Papers › Improved Training of Wasserstein GANs

Improved Training of Wasserstein GANs

31 Mar 2017NeurIPS 2017 12arXiv:1704.00028archive 2025-07-28

Ishaan Gulrajani, Faruk Ahmed, Martin Arjovsky, Vincent Dumoulin, Aaron Courville

Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only low-quality samples or fail to converge. We find that these problems are often due to the use of weight clipping in WGAN to enforce a Lipschitz constraint on the critic, which can lead to undesired behavior. We propose an alternative to clipping weights: penalize the norm of gradient of the critic with respect to its input. Our proposed method performs better than standard WGAN and enables stable training of a wide variety of GAN architectures with almost no hyperparameter tuning, including 101-layer ResNets and language models over discrete data. We also achieve high quality generations on CIFAR-10 and LSUN bedrooms.

PaperPDFConference PDFCodeCode 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 (igul222/improved_wgan_training) was not harvested; the 49 samples below come from 28 community repositories.

Syntology 49 code samples harvested from 28 repositories linked to this paper: 27 ran (of which 10 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 0 violated, 18 with no contract checked; 8 where Syntology's instrument failed) · 22 unverified. Where Syntology's instrument failed: 6 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): 49 samples from 28 repositories, 27 ran (19 with no instrument failure; 8 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 10 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

