{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-networks-with-stochastic-depth","title":"Deep Networks with Stochastic Depth","arxiv_id":"1603.09382","date":"2016-03-30","proceeding":null,"authors":["Gao Huang","Yu Sun","Zhuang Liu","Daniel Sedra","Kilian Weinberger"],"abstract":"Very deep convolutional networks with hundreds of layers have led to\nsignificant reductions in error on competitive benchmarks. Although the\nunmatched expressiveness of the many layers can be highly desirable at test\ntime, training very deep networks comes with its own set of challenges. The\ngradients can vanish, the forward flow often diminishes, and the training time\ncan be painfully slow. To address these problems, we propose stochastic depth,\na training procedure that enables the seemingly contradictory setup to train\nshort networks and use deep networks at test time. We start with very deep\nnetworks but during training, for each mini-batch, randomly drop a subset of\nlayers and bypass them with the identity function. This simple approach\ncomplements the recent success of residual networks. It reduces training time\nsubstantially and improves the test error significantly on almost all data sets\nthat we used for evaluation. With stochastic depth we can increase the depth of\nresidual networks even beyond 1200 layers and still yield meaningful\nimprovements in test error (4.91% on CIFAR-10).","url_abs":"http://arxiv.org/abs/1603.09382v3","url_pdf":"http://arxiv.org/pdf/1603.09382v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-networks-with-stochastic-depth","repo_url":"https://github.com/yueatsprograms/Stochastic_Depth","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok"}},{"paper_slug":"deep-networks-with-stochastic-depth","repo_url":"https://github.com/Anderies/stochastic-constant-pruninglayers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deep-networks-with-stochastic-depth","repo_url":"https://github.com/DarshanDeshpande/jax-models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"deep-networks-with-stochastic-depth","repo_url":"https://github.com/MiuGod0126/Stochastic-Depth-Paddle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok"}},{"paper_slug":"deep-networks-with-stochastic-depth","repo_url":"https://github.com/andreasveit/densenet-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-networks-with-stochastic-depth","repo_url":"https://github.com/dblN/stochastic_depth_keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-networks-with-stochastic-depth","repo_url":"https://github.com/felixgwu/img_classification_pk_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-networks-with-stochastic-depth","repo_url":"https://github.com/jiweeo/pytorch-stochastic-depth","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-networks-with-stochastic-depth","repo_url":"https://github.com/nachiket273/pytorch_resnet_rs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-networks-with-stochastic-depth","repo_url":"https://github.com/osmr/imgclsmob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-networks-with-stochastic-depth","repo_url":"https://github.com/rwightman/pytorch-image-models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-networks-with-stochastic-depth","repo_url":"https://github.com/ry/tensorflow-resnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-networks-with-stochastic-depth","repo_url":"https://github.com/shamangary/Pytorch-Stochastic-Depth-Resnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-networks-with-stochastic-depth","repo_url":"https://github.com/zpc-666/Paddle-Stochastic-Depth-ResNet110","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"deep-networks-with-stochastic-depth","repo_url":"https://github.com/pytorch/vision","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[{"method_slug":null,"method_name":null},{"method_slug":"stochastic-depth","method_name":"Stochastic Depth"}],"datasets_introduced":[],"methods_introduced":[{"slug":"stochastic-depth","name":"Stochastic Depth","full_name":"Stochastic Depth"}],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"Stochastic Depth","rank_in_archive_order":149,"of":265,"metrics":{"Percentage correct":"94.77"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"Stochastic Depth","rank_in_archive_order":153,"of":211,"metrics":{"Percentage correct":"75.42"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-svhn","task":"Image Classification","dataset":"SVHN","model":"Stochastic Depth","rank_in_archive_order":20,"of":62,"metrics":{"Percentage