Papers › SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

24 Feb 2016arXiv:1602.07360archive 2025-07-28

Forrest N. Iandola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, William J. Dally, Kurt Keutzer

Recent research on deep neural networks has focused primarily on improving accuracy. For a given accuracy level, it is typically possible to identify multiple DNN architectures that achieve that accuracy level. With equivalent accuracy, smaller DNN architectures offer at least three advantages: (1) Smaller DNNs require less communication across servers during distributed training. (2) Smaller DNNs require less bandwidth to export a new model from the cloud to an autonomous car. (3) Smaller DNNs are more feasible to deploy on FPGAs and other hardware with limited memory. To provide all of these advantages, we propose a small DNN architecture called SqueezeNet. SqueezeNet achieves AlexNet-level accuracy on ImageNet with 50x fewer parameters. Additionally, with model compression techniques we are able to compress SqueezeNet to less than 0.5MB (510x smaller than AlexNet). The SqueezeNet architecture is available for download here: https://github.com/DeepScale/SqueezeNet

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

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

Code

The archive's official repositories (DT42/squeezenet_demo, DeepScale/SqueezeNet, Element-Research/dpnn, ejlb/squeezenet-chainer, haria/SqueezeNet) were not harvested; the 4 samples below come from 2 community repositories.

Syntology 4 code samples harvested from 2 repositories linked to this paper: 4 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; 4 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: community (archive-listed): 4 samples from 2 repositories, 4 ran (0 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

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

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

DT42/squeezenet_demo officialmentioned in papermentioned on GitHubGPL-3.0Syntology: not harvested report
DeepScale/SqueezeNet officialmentioned in papermentioned on GitHubpytorchBSD-2-ClauseSyntology: not harvested report
Element-Research/dpnn officialmentioned in papermentioned on GitHubtorchBSD-3-ClauseSyntology: not harvested report
ejlb/squeezenet-chainer officialmentioned in papermentioned on GitHubSyntology: not harvested report
haria/SqueezeNet officialmentioned in papermentioned on GitHubmxnetSyntology: not harvested report
AlexandruBurlacu/keras_squeezenet mentioned on GitHubMITSyntology: not harvested report
Banus/caffe-demo mentioned on GitHubcaffe2Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to You Only Look Once: Unified, Real-Time Object Detection (arXiv:1506.02640; that paper's own run record: 89 ran (of which 27 constructed an object rather than computing a result; 58 with no instrument failure: 4 honoured, 4 violated, 50 with no contract checked; 31 where Syntology's instrument failed) · 59 unverified); nothing checks that they implement this paper's method. report
Dawars/SqueezeNet-tf mentioned on GitHubtfMITSyntology: not harvested report
Goandwanderfaraway/squeezenet-mindspore mentioned on GitHubmindsporeSyntology: not harvested report
Jastot/Rodinka_Neural_Network mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Going Deeper with Convolutions (arXiv:1409.4842; that paper's own run record: 34 ran (of which 19 constructed an object rather than computing a result; 30 with no instrument failure: 1 honoured, 0 violated, 29 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
Kaido0/Brain-Tissue-Segment-Keras mentioned on GitHubtfSyntology: not harvested report
KentaItakura/Classify-crack-image-and-explain-why-using-MATLAB mentioned on GitHubBSD-3-ClauseSyntology: not harvested report
King-Otaku/Emotion_Recognition_DNN mentioned on GitHubtfSyntology: not harvested report
Mayurji/Image-Classification-PyTorch mentioned on GitHubpytorchSyntology: 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), Aggregated Residual Transformations for Deep Neural Networks (arXiv:1611.05431; that paper's own run record: 51 ran (of which 7 constructed an object rather than computing a result; 31 with no instrument failure: 0 honoured, 0 violated, 31 with no contract checked; 20 where Syntology's instrument failed) · 29 unverified) and 5 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
Mind23-2/MindCode-80 mentioned on GitHubmindsporeSyntology: not harvested report
MrRen-sdhm/Embedded_Multi_Object_Detection_CNN mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications (arXiv:1704.04861; that paper's own run record: 53 ran (of which 28 constructed an object rather than computing a result; 44 with no instrument failure: 4 honoured, 0 violated, 40 with no contract checked; 9 where Syntology's instrument failed) · 30 unverified); nothing checks that they implement this paper's method. report
Qengineering/SqueezeNet-ncnn mentioned on GitHubBSD-3-ClauseSyntology: not harvested report
adeely9/experiment_2_python3 mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
avoroshilov/tf-squeezenet mentioned on GitHubtfSyntology: not harvested report
bogireddytejareddy/3d-squeezenet mentioned on GitHubSyntology: not harvested report
brianjychan/landuse mentioned on GitHubnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
cmasch/squeezenet mentioned on GitHubtfSyntology: not harvested report
deep-learning-algorithm/LightWeightCNN mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications (arXiv:1704.04861; that paper's own run record: 53 ran (of which 28 constructed an object rather than computing a result; 44 with no instrument failure: 4 honoured, 0 violated, 40 with no contract checked; 9 where Syntology's instrument failed) · 30 unverified) and MobileNetV2: Inverted Residuals and Linear Bottlenecks (arXiv:1801.04381; that paper's own run record: 85 ran (of which 40 constructed an object rather than computing a result; 64 with no instrument failure: 8 honoured, 0 violated, 56 with no contract checked; 21 where Syntology's instrument failed) · 26 unverified); nothing checks that they implement this paper's method. report
dividiti/ck-caffe mentioned on GitHubtfSyntology: not harvested report
gsp-27/pytorch_Squeezenet mentioned on GitHubpytorchSyntology: not harvested report
jiweibo/imagenet mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
johngear/eecs504 mentioned on GitHubtfSyntology: not harvested report
lizeng614/SqueezeNet-Neural-Style-Pytorch mentioned on GitHubpytorchSyntology: not harvested report
m1lhaus/SimpleSqueezeNet mentioned on GitHubSyntology: not harvested report
marload/ConvNets-TensorFlow2 mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Going Deeper with Convolutions (arXiv:1409.4842; that paper's own run record: 34 ran (of which 19 constructed an object rather than computing a result; 30 with no instrument failure: 1 honoured, 0 violated, 29 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified), MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications (arXiv:1704.04861; that paper's own run record: 53 ran (of which 28 constructed an object rather than computing a result; 44 with no instrument failure: 4 honoured, 0 violated, 40 with no contract checked; 9 where Syntology's instrument failed) · 30 unverified) and MobileNetV2: Inverted Residuals and Linear Bottlenecks (arXiv:1801.04381; that paper's own run record: 85 ran (of which 40 constructed an object rather than computing a result; 64 with no instrument failure: 8 honoured, 0 violated, 56 with no contract checked; 21 where Syntology's instrument failed) · 26 unverified); nothing checks that they implement this paper's method. report
matteo-rizzo/fc4-pytorch mentioned on GitHubpytorchSyntology: not harvested report
maxemerling/COVID_CT mentioned on GitHubtfSyntology: not harvested report
mdsarfarazulh/fire-module mentioned on GitHubSyntology: not harvested report
milliemince/eBay-shipping-predictions mentioned on GitHubpytorchSyntology: not harvested report
modelhub-ai/squeezenet mentioned on GitHubmxnetSyntology: not harvested report
mtmd/Mobile_ConvNet mentioned on GitHubSyntology: not harvested report
osmr/imgclsmob mentioned on GitHubmxnetMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ResNeSt: Split-Attention Networks (arXiv:2004.08955; that paper's own run record: 28 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 7 where Syntology's instrument failed) · 20 unverified); nothing checks that they implement this paper's method. report
rcmalli/keras-squeezenet mentioned on GitHubtfSyntology: not harvested report
songhan/SqueezeNet-Deep-Compression mentioned on GitHubcaffe2Syntology: not harvested report
taltole/CIFAR10_SqueezeNet mentioned on GitHubSyntology: not harvested report
taltole/LiteNetwork_Image_Classification mentioned on GitHubSyntology: not harvested report
vibhu444/alexnet-squeeze-mnist mentioned on GitHubtfSyntology: not harvested report
vonclites/squeezenet mentioned on GitHubtfSyntology: not harvested report
xin-w8023/SqueezeNet-PyTorch mentioned on GitHubpytorchSyntology: not harvested report
zjZSTU/LightWeightCNN mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design (arXiv:1807.11164; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 16 unverified); nothing checks that they implement this paper's method. report
2023-MindSpore-1/ms-code-217 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code11 mindsporeSyntology: not harvested report
MS-Mind/MS-Code-02 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications (arXiv:2206.10589; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
Mind23-2/MindCode-116 mindsporeSyntology: not harvested report
PaddlePaddle/PaddleClas paddleApache-2.0Syntology: not harvested report
code-implementation1/Code8 mindsporeSyntology: not harvested report
kingcong/squeezenet mindsporeSyntology: not harvested report
mindlab-ai/mindcv mindsporeSyntology: not harvested report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
mindspore-courses/heads-on-mindspore mindsporeSyntology: not harvested report
mindspore-ecosystem/mindcv mindsporeSyntology: 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