igul222/improved_wgan_training officialmentioned in papermentioned on GitHubtfSyntology: not harvested report
Aggrathon/MtGan mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Progressive Growing of GANs for Improved Quality, Stability, and Variation (arXiv:1710.10196; that paper's own run record: 58 ran (of which 0 constructed an object rather than computing a result; 41 with no instrument failure: 6 honoured, 1 violated, 34 with no contract checked; 17 where Syntology's instrument failed) · 31 unverified); nothing checks that they implement this paper's method. report
AlexMGitHub/PokeGAN mentioned on GitHubpytorchSyntology: not harvested report
AndreasWieg/PC-PGGAN mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Progressive Growing of GANs for Improved Quality, Stability, and Variation (arXiv:1710.10196; that paper's own run record: 58 ran (of which 0 constructed an object rather than computing a result; 41 with no instrument failure: 6 honoured, 1 violated, 34 with no contract checked; 17 where Syntology's instrument failed) · 31 unverified); nothing checks that they implement this paper's method. report
CIFASIS/splitting_gan mentioned on GitHubtfSyntology: not harvested report
ChengBinJin/WGAN-GP-tensorflow mentioned on GitHubtfSyntology: not harvested report
CtrlZ1/Domain-Adaptation-Algorithms mentioned on GitHubMITSyntology: not harvested report
DevashishJoshi/Transferring-GANs-FYP mentioned on GitHubtfSyntology: not harvested report
EmilienDupont/wgan-gp mentioned on GitHubpytorchSyntology: not harvested report
JiaYunSong/Gan-for-Gem-Generation mentioned on GitHubpaddleSyntology: not harvested report
LEEPEIQIN/EDSR mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Back-Projection Networks For Super-Resolution (arXiv:1803.02735; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
LWChen20/RCAN mentioned on GitHubpytorchMITSyntology: not harvested report
LynnHo/DCGAN-LSGAN-WGAN-WGAN-GP-Tensorflow mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
Michael-T-McCann/simple-WGAN mentioned on GitHubpytorchSyntology: not harvested report
MiloszGrabski/WGAN-gp mentioned on GitHubtfSyntology: not harvested report
MinkaiXu/SobolevWassersteinGAN mentioned on GitHubtfSyntology: not harvested report
Mohanned-Elkholy/ResNet-GAN mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Spectral Normalization for Generative Adversarial Networks (arXiv:1802.05957; that paper's own run record: 25 ran (of which 9 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 1 violated, 20 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
NMADALI97/Learning-With-Wasserstein-Loss mentioned on GitHubtfSyntology: not harvested report
SimoneDutto/EDSR mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
WuChenshen/MeRGAN mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Memory Replay GANs: learning to generate images from new categories without forgetting (arXiv:1809.02058; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
YuguangTong/improved_wgan_training mentioned on GitHubtfSyntology: 2 samples, 0 ran · 2 unverified report
Yukino1010/WGAN-GP mentioned on GitHubtfSyntology: not harvested report
adler-j/bwgan mentioned on GitHubtfSyntology: not harvested report
aelnouby/Text-to-Image-Synthesis mentioned on GitHubpytorchSyntology: not harvested report
akashpalrecha/deblurring-pipeline mentioned on GitHubpytorchMITSyntology: not harvested report
akashpalrecha/superres-deformable mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Back-Projection Networks For Super-Resolution (arXiv:1803.02735; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
alectryonexamples/gan_tf2 mentioned on GitHubtfSyntology: not harvested report
amurthy1/dagan_torch mentioned on GitHubpytorchSyntology: not harvested report
apisarek/gan_advances mentioned on GitHubpytorchSyntology: not harvested report
arturml/pytorch-wgan-gp mentioned on GitHubpytorchSyntology: not harvested report
asierae/VoiceDCGAN mentioned on GitHubtfSyntology: not harvested report
bhargavajs07/Packed-Wasserstein-GAN-with-GradientPenalty-Example mentioned on GitHubpytorchSyntology: not harvested report
bhargavajs07/Packed_WGAN_GP_Example mentioned on GitHubpytorchSyntology: not harvested report
bigmao8576/WGAN-GP-Tensorflow2 mentioned on GitHubtfSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
catalyst-team/gan mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
cedricoeldorf/ConditionalStyleGAN mentioned on GitHubtfSyntology: not harvested report
changwoolee/WGAN-GP-tensorflow mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
chanshing/sobolev_gan mentioned on GitHubpytorchSyntology: not harvested report
charlescheng0117/pytorch-WGAN-GP-TTUR-CelebA mentioned on GitHubpytorchSyntology: not harvested report
cryu854/SinGAN mentioned on GitHubtfSyntology: not harvested report
cwolfbrandt/csk mentioned on GitHubtfSyntology: not harvested report
dabsdamoon/Anime-Colorization-v0.2 mentioned on GitHubmxnetSyntology: 1 sample, 0 ran · 1 unverified report
dagrate/gan_network mentioned on GitHubSyntology: not harvested report
daheyinyin/wgan_gp mentioned on GitHubmindsporeSyntology: not harvested report
divyam25/Oh-My-GAN mentioned on GitHubpytorchSyntology: not harvested report
donand/GAN_pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Generative Adversarial Networks (arXiv:1406.2661; that paper's own run record: 46 ran (of which 0 constructed an object rather than computing a result; 28 with no instrument failure: 4 honoured, 1 violated, 23 with no contract checked; 18 where Syntology's instrument failed) · 9 unverified); nothing checks that they implement this paper's method. report
dylanell/conditional-wgan mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
dylanell/wasserstein-gan mentioned on GitHubpytorchSyntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified report
eriklindernoren/Keras-GAN mentioned on GitHubpytorchSyntology: not harvested report
eriklindernoren/PyTorch-GAN mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
fangyiyu/gnpassgan mentioned on GitHubpytorchSyntology: not harvested report
