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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1602.07360")

Code

Syntology Ran 4 of 4 code samples harvested from 2 repositories linked to this paper; 0 have no recorded run. Of those that ran: 4 ran · our draft was wrong.

By repository: community (archive-listed): 4 samples from 2 repositories, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

DT42/squeezenet_demo officialmentioned in papermentioned on GitHubGPL-3.0 report
DeepScale/SqueezeNet officialmentioned in papermentioned on GitHubpytorchBSD-2-Clause report
Element-Research/dpnn officialmentioned in papermentioned on GitHubtorchBSD-3-Clause report
ejlb/squeezenet-chainer officialmentioned in papermentioned on GitHub report
haria/SqueezeNet officialmentioned in papermentioned on GitHubmxnet report
AlexandruBurlacu/keras_squeezenet mentioned on GitHubMIT report
Banus/caffe-demo mentioned on GitHubcaffe2 report
Dawars/SqueezeNet-tf mentioned on GitHubtfMIT report
Goandwanderfaraway/squeezenet-mindspore mentioned on GitHubmindspore report
Jastot/Rodinka_Neural_Network mentioned on GitHubtf report
Mayurji/Image-Classification-PyTorch mentioned on GitHubpytorch report
Mind23-2/MindCode-80 mentioned on GitHubmindspore report
Qengineering/SqueezeNet-ncnn mentioned on GitHubBSD-3-Clause report
adeely9/experiment_2_python3 mentioned on GitHubpytorch report
avoroshilov/tf-squeezenet mentioned on GitHubtf report
brianjychan/landuse mentioned on GitHubnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-ready report
cmasch/squeezenet mentioned on GitHubtf report
deep-learning-algorithm/LightWeightCNN mentioned on GitHubpytorch report
dividiti/ck-caffe mentioned on GitHubtf report
gsp-27/pytorch_Squeezenet mentioned on GitHubpytorch report
jiweibo/imagenet mentioned on GitHubpytorch report
johngear/eecs504 mentioned on GitHubtf report
m1lhaus/SimpleSqueezeNet mentioned on GitHub report
marload/ConvNets-TensorFlow2 mentioned on GitHubtf report
matteo-rizzo/fc4-pytorch mentioned on GitHubpytorch report
maxemerling/COVID_CT mentioned on GitHubtf report
mdsarfarazulh/fire-module mentioned on GitHub report
milliemince/eBay-shipping-predictions mentioned on GitHubpytorch report
modelhub-ai/squeezenet mentioned on GitHubmxnet report
mtmd/Mobile_ConvNet mentioned on GitHub report
osmr/imgclsmob mentioned on GitHubmxnetMIT report
rcmalli/keras-squeezenet mentioned on GitHubtf report
songhan/SqueezeNet-Deep-Compression mentioned on GitHubcaffe2 report
taltole/CIFAR10_SqueezeNet mentioned on GitHub report
vibhu444/alexnet-squeeze-mnist mentioned on GitHubtf report
vonclites/squeezenet mentioned on GitHubtf report
xin-w8023/SqueezeNet-PyTorch mentioned on GitHubpytorch report
zjZSTU/LightWeightCNN mentioned on GitHubpytorchApache-2.0 report
PaddlePaddle/PaddleClas paddleApache-2.0 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.

Code Syntology ran Syntology

4 samples harvested; 4 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, 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; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

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 from a repository marked official are listed first. 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 four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

fire_layer adeely9/experiment_2_python3/model.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 8791c0396e418bc7 · report
squeezenet adeely9/experiment_2_python3/model.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 988c8db2810e24f8 · report
squeezenet1_0 jiweibo/imagenet/models/squeezenet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · fcda65eed65cff5d · report
squeezenet1_1 jiweibo/imagenet/models/squeezenet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 44349b0fe759e3a9 · report

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