Papers › Designing Network Design Spaces
Designing Network Design Spaces
Ilija Radosavovic, Raj Prateek Kosaraju, Ross Girshick, Kaiming He, Piotr Dollár
In this work, we present a new network design paradigm. Our goal is to help advance the understanding of network design and discover design principles that generalize across settings. Instead of focusing on designing individual network instances, we design network design spaces that parametrize populations of networks. The overall process is analogous to classic manual design of networks, but elevated to the design space level. Using our methodology we explore the structure aspect of network design and arrive at a low-dimensional design space consisting of simple, regular networks that we call RegNet. The core insight of the RegNet parametrization is surprisingly simple: widths and depths of good networks can be explained by a quantized linear function. We analyze the RegNet design space and arrive at interesting findings that do not match the current practice of network design. The RegNet design space provides simple and fast networks that work well across a wide range of flop regimes. Under comparable training settings and flops, the RegNet models outperform the popular EfficientNet models while being up to 5x faster on GPUs.
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):
get_harvested_code_for_paper(arxiv_id="2003.13678")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2003.13678", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2003.13678")
Code
No sample from the archive's official repository (facebookresearch/pycls) is linked to this paper; the 53 samples below come from 5 community repositories. Syntology harvested code from facebookresearch/pycls for 3 other papers.
facebookresearch/pycls: 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), 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 EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (arXiv:1905.11946; that paper's own run record: 198 ran (of which 73 constructed an object rather than computing a result; 157 with no instrument failure: 26 honoured, 2 violated, 129 with no contract checked; 41 where Syntology's instrument failed) · 104 unverified); nothing checks that they implement this paper's method.
Syntology 53 code samples harvested from 5 repositories linked to this paper: 48 ran (of which 0 constructed an object rather than computing a result; 41 with no instrument failure: 4 honoured, 0 violated, 37 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: community (archive-listed): 53 samples from 5 repositories, 48 ran (41 with no instrument failure; 7 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 15 of its repositories that Syntology harvested for other papers:
- facebookresearch/pycls, official repository: harvested for 3 other papers, listed under the repository
- Deci-AI/super-gradients, community (archive-listed): harvested for 4 other papers, listed under the repository
- facebookresearch/vissl, community (archive-listed): harvested for 4 other papers, listed under the repository
- hsd1503/resnet1d, community (archive-listed): harvested for 2 other papers, listed under the repository
- james77777778/keras-image-models, community (archive-listed): harvested for another paper, listed under the repository
- osmr/imgclsmob, community (archive-listed): harvested for another paper, listed under the repository
- rwightman/pytorch-image-models, community (archive-listed): harvested for another paper, listed under the repository
- tuggeluk/pycls, community (archive-listed): harvested for 2 other papers, listed under the repository
- leondgarse/keras_cv_attention_models, community (archive-listed): harvested for another paper, listed under the repository
- megvii-research/basecls, community (archive-listed): harvested for another paper, listed under the repository
- mindspore-ai/models, community (archive-listed): harvested for another paper, listed under the repository
- open-mmlab/mmclassification, community (archive-listed): harvested for another paper, listed under the repository
- open-mmlab/mmdetection, community (archive-listed): harvested for another paper, listed under the repository
- open-mmlab/mmdetection3d, community (archive-listed): harvested for another paper, listed under the repository
- pytorch/vision, community (archive-listed): harvested for 10 other papers, listed under the repository
Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 48 samples that ran have no recorded date.
26 repositories listed; official and paper-mentioned ones first.
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
53 samples harvested: 48 ran (of which 0 constructed an object rather than computing a result; 41 with no instrument failure: 4 honoured, 0 violated, 37 with no contract checked; 7 where Syntology's instrument failed) · 5 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.