franroldans/tfm-franroldan-wav2pix mentioned on GitHubpytorchSyntology: not harvested report
goldhuang/SRGAN-PyTorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
henry32144/wgan-gp-tensorflow mentioned on GitHubtfSyntology: not harvested report
itsuki8914/wgan-gp-TensorFlow mentioned on GitHubtfSyntology: 5 samples, 1 ran (1 instrument-failed) · 4 unverified report
jackyjsy/ACWGAN mentioned on GitHubpytorchSyntology: not harvested report
jesse1029/Fake-Face-Images-Detection-Tensorflow mentioned on GitHubtfGPL-3.0Syntology: not harvested report
joshpc/StyledFontGAN mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
jss367/thiskangaroodoesnotexist mentioned on GitHubtfSyntology: not harvested report
k--chow/Generative-Well-intentioned-Networks mentioned on GitHubtfSyntology: not harvested report
kangyeolk/pytorch-gan-collections mentioned on GitHubpytorchSyntology: not harvested report
kynk94/TF2-Image-Generation mentioned on GitHubtfSyntology: not harvested report
laowng/GISR mentioned on GitHubpytorchMITSyntology: not harvested report
leejaeka/PixelGAN mentioned on GitHubSyntology: not harvested report
leejaeka/incrementum mentioned on GitHubpytorchSyntology: not harvested report
lilianweng/unified-gan-tensorflow mentioned on GitHubtfSyntology: not harvested report
lonce/sonyGanFork mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
lukovnikov/improved_wgan_training mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to On the regularization of Wasserstein GANs (arXiv:1709.08894; that paper's own run record: 0 ran · 2 unverified); nothing checks that they implement this paper's method. report
lvyufeng/MindSpore-GAN mentioned on GitHubmindsporeMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ClusterGAN : Latent Space Clustering in Generative Adversarial Networks (arXiv:1809.03627; that paper's own run record: 1 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; 0 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
markmaxt/VideoSR mentioned on GitHubpytorchMITSyntology: not harvested report
marload/GANs-TensorFlow2 mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
marload/TensorFlow2-GANs mentioned on GitHubtfSyntology: not harvested report
matjazmav/fri-2021-ibb-seminar mentioned on GitHubpytorchSyntology: not harvested report
maxmax1992/WGAN_WGAN-GP mentioned on GitHubpytorchSyntology: not harvested report
mbarbetti/tf-gen-models mentioned on GitHubtfSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
mcclow12/wgan-gp-pytorch mentioned on GitHubpytorchSyntology: not harvested report
michael13162/DoodleGAN mentioned on GitHubSyntology: not harvested report
mitscha/dplc mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
nannau/DoWnGAN mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
natuan310/scale-recurrent-network-images-deblurring mentioned on GitHubtfSyntology: not harvested report
nicobernasconi/specgan mentioned on GitHubtfSyntology: not harvested report
polmonroig/faceGAN mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
qnduan/wgan-scrna mentioned on GitHubpytorchSyntology: not harvested report
raylyh/misgan-reimplementation mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
rkem1542/EDSR-pytorch mentioned on GitHubpytorchMITSyntology: not harvested report
sanghyun-son/EDSR-PyTorch mentioned on GitHubpytorchMITSyntology: not harvested report
seanmullery/iWGAN mentioned on GitHubSyntology: not harvested report
shahbuland/basic-gans mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
snow-mn/GAN-INT-CLS mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
spandan2/Wgan-GP_cats mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
t0nberryking/DCGAN256 mentioned on GitHubSyntology: not harvested report
tSchlegl/f-AnoGAN mentioned on GitHubtfSyntology: not harvested report
tensorpack/tensorpack mentioned on GitHubtfSyntology: 2 samples, 0 ran · 2 unverified report
thstkdgus35/EDSR-PyTorch mentioned on GitHubpytorchMITSyntology: not harvested report
unicredit/ganzo mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (1 instrument-failed) · 0 unverified report
wayne1123/mnist_wgan_gp mentioned on GitHubpytorchSyntology: not harvested report
wsfreund/decoder-generative-models mentioned on GitHubtfSyntology: not harvested report
yaxingwang/Transferring-GANs mentioned on GitHubtfSyntology: not harvested report
zeleni9/pytorch-wgan mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
zhusiling/EDSR mentioned on GitHubpytorchMITSyntology: not harvested report
ChristophReich1996/Dirac-GAN pytorchSyntology: 1 sample, 0 ran · 1 unverified report
ChristophReich1996/Mode_Collapse pytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
CtrlZ1/Domain-Adaptive-CodeBase MITSyntology: not harvested report
MaximeVandegar/Papers-in-100-Lines-of-Code pytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
MindSpore-paper-code-2/code3 mindsporeSyntology: not harvested report
MindSpore-paper-code-2/code400 mindsporeSyntology: not harvested report
Negus25/Mindspore-wgan_gp mindsporeSyntology: not harvested report
labmlai/annotated_deep_learning_paper_implementations pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Playing Atari with Deep Reinforcement Learning (arXiv:1312.5602; that paper's own run record: 64 ran (of which 24 constructed an object rather than computing a result; 46 with no instrument failure: 5 honoured, 0 violated, 41 with no contract checked; 18 where Syntology's instrument failed) · 53 unverified), Adam: A Method for Stochastic Optimization (arXiv:1412.6980; that paper's own run record: 27 ran (of which 7 constructed an object rather than computing a result; 23 with no instrument failure: 4 honoured, 2 violated, 17 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified), Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified) and 12 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
open-mmlab/mmgeneration pytorchSyntology: not harvested report
ydataai/ydata-synthetic tfSyntology: 2 samples, 0 ran · 2 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