4 samples harvested: 4 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; 4 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · our draft was wrong

Licence: 2 of the 4 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 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”. “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.

adeely9/experiment_2_python3 community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
fire_layer model.py ran · our draft was wrong no licence file found · pointer only · 8791c0396e418bc7 · report fixture: signature inp:int/0/int, s:int/0/int, e:int/0/int · returned fire · level recorded 2026-09-22
squeezenet model.py ran · our draft was wrong no licence file found · pointer only · 988c8db2810e24f8 · report fixture: signature pretrained:bool/0/bool · returned SqueezeNet · level recorded 2026-09-22
jiweibo/imagenet community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
squeezenet1_0 in 5 papers models/squeezenet.py ran · our draft was wrong MIT (permissive) · fcda65eed65cff5d · report fixture: signature pretrained:bool/0/bool · returned SqueezeNet · level recorded 2026-09-22
squeezenet1_1 in 6 papers models/squeezenet.py ran · our draft was wrong MIT (permissive) · 44349b0fe759e3a9 · report fixture: signature pretrained:bool/0/bool · returned SqueezeNet · level recorded 2026-09-22

Tasks

Image ClassificationModel CompressionNetwork Pruning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet-9 SqueezeNet + Simple Bypass Top 1 Accuracy 60.4% #1 of 1 Archive leaderboard report
Image Classification ImageNet-P SqueezeNet + Simple Bypass Top 5 Accuracy 82.5% #1 of 1 Archive leaderboard report
Network Pruning ImageNet SqueezeNet (6-bit Deep Compression) Accuracy 57.5% #16 of 16 Archive leaderboard report
Network Pruning ImageNet SqueezeNet (6-bit Deep Compression) MParams 1.24 #16 of 16 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: SqueezeNet

1x1 ConvolutionAverage PoolingConvolutionDropoutFire ModuleGlobal Average PoolingMax PoolingReLUResidual ConnectionSGD with MomentumSoftmaxSqueezeNetWeight DecayXavier Initialization

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