Papers › Deep Networks with Stochastic Depth

Deep Networks with Stochastic Depth

30 Mar 2016arXiv:1603.09382archive 2025-07-28

Gao Huang, Yu Sun, Zhuang Liu, Daniel Sedra, Kilian Weinberger

Very deep convolutional networks with hundreds of layers have led to significant reductions in error on competitive benchmarks. Although the unmatched expressiveness of the many layers can be highly desirable at test time, training very deep networks comes with its own set of challenges. The gradients can vanish, the forward flow often diminishes, and the training time can be painfully slow. To address these problems, we propose stochastic depth, a training procedure that enables the seemingly contradictory setup to train short networks and use deep networks at test time. We start with very deep networks but during training, for each mini-batch, randomly drop a subset of layers and bypass them with the identity function. This simple approach complements the recent success of residual networks. It reduces training time substantially and improves the test error significantly on almost all data sets that we used for evaluation. With stochastic depth we can increase the depth of residual networks even beyond 1200 layers and still yield meaningful improvements in test error (4.91% on CIFAR-10).

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="1603.09382")

Code

Syntology Ran 8 of 9 code samples harvested from 8 repositories linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · violated contract; 1 ran · fixture could not drive it; 6 ran with no contract checked.

By repository: community (archive-listed): 9 samples from 8 repositories, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

yueatsprograms/Stochastic_Depth officialmentioned in papermentioned on GitHubtorch report
DarshanDeshpande/jax-models mentioned on GitHubjax report
MiuGod0126/Stochastic-Depth-Paddle mentioned on GitHubpaddle report
andreasveit/densenet-pytorch mentioned on GitHubpytorch report
dblN/stochastic_depth_keras mentioned on GitHubtfMIT report
felixgwu/img_classification_pk_pytorch mentioned on GitHubpytorch report
jiweeo/pytorch-stochastic-depth mentioned on GitHubpytorch report
nachiket273/pytorch_resnet_rs mentioned on GitHubpytorch report
osmr/imgclsmob mentioned on GitHubmxnetMIT report
rwightman/pytorch-image-models mentioned on GitHubpytorch report
ry/tensorflow-resnet mentioned on GitHubtf report
zpc-666/Paddle-Stochastic-Depth-ResNet110 mentioned on GitHubpaddleApache-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

9 samples harvested; 8 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · violated contract
1ran · fixture could not drive it
6ran
1unverified

Licence: 2 of the 9 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 8 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.

BasicBlock andreasveit/densenet-pytorch/densenet.py community (archive-listed) ran fingerprinted BSD-3-Clause (permissive) · 0a1bd35d26d9935a · report
BasicBlock jiweeo/pytorch-stochastic-depth/models/base.py community (archive-listed) ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 0c07f75568d64e8b · report
BasicBlockWithDeathRate felixgwu/img_classification_pk_pytorch/models/resnet.py community (archive-listed) ran · metamorphic tier: deterministic no licence file found · pointer only · dc11082963595174 · report
DropPath nachiket273/pytorch_resnet_rs/model/base.py community (archive-listed) ran fingerprinted MIT (permissive) · bd6c794dd7be5c10 · report
DropPath DarshanDeshpande/jax-models/jax_models/layers/drop.py community (archive-listed) ran Apache-2.0 (permissive) · 7e0f6db857f04fb0 · report
StoDepth_BasicBlock shamangary/Pytorch-Stochastic-Depth-Resnet/TYY_stodepth_lineardecay.py community (archive-listed) ran fingerprinted no licence file found · pointer only · 53cd9fb110b96e3c · report
stochastic_depth pytorch/vision/torchvision/ops/stochastic_depth.py community (archive-listed) ran · fixture could not drive it BSD-3-Clause (permissive) · 23e54ee64c53fb22 · report
str2bool zpc-666/Paddle-Stochastic-Depth-ResNet110/config/config.py community (archive-listed) ran · violated contract Apache-2.0 (permissive) · 7c508037b40522af · report
_log_api_usage_once pytorch/vision/torchvision/ops/stochastic_depth.py community (archive-listed) unverified BSD-3-Clause (permissive) · ce9d2f65bde2578c · report

Tasks

Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification CIFAR-10 Stochastic Depth Percentage correct 94.77 #149 of 265 Archive leaderboard report
Image Classification CIFAR-100 Stochastic Depth Percentage correct 75.42 #153 of 211 Archive leaderboard report
Image Classification SVHN Stochastic Depth Percentage error 1.75 #20 of 62 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: Stochastic Depth

Stochastic Depth

1 archive method tag without a method page not shown.

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