49 samples harvested: 27 ran (of which 10 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 0 violated, 18 with no contract checked; 8 where Syntology's instrument failed) · 22 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 · honoured contract
6ran · our draft was wrong
2ran; the contract check could not run
18ran
22unverified

Licence: 20 of the 49 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 28 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 1 sample 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.

LynnHo/DCGAN-LSGAN-WGAN-WGAN-GP-Tensorflow community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
gradient_penalty in 23 papers tf2gan/loss.py ran; the contract check could not run (RAISES) MIT (permissive) · db554be6d2613650 · report fixture: signature f:callable/0/?, real:EagerTensor/2/float, fake:EagerTensor/2/float, mode:str/0/str · returned SymbolicTensor · level recorded 2026-09-22
SimoneDutto/EDSR community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
SpatialGradient src/loss/WMSE.py ran fingerprinted MIT (permissive) · 2b2279cf4c0b7a8a · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-24
_get_sobel_kernel_3x3 src/loss/WMSE.py ran MIT (permissive) · dbe8774da55540af · report fixture: returned Tensor · level recorded 2026-09-22
YuguangTong/improved_wgan_training community (archive-listed) 2 samples, 0 ran · 2 unverified
Discriminator in 42 papers gan_toy.py unverified MIT (permissive) · 9e3664dc1f8d79a4 · report
ReLULayer gan_toy.py unverified MIT (permissive) · 5ee58317d1dcf2be · report
bigmao8576/WGAN-GP-Tensorflow2 community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
gradient_penalty in 23 papers WGAN_GP_mask.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 86a6bb90b9961d27 · report fixture: signature x:EagerTensor/4/float, x_fake:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-22
mask_dis WGAN_GP_mask.py ran fingerprinted no licence file found · pointer only · 496ef1809697c415 · report fixture: signature x:EagerTensor/3/float · returned EagerTensor · level recorded 2026-09-24
catalyst-team/gan community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
WassersteinLossDiscriminator catalyst_gan/nn/criterion/wasserstein.py ran fingerprinted Apache-2.0 (permissive) · de7b7d62cd6320f4 · report fixture: signature fake_logits:Tensor/2/float, real_logits:Tensor/2/float · returned Tensor · level recorded 2026-09-24
changwoolee/WGAN-GP-tensorflow community (archive-listed) 1 sample, 0 ran · 1 unverified
WGAN model.py unverified MIT (permissive) · 65bfd6652f1fb02c · report
dabsdamoon/Anime-Colorization-v0.2 community (archive-listed) 1 sample, 0 ran · 1 unverified
WGAN_GP_MODEL WGAN-GP/model.py unverified no licence file found · pointer only · 1c858a9e29fdfd8d · report
dylanell/conditional-wgan community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Critic in 60 papers conditional_gan/modules.py ran no licence file found · pointer only · 0faeeae133c3fe8e · report fixture: returned Critic · level recorded 2026-09-22
dylanell/wasserstein-gan community (archive-listed) 4 samples, 2 ran (0 instrument-failed) · 2 unverified
CNN in 23 papers model/wasserstein_gan.py ran no licence file found · pointer only · 0ec8f070b436bb82 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
TransposeCNN model/wasserstein_gan.py ran fingerprinted no licence file found · pointer only · 7eb6570e1d44fd51 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
WassersteinGAN model/wasserstein_gan.py unverified no licence file found · pointer only · 4d3cbfe5a38c03da · report
tile_images in 10 papers model/wasserstein_gan.py unverified no licence file found · pointer only · 47b7024248fb9c22 · report
eriklindernoren/PyTorch-GAN community (archive-listed) 1 sample, 0 ran · 1 unverified
compute_gradient_penalty in 15 papers implementations/wgan_gp/wgan_gp.py unverified MIT (permissive) · 90d0782f63f78a1d · report
goldhuang/SRGAN-PyTorch community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
compute_gradient_penalty in 15 papers model.py ran · our draft was wrong no licence file found · pointer only · 8ad87c2d347e436c · report fixture: signature D:callable/0/?, real_samples:Tensor/4/float, fake_samples:Tensor/4/float · returned Tensor · level recorded 2026-09-22
itsuki8914/wgan-gp-TensorFlow community (archive-listed) 5 samples, 1 ran (1 instrument-failed) · 4 unverified
_conv2d model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 688218e8a8429c4e · report fixture: signature x:EagerTensor/4/float, W:EagerTensor/4/float, stride:int/0/int · returned EagerTensor · level recorded 2026-09-22
_conv_layer model.py unverified no licence file found · pointer only · 01ccd87d89d80f58 · report
_conv_variable model.py unverified no licence file found · pointer only · d3cc657acec1530d · report
_fc_variable model.py unverified no licence file found · pointer only · 4e7d156f3933749a · report
buildDiscriminator model.py unverified no licence file found · pointer only · 4e63648612d1972d · report
joshpc/StyledFontGAN community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
calculate_gradient_penalty models/loss.py ran · our draft was wrong MIT (permissive) · 86e942c662b837d6 · report fixture: returned Tensor · level recorded 2026-09-22
lonce/sonyGanFork community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
