{"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/are-gans-created-equal-a-large-scale-study","title":"Are GANs Created Equal? A Large-Scale Study","arxiv_id":"1711.10337","date":"2017-11-28","proceeding":"NeurIPS 2018 12","authors":["Mario Lucic","Karol Kurach","Marcin Michalski","Sylvain Gelly","Olivier Bousquet"],"abstract":"Generative adversarial networks (GAN) are a powerful subclass of generative\nmodels. Despite a very rich research activity leading to numerous interesting\nGAN algorithms, it is still very hard to assess which algorithm(s) perform\nbetter than others. We conduct a neutral, multi-faceted large-scale empirical\nstudy on state-of-the art models and evaluation measures. We find that most\nmodels can reach similar scores with enough hyperparameter optimization and\nrandom restarts. This suggests that improvements can arise from a higher\ncomputational budget and tuning more than fundamental algorithmic changes. To\novercome some limitations of the current metrics, we also propose several data\nsets on which precision and recall can be computed. Our experimental results\nsuggest that future GAN research should be based on more systematic and\nobjective evaluation procedures. Finally, we did not find evidence that any of\nthe tested algorithms consistently outperforms the non-saturating GAN\nintroduced in \\cite{goodfellow2014generative}.","url_abs":"http://arxiv.org/abs/1711.10337v4","url_pdf":"http://arxiv.org/pdf/1711.10337v4.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":"are-gans-created-equal-a-large-scale-study","repo_url":"https://github.com/google/compare_gan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"are-gans-created-equal-a-large-scale-study","repo_url":"https://github.com/agupta231/CARROL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"are-gans-created-equal-a-large-scale-study","repo_url":"https://github.com/beresandras/gan-flavours-keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"are-gans-created-equal-a-large-scale-study","repo_url":"https://github.com/blessengeorge/compare_gan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"are-gans-created-equal-a-large-scale-study","repo_url":"https://github.com/djl11/mxnet-fid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"unanswered"}},{"paper_slug":"are-gans-created-equal-a-large-scale-study","repo_url":"https://github.com/leognha/PyTorch-FID-score","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"are-gans-created-equal-a-large-scale-study","repo_url":"https://github.com/mseitzer/pytorch-fid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"are-gans-created-equal-a-large-scale-study","repo_url":"https://github.com/simon0987/ACGAN-implemented-with-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"are-gans-created-equal-a-large-scale-study","repo_url":"https://github.com/xiao7199/compare_gan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"hyperparameter-optimization","task_name":"Hyperparameter Optimization"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.10337","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.10337"}},"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/mseitzer/pytorch-fid","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/djl11/mxnet-fid","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google/compare_gan","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/blessengeorge/compare_gan","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/simon0987/ACGAN-implemented-with-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xiao7199/compare_gan","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/agupta231/CARROL","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/beresandras/gan-flavours-keras","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/leognha/PyTorch-FID-score","reach":{"status":"unanswered"}}],"summary":{"ran_draft_wrong":2,"ran_violates":1},"by_repo_kind":{"listed":{"samples":3,"ran":3,"repositories":2}},"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":"a3c9ee0e5a930a73","entry":"GetDefaultParams","repo":"blessengeorge/compare_gan","repo_kind":"listed","path":"compare_gan/src/generate_tasks_lib.py","file_url":"https://github.com/blessengeorge/compare_gan/blob/HEAD/compare_gan/src/generate_tasks_lib.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a3c9ee0e5a930a73"}},{"code_sha256_prefix":"5507a6f1c680f8cb","entry":"adversarial_loss_d","repo":"simon0987/ACGAN-implemented-with-pytorch","repo_kind":"listed","path":"GAN/gangangan.py","file_url":"https://github.com/simon0987/ACGAN-implemented-with-pytorch/blob/HEAD/GAN/gangangan.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5507a6f1c680f8cb"}},{"code_sha256_prefix":"9464a3295e71013d","entry":"adversarial_loss_g","repo":"simon0987/ACGAN-implemented-with-pytorch","repo_kind":"listed","path":"GAN/gangangan.py","file_url":"https://github.com/simon0987/ACGAN-implemented-with-pytorch/blob/HEAD/GAN/gangangan.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9464a3295e71013d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}