Papers › A Large-Scale Study on Regularization and Normalization in GANs

A Large-Scale Study on Regularization and Normalization in GANs

12 Jul 2018ICLR 2019 5arXiv:1807.04720archive 2025-07-28

Karol Kurach, Mario Lucic, Xiaohua Zhai, Marcin Michalski, Sylvain Gelly

Generative adversarial networks (GANs) are a class of deep generative models which aim to learn a target distribution in an unsupervised fashion. While they were successfully applied to many problems, training a GAN is a notoriously challenging task and requires a significant number of hyperparameter tuning, neural architecture engineering, and a non-trivial amount of "tricks". The success in many practical applications coupled with the lack of a measure to quantify the failure modes of GANs resulted in a plethora of proposed losses, regularization and normalization schemes, as well as neural architectures. In this work we take a sober view of the current state of GANs from a practical perspective. We discuss and evaluate common pitfalls and reproducibility issues, open-source our code on Github, and provide pre-trained models on TensorFlow Hub.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1807.04720")

Code

Syntology Ran 2 of 15 code samples harvested from 2 repositories linked to this paper; 13 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: community (archive-listed): 14 samples from 2 repositories, 1 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

google/compare_gan officialmentioned in papermentioned on GitHubtfApache-2.0 report
adrienchaton/BERGAN mentioned on GitHubpytorch report
blessengeorge/compare_gan mentioned on GitHubtf report
w510056105/DeepLearning mentioned on GitHubtfApache-2.0 report
xiao7199/compare_gan mentioned on GitHubtfApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

15 samples harvested; 2 ran; 0 honoured the contract we drafted; 13 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
1ran · fixture could not drive it
13unverified

Licence: 12 of the 15 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 2 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

prd_to_max_f_beta_pair xiao7199/compare_gan/compare_gan/src/prd_score.py community (archive-listed) ran · fixture could not drive it Apache-2.0 recorded; this copy not marked cleared · pointer only · 5adbefd0ebfa3e5e · report
FSpecialGauss xiao7199/compare_gan/compare_gan/src/image_similarity.py community (archive-listed) unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 980a02883b50afd3 · report
MultiscaleSSIM xiao7199/compare_gan/compare_gan/src/image_similarity.py community (archive-listed) unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 91e52735a9a4ef77 · report
VerifyCompatibleImageShapes xiao7199/compare_gan/compare_gan/src/image_similarity.py community (archive-listed) unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · caf55addd2a79ff2 · report
analyze_jacobian xiao7199/compare_gan/compare_gan/src/jacobian_conditioning.py community (archive-listed) unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · df48993045f1fb99 · report
compute_jacobian xiao7199/compare_gan/compare_gan/src/jacobian_conditioning.py community (archive-listed) unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · d088682165b591d6 · report
compute_prd xiao7199/compare_gan/compare_gan/src/prd_score.py community (archive-listed) unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 91b26d9e0c4aab9b · report
compute_prd_from_embedding xiao7199/compare_gan/compare_gan/src/prd_score.py community (archive-listed) unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 0fd2f6b430b748c0 · report
create_image_lists w510056105/DeepLearning/Projects/TransferLearning/InceptionV3_TransferLearning.py community (archive-listed) unverified Apache-2.0 (permissive) · af5a5c1e5be254a9 · report
get_bottleneck_path w510056105/DeepLearning/Projects/TransferLearning/InceptionV3_TransferLearning.py community (archive-listed) unverified Apache-2.0 (permissive) · 32bda22aba147afb · report
get_image_path w510056105/DeepLearning/Projects/TransferLearning/InceptionV3_TransferLearning.py community (archive-listed) unverified Apache-2.0 (permissive) · 124ce005185e25a3 · report
kid xiao7199/compare_gan/compare_gan/src/kid_score.py community (archive-listed) unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 023f8427ea56eaec · report
unpack_png_image xiao7199/compare_gan/compare_gan/src/datasets.py community (archive-listed) unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · d5d2e5cba8355657 · report
unpack_raw_image xiao7199/compare_gan/compare_gan/src/datasets.py community (archive-listed) unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 7c6a1c5735f9a270 · report
GetDefaultParams identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · a3c9ee0e5a930a73 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Convolution

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