WGANGPGradientPenalty pg_gan/gradient_losses.py ran · our draft was wrong no licence file found · pointer only · 0b8b1f3450493cad · report fixture: signature input:Tensor/2/float, fake:Tensor/2/float, discriminator:callable/0/?, weight:float/0/float, backward:bool/0/bool · returned tuple · level recorded 2026-09-22
marload/GANs-TensorFlow2 community (archive-listed) 1 sample, 0 ran · 1 unverified
gradient_penalty in 23 papers WGAN-GP/WGAN-GP.py unverified Apache-2.0 (permissive) · a931b7024fe9731c · report
mbarbetti/tf-gen-models community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
GAN in 5 papers tf_gen_models/algorithms/gan/WGAN_GP.py ran MIT (permissive) · ca66ddb9527ba712 · report fixture: returned GAN · level recorded 2026-09-22
WGAN_GP tf_gen_models/algorithms/gan/WGAN_GP.py unverified MIT (permissive) · 856effeb4071ae21 · report
polmonroig/faceGAN community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
Discriminator in 42 papers models/WGAN/WGAN.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 4c30b6ec62e2cafa · report fixture: returned Discriminator · level recorded 2026-09-22
Generator in 95 papers models/WGAN/WGAN.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 5d714c6e5dfd6843 · report fixture: returned Generator · level recorded 2026-09-22
WGAN models/WGAN/WGAN.py ran Apache-2.0 (permissive) · 880e09007bbd86e5 · report fixture: returned WGAN · level recorded 2026-09-22
raylyh/misgan-reimplementation community (archive-listed) 1 sample, 0 ran · 1 unverified
gradient_penalty in 23 papers src/conv_misgan.py unverified no licence file found · pointer only · ca4a31233df66289 · report
shahbuland/basic-gans community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
Discriminator in 42 papers GP-WGAN-pytorch.py ran · metamorphic tier: deterministic no licence file found · pointer only · 3baa46870ebaf2e7 · report fixture: returned Discriminator · level recorded 2026-09-22
GP_Loss GP-WGAN-pytorch.py unverified no licence file found · pointer only · 38d85a91590ced10 · report
snow-mn/GAN-INT-CLS community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
discriminator in 10 papers models/wgan.py ran · metamorphic tier: deterministic GPL-3.0 (copyleft) · pointer only · be8c52d2d8f0b336 · report fixture: returned discriminator · level recorded 2026-09-22
spandan2/Wgan-GP_cats community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
gradient_penalty in 23 papers wgan-gp.py ran · our draft was wrong no licence file found · pointer only · e7dcf2e7ee3db27c · report fixture: returned Tensor · level recorded 2026-09-22
tensorpack/tensorpack community (archive-listed) 2 samples, 0 ran · 2 unverified
GlobalNormClip tensorpack/tfutils/gradproc.py unverified Apache-2.0 (permissive) · 50a07668fe9b3d3b · report
GradientProcessor tensorpack/tfutils/gradproc.py unverified Apache-2.0 (permissive) · bbe44bc91a190f0e · report
unicredit/ganzo community (archive-listed) 4 samples, 4 ran (1 instrument-failed) · 0 unverified
Registry in 34 papers src/loss.py ran Apache-2.0 (permissive) · 1211de6102f39af9 · report fixture: signature namespace:str/0/str, name:str/0/str, cls:callable/0/? · returned NoneType · level recorded 2026-09-24
RegistryError src/loss.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 118386abde232ad1 · report fixture: returned RegistryError · level recorded 2026-09-22
WGANGPLoss src/loss.py ran Apache-2.0 (permissive) · 6dbc8747d0edf6a9 · report fixture: returned WGANGPLoss · level recorded 2026-09-22
register in 66 papers src/loss.py ran · our draft was wrong Apache-2.0 (permissive) · 28c0e133abb7a340 · report fixture: signature namespace:str/0/str, name:str/0/str, default:bool/0/bool · returned function · level recorded 2026-09-22
zeleni9/pytorch-wgan community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
Discriminator in 42 papers models/wgan_gradient_penalty.py ran · metamorphic tier: deterministic MIT (permissive) · 1574ea170dc9603e · report fixture: returned Discriminator · level recorded 2026-09-22
WGAN_GP models/wgan_gradient_penalty.py unverified MIT (permissive) · bb30b440df15c192 · report
ChristophReich1996/Dirac-GAN community (archive-listed) 1 sample, 0 ran · 1 unverified
WassersteinGANLossGPDiscriminator dirac_gan/loss.py unverified MIT (permissive) · 02d4f9b368ee5f51 · report
ChristophReich1996/Mode_Collapse community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
WassersteinGANLossGPDiscriminator loss.py ran MIT (permissive) · 355747b27841a53b · report fixture: signature discriminator_prediction_real:Tensor/2/float, discriminator_prediction_fake:Tensor/2/float, discriminator:callable/0/?, real_samples:Tensor/2/float, fake_samples:Tensor/2/float, lambda_gradient_penalty:float/0/float · returned Tensor · level recorded 2026-09-24
MaximeVandegar/Papers-in-100-Lines-of-Code community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
sample_noise in 10 papers Improved_Training_of_Wasserstein_GANs/wgan.py ran · honoured contract MIT (permissive) · 1d4e891b5ef55d07 · report fixture: signature batch_size:int/0/int, device:device/0/? · returned Tensor · level recorded 2026-09-24
train in 522 papers Improved_Training_of_Wasserstein_GANs/wgan.py unverified MIT (permissive) · 0fdb0bd2677b553b · report
ydataai/ydata-synthetic community (archive-listed) 2 samples, 0 ran · 2 unverified
Mode src/data_synthetic/synthesizers/loss.py unverified MIT (permissive) · f71df416fb250739 · report
gradient_penalty in 23 papers src/data_synthetic/synthesizers/loss.py unverified MIT (permissive) · 317df542c2389065 · 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.