error":"1.75"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1603.09382","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1603.09382"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rwightman/pytorch-image-models","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pytorch/vision","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zpc-666/Paddle-Stochastic-Depth-ResNet110","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MiuGod0126/Stochastic-Depth-Paddle","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/andreasveit/densenet-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/felixgwu/img_classification_pk_pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shamangary/Pytorch-Stochastic-Depth-Resnet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dblN/stochastic_depth_keras","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Anderies/stochastic-constant-pruninglayers","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/osmr/imgclsmob","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DarshanDeshpande/jax-models","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jiweeo/pytorch-stochastic-depth","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/yueatsprograms/Stochastic_Depth","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nachiket273/pytorch_resnet_rs","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ry/tensorflow-resnet","reach":null}],"summary":{"ran":6,"ran_fixture":1,"ran_violates":1,"unverified":1},"by_repo_kind":{"listed":{"samples":9,"ran":8,"repositories":8}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"0a1bd35d26d9935a","entry":"BasicBlock","repo":"andreasveit/densenet-pytorch","repo_kind":"listed","path":"densenet.py","file_url":"https://github.com/andreasveit/densenet-pytorch/blob/HEAD/densenet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"0a1bd35d26d9935a"}},{"code_sha256_prefix":"0c07f75568d64e8b","entry":"BasicBlock","repo":"jiweeo/pytorch-stochastic-depth","repo_kind":"listed","path":"models/base.py","file_url":"https://github.com/jiweeo/pytorch-stochastic-depth/blob/HEAD/models/base.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0c07f75568d64e8b"}},{"code_sha256_prefix":"dc11082963595174","entry":"BasicBlockWithDeathRate","repo":"felixgwu/img_classification_pk_pytorch","repo_kind":"listed","path":"models/resnet.py","file_url":"https://github.com/felixgwu/img_classification_pk_pytorch/blob/HEAD/models/resnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dc11082963595174"}},{"code_sha256_prefix":"bd6c794dd7be5c10","entry":"DropPath","repo":"nachiket273/pytorch_resnet_rs","repo_kind":"listed","path":"model/base.py","file_url":"https://github.com/nachiket273/pytorch_resnet_rs/blob/HEAD/model/base.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd6c794dd7be5c10"}},{"code_sha256_prefix":"7e0f6db857f04fb0","entry":"DropPath","repo":"DarshanDeshpande/jax-models","repo_kind":"listed","path":"jax_models/layers/drop.py","file_url":"https://github.com/DarshanDeshpande/jax-models/blob/HEAD/jax_models/layers/drop.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7e0f6db857f04fb0"}},{"code_sha256_prefix":"53cd9fb110b96e3c","entry":"StoDepth_BasicBlock","repo":"shamangary/Pytorch-Stochastic-Depth-Resnet","repo_kind":"listed","path":"TYY_stodepth_lineardecay.py","file_url":"https://github.com/shamangary/Pytorch-Stochastic-Depth-Resnet/blob/HEAD/TYY_stodepth_lineardecay.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"53cd9fb110b96e3c"}},{"code_sha256_prefix":"23e54ee64c53fb22","entry":"stochastic_depth","repo":"pytorch/vision","repo_kind":"listed","path":"torchvision/ops/stochastic_depth.py","file_url":"https://github.com/pytorch/vision/blob/HEAD/torchvision/ops/stochastic_depth.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"23e54ee64c53fb22"}},{"code_sha256_prefix":"7c508037b40522af","entry":"str2bool","repo":"zpc-666/Paddle-Stochastic-Depth-ResNet110","repo_kind":"listed","path":"config/config.py","file_url":"https://github.com/zpc-666/Paddle-Stochastic-Depth-ResNet110/blob/HEAD/config/config.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7c508037b40522af"}},{"code_sha256_prefix":"ce9d2f65bde2578c","entry":"_log_api_usage_once","repo":"pytorch/vision","repo_kind":"listed","path":"torchvision/ops/stochastic_depth.py","file_url":"https://github.com/pytorch/vision/blob/HEAD/torchvision/ops/stochastic_depth.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"ce9d2f65bde2578c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}