Licence: 7 of the 53 samples are pointer only, meaning Syntology does not serve that copy's text. For 7 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from 5 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. 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.
c804dfc430391ebb · report
fixture: signature basic_dir:str/0/str · returned str · level recorded 2026-09-24 4f00c5e336d1fab1 · report
fixture: signature img:Tensor/3/float, mean:Tensor/1/float, std:Tensor/1/float · returned Tensor · level recorded 2026-09-24 984a028631f19887 · report
fixture: signature log_dir:str/0/str · returned str · level recorded 2026-09-24 d2c4ab4309330f86 · report
fixture: signature dataset:SimpleDataset/0/? · returned tuple · level recorded 2026-09-24 71ed90ac72db0a23 · report
fixture: signature log_dir:str/0/str · returned str · level recorded 2026-09-24 d401541fae28c8df · report
fixture: signature img:ndarray/3/float, p:float/0/float, order:str/0/str · returned ndarray · level recorded 2026-09-24 de7df4cd7f7cb239 · report
fixture: signature cfg_path:str/0/str · returned dict · level recorded 2026-09-24 0fe8c6f466ab4c72 · report
fixture: signature checkpoint_file:str/0/str, gpu_num:int/0/int, model:callable/0/?, optimizer:SGD/0/? · returned int · level recorded 2026-09-24 086239779f8ee4d5 · report
fixture: signature filepath:str/0/str · returned ndarray · level recorded 2026-09-24 4cc9b1db1b0d55b6 · report
fixture: signature epoch_i:int/0/int, base_lr:float/0/float, max_epoch:int/0/int · returned float64 · level recorded 2026-09-24 d37a1ce2bc6180e6 · report
fixture: signature epoch_i:int/0/int, base_lr:float/0/float, gamma:float/0/float · returned float · level recorded 2026-09-24 cb66896e95a24c22 · report
fixture: signature epoch_i:int/0/int, base_lr:float/0/float, milestone:list/1/int, lr_mult:float/0/float · returned float · level recorded 2026-09-24 a0cc9cf5cccaf75a · report
fixture: signature model:callable/0/?, optimizer:SGD/0/?, epoch:int/0/int, gpu_num:int/0/int, checkpoint_file:str/0/str · returned str · level recorded 2026-09-24 94d1acf6801b9a00 · report
fixture: signature img:ndarray/3/float, pad_size:int/0/int · returned ndarray · level recorded 2026-09-24 census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket utils/evalutator.py unverified MIT (permissive) ·
26219ca9c20a331d · report
census: 6 implementations from 6 papers, 5 distinct outputs on one shared input model/anynet.py ran MIT (permissive) ·
2f49808e608b8c96 · report
fixture: signature args:NoneType/0/?, x:KerasTensor/0/float, features:int/0/int, strides:int/0/int, name:str/0/str · returned KerasTensor · level recorded 2026-09-24 census: 6 implementations from 5 papers, 6 distinct outputs across 2 buckets, one shared input per bucket model/anynet.py ran MIT (permissive) ·
2fc21a3ff370f732 · report
fixture: signature args:NoneType/0/?, x:EagerTensor/4/float, features:int/0/int, strides:int/0/int, name:str/0/str · returned EagerTensor · level recorded 2026-09-24 e4fa2e354a4ccd53 · report
fixture: signature args:Args/0/?, x:EagerTensor/4/float, features:int/0/int, strides:int/0/int, name:str/0/str · returned EagerTensor · level recorded 2026-09-24 f3b3cc6d74abcfcb · report
fixture: signature filepath:str/0/str, monitor:str/0/str, verbose:int/0/int, mode:str/0/str, save_best_only:bool/0/bool, save_weights_only:bool/0/bool · returned ModelCheckpoint · level recorded 2026-09-24 300864db1e3cdd90 · report
fixture: signature filename:str/0/str, separator:str/0/str, append:bool/0/bool · returned CSVLogger · level recorded 2026-09-24 129adedbc3f353c4 · report
fixture: signature args:Namespace/0/? · returned Namespace · level recorded 2026-09-24 733d2079c07e80b7 · report
fixture: signature path:str/0/str, whole_cfg:dict/0/?, new_cfg:dict/0/? · returned bool · level recorded 2026-09-24 3b4634faa337b07b · report
fixture: signature cx:dict/0/?, w_in:int/0/int · returned dict · level recorded 2026-09-24 a2c61cf1be6f496a · report
fixture: signature cx:dict/0/?, w_in:int/0/int, w_out:int/0/int, k:int/0/int, s:int/0/int, p:int/0/int, g:int/0/int, b:bool/0/bool · returned dict · level recorded 2026-09-24 a7c0f04b031c05be · report
fixture: signature cx:dict/0/?, k:int/0/int, s:int/0/int, p:int/0/int · returned dict · level recorded 2026-09-24 e9cdcc13fe49820c · report