28 assemblies on this paper: 28 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

28 sibling assemblies for penalize the norm of gradient of the critic (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another. Bricks printed for 12 of 28 sibling assemblies; the other 16 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for penalize the norm of gradient of the critic (graph method: penalize the norm of gradient of the critic). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 28 siblings

  1. WGAN entry · level 0 · unverified · 65bfd6652f1fb02c

harvested Assembly for penalize the norm of gradient of the critic (graph method: penalize the norm of gradient of the critic). 2 bricks; 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) · 1 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 28 siblings

  1. GP_Loss entry · level 0 · unverified · 38d85a91590ced10
  2. Discriminator helper · level 1 · ran · 3baa46870ebaf2e7

harvested Assembly for penalize the norm of gradient of the critic (graph method: penalize the norm of gradient of the critic). 2 bricks; individually on a fixture: 0 ran · 2 unverified. The assembly has not been run end-to-end.

one of 28 siblings

  1. Discriminator entry · level 0 · unverified · 9e3664dc1f8d79a4
  2. ReLULayer helper · level 0 · unverified · 5ee58317d1dcf2be

harvested Assembly for penalize the norm of gradient of the critic (graph method: penalize the norm of gradient of the critic). 1 brick; individually on a fixture: 1 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; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 28 siblings

  1. WassersteinLossDiscriminator entry · level 1 · ran · de7b7d62cd6320f4

harvested Assembly for penalize the norm of gradient of the critic (graph method: penalize the norm of gradient of the critic). 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 28 siblings

  1. discriminator entry · level 1 · ran · be8c52d2d8f0b336

harvested Assembly for penalize the norm of gradient of the critic (graph method: penalize the norm of gradient of the critic). 2 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 28 siblings

  1. SpatialGradient entry · level 1 · ran · 2b2279cf4c0b7a8a
  2. _get_sobel_kernel_3x3 helper · level 1 · ran · dbe8774da55540af

harvested Assembly for penalize the norm of gradient of the critic (graph method: penalize the norm of gradient of the critic). 4 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 28 siblings

  1. WGAN_GP entry · level 0 · unverified · bb30b440df15c192
  2. Discriminator model · level 1 · ran · 1574ea170dc9603e
  3. Generator model · level 1 · ran · 8052df388291fe70
  4. Logger helper · level 1 · ran · 064cfba85812c032

harvested Assembly for penalize the norm of gradient of the critic (graph method: penalize the norm of gradient of the critic). 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 28 siblings

