature input:Tensor/2/float, axis:int/0/int · returned Tensor · level recorded 2026-09-22 Method as code Syntology
What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.
34 assemblies on this paper: 34 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
34 sibling assemblies for EfficientNets (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another. Bricks printed for 12 of 34 sibling assemblies; the other 22 are listed with their counts; every brick is in this page's JSON twin.
harvested Assembly for EfficientNets (graph method: EfficientNets). 21 bricks; individually on a fixture: 13 ran (of which 7 constructed an object rather than computing a result; 12 with no instrument failure: 4 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.
one of 34 siblings
- EfficientNet entry · level 0 · unverified ·
0b6d8d6cabdcc17f - EfficientNetParams helper · level 1 · ran ·
afdcbdb347bce946 - MBConvBlock model · level 0 · unverified ·
59722dac41b7de0c - register_model helper · level 0 · unverified ·
a6c621cb376b2db5 - scale_depth helper · level 1 · ran · honoured contract ·
e2c0fb9163a8c931 - scale_width helper · level 1 · ran · honoured contract ·
6d8fa73dcf4bf74d - swish helper · level 1 · ran · honoured contract ·
0aeebcafcf0c595f - drop_connect helper · level 1 · ran; the contract check could not run (RAISES) ·
01ef2c316f547d5d - get_same_padding_for_kernel_size helper · level 1 · ran · honoured contract ·
a9eb26de692dd5db - get_torch_version helper · level 1 · ran ·
fc71d27f7272c011 - BlockParams helper · level 1 · ran ·
dc799498e0608db3 - ClassyBlock helper · level 1 · ran ·
504d27ed9a1c6e35 - ClassyHead helper · level 1 · ran ·
3c769f926756099c - ClassyModelWrapper helper · level 1 · ran ·
50680c5a4b27413d - _ClassyModelMeta helper · level 0 · unverified ·
ccf63c8b1bf1df9b - _ClassyModelMethod helper · level 1 · ran ·
5ccf8b0ea00c8551 - build_head helper · level 0 · unverified ·
75db8e91ea09dcba - build_model helper · level 0 · unverified ·
b479311cbdb39c73 - log_class_usage helper · level 0 · unverified ·
da0d7f14befd42aa - ClassyModelHeadExecutorWrapper helper · level 1 · ran ·
b7d0531d672b00e4 - _ClassyModelAdapter helper · level 0 · unverified ·
577fe9205f975d68
harvested Assembly for EfficientNets (graph method: EfficientNets). 6 bricks; individually on a fixture: 6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 34 siblings
- make_model entry · level 1 · ran ·
1c78bc0ff1affcfa - Final_Layer model · level 1 · ran ·
b62213f6ab8d5d94 - LayerSuperBlock model · level 1 · ran ·
c575f4a06415232c - MBConv model · level 1 · ran ·
355e6e1120d560a9 - Pool_Expand model · level 1 · ran ·
9848798a20cf7637 - clones helper · level 1 · ran · our draft was wrong ·
22237c8ec0880bfd
harvested Assembly for EfficientNets (graph method: EfficientNets). 4 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 34 siblings
harvested Assembly for EfficientNets (graph method: EfficientNets). 10 bricks; individually on a fixture: 6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.
one of 34 siblings
- EfficientNet entry · level 0 · unverified ·
09a35fc3459f078c - Efficient_Net helper · level 0 · unverified ·
295b2c0d91581363 - ConvNormActivation model · level 1 · ran ·
6c89d2fc1db6b9b3 - SqueezeExcitation model · level 1 · ran ·
ce15b235b406b179 - StochasticDepth model · level 1 · ran ·
9326f2905cb9ca12 - _MBConvConfig helper · level 1 · ran ·
71a8c46d263c01df - _make_divisible helper · level 1 · ran · honoured contract ·
c0621a0616046823 - stochastic_depth helper · level 1 · ran; the contract check could not run (RAISES) ·
326c8379ce627360 - FusedMBConv model · level 0 · unverified ·
461b7bb4f0934e47 - MBConv model · level 0 · unverified ·
96cb6ea5181b5b58
harvested Assembly for EfficientNets (graph method: EfficientNets). 11 bricks; individually on a fixture: 11 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 34 siblings
- EfficientNet entry · level 1 · ran ·