fixture: signature name:str/0/str · returned Logger · level recorded 2026-09-24 4d3ce1e2a3d645cb · report
fixture: signature args:SimpleNamespace/0/? · returned tuple · level recorded 2026-09-24 113ee8ba2c42d3b4 · report
fixture: signature cfg:dict/0/? · returned tuple · level recorded 2026-09-24 efceaef7f38bd7b9 · report
fixture: signature args:Args/0/? · returned tuple · level recorded 2026-09-24 census: 3 implementations from 7 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32 models/backbone/shufflenet_backbone.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only ·
b9da06d4f527dd6c · report
fixture: signature x:Tensor/4/float, groups:int/0/int · returned Tensor · level recorded 2026-09-22 d9def42110729a85 · report
fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded 160bb14bd76201b4 · report
fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned Conv2d · level recorded, date not recorded 7186655759897af6 · report
fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:int/0/int, groups:int/0/int · returned Sequential · level recorded 2026-09-22 c0ebab789418c9e4 · report
fixture: signature i:int/0/int, inplace:bool/0/bool · returned type · level recorded 2026-09-24 census: 9 implementations from 7 papers, 4 distinct outputs across 2 buckets, one shared input per bucket models/backbone/efficientnet_backbone.py ran MIT (permissive) ·
45eada2b88e70500 · report
fixture: signature inputs:Tensor/4/float, p:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-25 73876e077d3acdf5 · report
fixture: signature kernel_size:int/0/int, stride:int/0/int, dilation:int/0/int · returned int · level recorded 2026-09-22 54e11386110ff042 · report
fixture: signature x:int/0/int, k:int/0/int, s:int/0/int, d:int/0/int · returned int · level recorded 2026-09-22 11d3877a0ccf3ee3 · report
fixture: signature fpn_level:int/0/int, num_anchors:int/0/int, num_classes:int/0/int, fea_channel:int/0/int, dis_channel:int/0/int, conv_block:callable/0/? · returned tuple · level recorded 2026-09-24 fea14f1f6c2644bf · report
fixture: signature filters:int/0/int, global_params:GlobalParams/0/? · returned int · level recorded 2026-09-25 f93cb693ac8bb537 · report
fixture: signature repeats:int/0/int, global_params:GlobalParams/0/? · returned int · level recorded 2026-09-22 census: 37 implementations from 54 papers, 4 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 models/backbone/swin_backbone.py ran; the contract check could not run (RAISES) MIT (permissive) ·
af8aefa30bd76920 · report
fixture: signature tensor:Tensor/2/float, mean:float/0/float, std:float/0/float, a:float/0/float, b:float/0/float · returned Tensor · level recorded 2026-09-22 census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket models/backbone/swin_backbone.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) here; the stored copy is pointer only ·
f6b2d702fc756d64 · report
fixture: signature x:Tensor/4/float, window_size:int/0/int · returned Tensor · level recorded 2026-09-22 7b0d02f75bf6b439 · report
fixture: signature windows:Tensor/4/float, window_size:int/0/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded 2026-09-22 census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket utils.py ran MIT (permissive) ·
f04c9abd65570251 · report
fixture: signature output:Tensor/2/float, target:Tensor/1/int, topk:tuple/1/int · returned list · level recorded 2026-09-24 9ae24bb873bceeb8 · report
fixture: signature initial_width:int/0/int, width_slope:float/0/float, quantilize:int/0/int, width_m:float/0/float, depth:int/0/int, bottleneck_ratio:int/0/int, group_width:int/0/int · returned tuple · level recorded 2026-09-24 7337f1f5ff01dcd0 · report
fixture: signature optimizer:SGD/0/? · returned float · level recorded, date not recorded 776c7e0f77f8b8e1 · report
fixture: signature ws:list/1/int, bms:list/1/float, gs:list/1/int · returned tuple · level recorded 2026-09-25 cf37365adf0e1e42 · report
fixture: signature ws:list/1/int, rs:list/1/int · returned tuple · level recorded 2026-09-25 a7f56f01db1812a0 · report
fixture: signature f:float/0/float, q:float/0/float · returned int · level recorded 2026-09-25 Tasks
Results from the paper archive 2025-07-28
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: RegNetX, RegNetY
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