  1. gradient_penalty entry · level 1 · ran; the contract check could not run (RAISES) · 86a6bb90b9961d27
  2. mask_dis helper · level 1 · ran · 496ef1809697c415

harvested Assembly for penalize the norm of gradient of the critic (graph method: penalize the norm of gradient of the critic). 4 bricks; individually on a fixture: 4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 28 siblings

  1. WGANGPLoss entry · level 1 · ran · 6dbc8747d0edf6a9
  2. register helper · level 1 · ran · our draft was wrong · 28c0e133abb7a340
  3. Registry helper · level 1 · ran · 1211de6102f39af9
  4. RegistryError helper · level 1 · ran · 118386abde232ad1

harvested Assembly for penalize the norm of gradient of the critic (graph method: penalize the norm of gradient of the critic). 3 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 28 siblings

  1. WGAN entry · level 1 · ran · 880e09007bbd86e5
  2. Discriminator model · level 1 · ran · 4c30b6ec62e2cafa
  3. Generator model · level 1 · ran · 5d714c6e5dfd6843

harvested Assembly for penalize the norm of gradient of the critic (graph method: penalize the norm of gradient of the critic). 1 brick; 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) · 0 unverified. The assembly has not been run end-to-end.

one of 28 siblings

  1. calculate_gradient_penalty entry · level 1 · ran · our draft was wrong · 86e942c662b837d6

harvested Assembly for penalize the norm of gradient of the critic (graph method: penalize the norm of gradient of the critic). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 28 siblings

  1. gradient_penalty entry · level 0 · unverified · ca4a31233df66289
  1. WGAN_GP · 61590e75e7682e0e · 2 bricks; 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) · 1 unverified; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
  2. compute_gradient_penalty · 64ca57d14e26bb6e · 1 brick; 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) · 0 unverified · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
  3. gradient_penalty · 75c15a34d14186c7 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
  4. WassersteinGANLossGPDiscriminator · 7ee88d02d4c02954 · 1 brick; individually on a fixture: 1 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; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[15] in the JSON twin
  5. gradient_penalty · 844d73492c270c77 · 2 bricks; individually on a fixture: 0 ran · 2 unverified · The assembly has not been run end-to-end · assemblies[16] in the JSON twin
  6. buildDiscriminator · 90a99930db74e800 · 5 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) · 4 unverified · The assembly has not been run end-to-end · assemblies[17] in the JSON twin
  7. WGANGPGradientPenalty · 9795d193e3b9f290 · 1 brick; 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) · 0 unverified · The assembly has not been run end-to-end · assemblies[18] in the JSON twin
  8. Critic · b2c11bb15ff09d32 · 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 · assemblies[19] in the JSON twin
  9. gradient_penalty · bd0dfca9c94e9cca · 1 brick; 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) · 0 unverified · The assembly has not been run end-to-end · assemblies[20] in the JSON twin
  10. compute_gradient_penalty · cc2f0ed22e767676 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[21] in the JSON twin
  11. gradient_penalty · e3aa53042d5c94a8 · 1 brick; 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) · 0 unverified · The assembly has not been run end-to-end · assemblies[22] in the JSON twin
  12. train · e9f0a3fb875de49f · 2 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[23] in the JSON twin
  13. GlobalNormClip · eb345261e384fab6 · 2 bricks; individually on a fixture: 0 ran · 2 unverified · The assembly has not been run end-to-end · assemblies[24] in the JSON twin
  14. WGAN_GP_MODEL · ef0bebb0f7bb5a1c · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[25] in the JSON twin
  15. WassersteinGANLossGPDiscriminator · fa10c48068db4208 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[26] in the JSON twin
  16. WassersteinGAN · faa06e726ff1c76e · 4 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[27] in the JSON twin

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="1704.00028") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Conditional Image GenerationImage GenerationSynthetic Data Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Conditional Image Generation CIFAR-10 WGAN-GP Inception score 8.67 #18 of 25 Archive leaderboard report
Image Generation CAT 256x256 WGAN-GP FID 155.46 #3 of 3 Archive leaderboard report
Image Generation CIFAR-10 WGAN-GP FID 29.3 #68 of 78 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: WGAN GP, WGAN-GP Loss

1x1 ConvolutionAdamAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationLayer NormalizationMax PoolingRMSPropReLUResidual BlockResidual ConnectionWGAN GPWGAN-GP Loss

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