bf45f9808b476931 - Arcface loss · level 1 · ran ·
ffeacdf965f2b5e1 - ConvBNReLU helper · level 1 · ran ·
998f5b8d1f852446 - L2norm helper · level 1 · ran ·
8094ed61838ecd75 - MBConvBlock model · level 1 · ran ·
6eb3c2113f675e0d - _round_filters helper · level 1 · ran · honoured contract ·
0185d7ea7d47feea - _round_repeats helper · level 1 · ran · honoured contract ·
a20ed96fe07da037 - l2_norm helper · level 1 · ran · our draft was wrong ·
c54fea429589425d - Swish helper · level 1 · ran ·
75f27b8c7fec5a95 - SqueezeExcitation model · level 1 · ran ·
a03ef768d6f14956 - _make_divisible helper · level 1 · ran · honoured contract ·
98d68ff672dd2414
harvested Assembly for EfficientNets (graph method: EfficientNets). 10 bricks; individually on a fixture: 9 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 34 siblings
- EfficientNet entry · level 0 · unverified ·
da7004d73c684ef6 - MBConvBlock model · level 1 · ran ·
20b2eb990021c72b - global_average_pooling2d model · level 1 · ran; the contract check could not run (RAISES) ·
24bda4b29a97ed5d - round_filters helper · level 1 · ran · honoured contract ·
5cc7cf3352391247 - round_repeats helper · level 1 · ran · honoured contract ·
a02458cc5b951e63 - swish model · level 1 · ran · honoured contract ·
20fb7a08507b85ec - SeperableConv2d model · level 1 · ran ·
2fc126caba9b65d8 - Conv2dSame helper · level 1 · ran ·
06323037fec4c414 - _ConvNd helper · level 1 · ran ·
3a89c82bf8719699 - conv2d_same_padding helper · level 1 · ran; the contract check could not run (RAISES) ·
7db873e7bc29b164
harvested Assembly for EfficientNets (graph method: EfficientNets). 8 bricks; individually on a fixture: 8 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; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 34 siblings
- EfficientNet entry · level 1 · ran ·
b54dcb0ff1ef33f6 - Flatten helper · level 1 · ran ·
c49413302c78006f - MBBlock model · level 1 · ran ·
25f0b7a4b6a66e1b - SamePadConv2d helper · level 1 · ran ·
5d7f11210997edf7 - conv_bn_act helper · level 1 · ran · our draft was wrong ·
61a5c9dd36b9652b - MBConv model · level 1 · ran ·
733d26522c639130 - Swish helper · level 1 · ran ·
1b5e656b7306390c - SEModule model · level 1 · ran ·
8057aed3a16324a9
harvested Assembly for EfficientNets (graph method: EfficientNets). 9 bricks; individually on a fixture: 8 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 34 siblings
- EfficientNet entry · level 0 · unverified ·
748aee49bbd751b5 - Conv_Bn_Act helper · level 1 · ran ·
6934311622c0b9ee - Flatten helper · level 1 · ran ·
c49413302c78006f - MBBlock model · level 1 · ran ·
caa7473dbc2ecc01 - SamePadConv2d helper · level 1 · ran ·
5d7f11210997edf7 - conv2d helper · level 1 · ran · our draft was wrong ·
8d49f7a6dd466a76 - MBConv model · level 1 · ran ·
87bb84ef873236e1 - DropConnect model · level 1 · ran ·
d0a7c70cc6b4bc84 - SEModule model · level 1 · ran ·
9a1c69d3423d4c53
harvested Assembly for EfficientNets (graph method: EfficientNets). 11 bricks; individually on a fixture: 8 ran (of which 5 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.
one of 34 siblings
- EfficientNet entry · level 0 · unverified ·
453fbbf2e315aaff - ConvBNAct model · level 1 · ran ·
e5d7394f702bce4f - EnetStage model · level 0 · unverified ·
4325226df196a0dd - Swish model · level 1 · ran ·
162b59d598cf2b8d - _pair helper · level 1 · ran · violated contract ·
b9a0d4810abb3ba2 - round_filters helper · level 1 · ran · honoured contract ·
c02cf42f58d8ba47 - round_repeats helper · level 1 · ran · honoured contract ·
0bacadac82be1cf1 - SamePaddingConv2d helper · level 1 · ran ·
83e6b8c7711100ba - MBConvBlock model · level 0 · unverified ·
d9d45fe93ed744ce - DropConnect model · level 1 · ran ·
022a04f9d9946e65 - SqueezeExcitate model · level 1 · ran ·
2dd850153bf41407
harvested Assembly for EfficientNets (graph method: EfficientNets). 9 bricks; individually on a fixture: 4 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.
