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 ranMethod as code

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

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

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

Code

The archive's official repository (yueatsprograms/Stochastic_Depth) was not harvested; the 9 samples below come from 8 community repositories.

Syntology 9 code samples harvested from 8 repositories linked to this paper: 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. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 9 samples from 8 repositories, 8 ran (7 with no instrument failure; 1 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 3 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. 1 of the 8 samples that ran has no recorded date.

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

yueatsprograms/Stochastic_Depth officialmentioned in papermentioned on GitHubtorchSyntology: not harvested report
Anderies/stochastic-constant-pruninglayers mentioned on GitHubpytorchSyntology: not harvested report
DarshanDeshpande/jax-models mentioned on GitHubjaxSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
MiuGod0126/Stochastic-Depth-Paddle mentioned on GitHubpaddleSyntology: not harvested report
andreasveit/densenet-pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
dblN/stochastic_depth_keras mentioned on GitHubtfMITSyntology: not harvested report
felixgwu/img_classification_pk_pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
jiweeo/pytorch-stochastic-depth mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
nachiket273/pytorch_resnet_rs mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified 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
rwightman/pytorch-image-models mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights (arXiv:2006.08217; that paper's own run record: 4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
ry/tensorflow-resnet mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to 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); nothing checks that they implement this paper's method. report
shamangary/Pytorch-Stochastic-Depth-Resnet mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
zpc-666/Paddle-Stochastic-Depth-ResNet110 mentioned on GitHubpaddleApache-2.0Syntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
pytorch/vision pytorchSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified 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

9 samples harvested: 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. “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.

1ran · violated contract
1ran; the contract check could not run
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; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 3 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.

DarshanDeshpande/jax-models community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
DropPath in 75 papers
census: 17 implementations from 17 papers, 8 distinct outputs across 3 buckets, one shared input per bucket
jax_models/layers/drop.py ran Apache-2.0 (permissive) · 7e0f6db857f04fb0 · report fixture: returned DropPath · level recorded 2026-09-22
andreasveit/densenet-pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
BasicBlock in 126 papers
census: 6 implementations from 6 papers, 5 distinct outputs on one shared input
densenet.py ran fingerprinted BSD-3-Clause (permissive) · 0a1bd35d26d9935a · report fixture: returned BasicBlock · level recorded 2026-09-22
felixgwu/img_classification_pk_pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
BasicBlockWithDeathRate models/resnet.py ran · metamorphic tier: deterministic no licence file found · pointer only · dc11082963595174 · report fixture: returned BasicBlockWithDeathRate · level recorded 2026-09-22
jiweeo/pytorch-stochastic-depth community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
BasicBlock in 126 papers
census: 6 implementations from 6 papers, 5 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
models/base.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 0c07f75568d64e8b · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
nachiket273/pytorch_resnet_rs community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
DropPath in 75 papers
census: 17 implementations from 17 papers, 8 distinct outputs across 3 buckets, one shared input per bucket
model/base.py ran fingerprinted MIT (permissive) · bd6c794dd7be5c10 · report fixture: returned DropPath · level recorded 2026-09-22
shamangary/Pytorch-Stochastic-Depth-Resnet community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
StoDepth_BasicBlock TYY_stodepth_lineardecay.py ran fingerprinted no licence file found · pointer only · 53cd9fb110b96e3c · report fixture: returned StoDepth_BasicBlock · level recorded 2026-09-22
zpc-666/Paddle-Stochastic-Depth-ResNet110 community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
str2bool in 533 papers config/config.py ran · violated contract Apache-2.0 (permissive) · 7c508037b40522af · report fixture: signature v:str/0/str · returned bool · level recorded, date not recorded
pytorch/vision community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
stochastic_depth in 8 papers torchvision/ops/stochastic_depth.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant BSD-3-Clause (permissive) · 23e54ee64c53fb22 · 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
_log_api_usage_once in 8 papers torchvision/ops/stochastic_depth.py unverified BSD-3-Clause (permissive) · ce9d2f65bde2578c · report

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.

7 assemblies on this paper: 7 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

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

harvested Assembly for stochastic depth (graph method: stochastic depth). 2 bricks; 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) · 1 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. stochastic_depth entry · level 1 · ran; the contract check could not run (RAISES) · 23e54ee64c53fb22
  2. _log_api_usage_once helper · level 0 · unverified · ce9d2f65bde2578c

harvested Assembly for stochastic depth (graph method: stochastic depth). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 7 siblings

  1. BasicBlockWithDeathRate entry · level 1 · ran · dc11082963595174

harvested Assembly for stochastic depth (graph method: stochastic depth). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 7 siblings

  1. DropPath entry · level 1 · ran · bd6c794dd7be5c10

harvested Assembly for stochastic depth (graph method: stochastic depth). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 7 siblings

  1. DropPath entry · level 1 · ran · 7e0f6db857f04fb0

harvested Assembly for stochastic depth (graph method: stochastic depth). 2 bricks; individually on a fixture: 2 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; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. StoDepth_BasicBlock entry · level 1 · ran · 53cd9fb110b96e3c
  2. conv3x3 helper · level 1 · ran · our draft was wrong · fac5364e2f53c6db

harvested Assembly for stochastic depth (graph method: stochastic depth). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 7 siblings

  1. BasicBlock entry · level 1 · ran · 0a1bd35d26d9935a

harvested Assembly for stochastic depth (graph method: stochastic depth). 2 bricks; individually on a fixture: 2 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; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. BasicBlock entry · level 1 · ran · 0c07f75568d64e8b
  2. conv3x3 helper · level 1 · ran · our draft was wrong · fac5364e2f53c6db

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="1603.09382") returns these assemblies with each brick's role and wiring (how to connect).

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