one of 34 siblings
- EfficientNet entry · level 0 · unverified ·
752ac97648764023 - MBConvBlock helper · level 0 · unverified ·
1138d11e9960eaac - Swish helper · level 1 · ran ·
056a3c50f2525d95 - round_filters helper · level 1 · ran · honoured contract ·
8c25eeaec4c91203 - round_repeats helper · level 1 · ran · honoured contract ·
32213b389c413189 - DropConnect helper · level 0 · unverified ·
76a0661fe2c7d793 - SEBlock helper · level 1 · ran ·
6356571ff908158d - EfficientConv2DKernelInitializer helper · level 0 · unverified ·
dd9cd5e8d423782a - EfficientDenseKernelInitializer helper · level 0 · unverified ·
3ff08876de703a2c
harvested Assembly for EfficientNets (graph method: EfficientNets). 2 bricks; individually on a fixture: 2 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; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 34 siblings
- efficientnet_lite_b0 entry · level 1 · ran · our draft was wrong ·
d2d7c8a380d03958 - _efficientnet_lite helper · level 1 · ran · our draft was wrong ·
eb0c08d7cb7b4e65
harvested Assembly for EfficientNets (graph method: EfficientNets). 6 bricks; individually on a fixture: 2 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; 2 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.
one of 34 siblings
- EfficientNet entry · level 0 · unverified ·
ee3ddfb8b877c630 - block model · level 0 · unverified ·
3dd1a3bf20911c40 - build_branch model · level 0 · unverified ·
4c2489abf5f3f26e - correct_pad helper · level 1 · ran · our draft was wrong ·
efc14c51253aa080 - get_submodules_from_kwargs helper · level 1 · ran · our draft was wrong ·
a29c10730e448370 - swish helper · level 0 · unverified ·
fb78bfa29ec2868d
- EfficientNet3D · 581451b0fadb5235 · 16 bricks; individually on a fixture: 13 ran (of which 4 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
- GenEfficientNet · 5b57c49632cd0ec8 · 18 bricks; individually on a fixture: 16 ran (of which 4 constructed an object rather than computing a result; 11 with no instrument failure: 4 honoured, 1 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
- PSMClassifier2 · 66efc2b106961ece · 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 · assemblies[14] in the JSON twin
- EfficientNet · 76a6d9adf31c3475 · 19 bricks; individually on a fixture: 15 ran (of which 5 constructed an object rather than computing a result; 11 with no instrument failure: 3 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified · The assembly has not been run end-to-end · assemblies[15] in the JSON twin
- efficientnet · 7730985f3c695a8e · 2 bricks; individually on a fixture: 0 ran · 2 unverified · The assembly has not been run end-to-end · assemblies[16] in the JSON twin
- EfficientNet · 85dab5366027f558 · 17 bricks; individually on a fixture: 12 ran (of which 3 constructed an object rather than computing a result; 8 with no instrument failure: 3 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified · The assembly has not been run end-to-end · assemblies[17] in the JSON twin
- EfficientNet · 99d71eb6cd9498d6 · 16 bricks; individually on a fixture: 13 ran (of which 4 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified · The assembly has not been run end-to-end · assemblies[18] in the JSON twin
- EfficientNet · a0ab147089bfdba4 · 7 bricks; individually on a fixture: 6 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[19] in the JSON twin
- EfficientNet · a646c306c8b1e438 · 10 bricks; individually on a fixture: 9 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[20] in the JSON twin
- build_model_base · a9294c3ac44deeb8 · 5 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) · 4 unverified · The assembly has not been run end-to-end · assemblies[21] in the JSON twin
- EfficientDet · b5473ee57d92b593 · 15 bricks; individually on a fixture: 8 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified · The assembly has not been run end-to-end · assemblies[22] in the JSON twin
- efficientnet_lite · b65bc9e3f7d2b806 · 3 bricks; individually on a fixture: 2 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; 2 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[23] in the JSON twin
- EffNet · e352334b4a48ea90 · 18 bricks; individually on a fixture: 9 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; 8 where Syntology's instrument failed) · 9 unverified · The assembly has not been run end-to-end · assemblies[24] in the JSON twin
- EffNet · e4c70fce8bfc8f50 · 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[25] in the JSON twin
- build_model_base · ea68bfd306dad19f · 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 · assemblies[26] in the JSON twin
- build_classification_model · eb9fce333c81138b · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[27] in the JSON twin
- EfficientNet · ebb8975172af753a · 9 bricks; individually on a fixture: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified · The assembly has not been run end-to-end · assemblies[28] in the JSON twin
- EfficientNet · f5642ea32fcec986 · 17 bricks; individually on a fixture: 13 ran (of which 3 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified · The assembly has not been run end-to-end · assemblies[29] in the JSON twin
- EfficientNet · faf08a693f5b95a6 · 12 bricks; individually on a fixture: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified · The assembly has not been run end-to-end · assemblies[30] in the JSON twin
- ImageEncoderBackbone · fc96c2fdc437f8d5 · 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[31] in the JSON twin
- EfficientNet · fca331fecdd7369e · 15 bricks; individually on a fixture: 10 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified · The assembly has not been run end-to-end · assemblies[32] in the JSON twin
- EfficientNet · fe58872670c9aa7a · 12 bricks; individually on a fixture: 11 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; 5 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[33] in the JSON twin
Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1905.11946") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
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
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