{"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/gan-lab-understanding-complex-deep-generative","title":"GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation","arxiv_id":"1809.01587","date":"2018-09-05","proceeding":null,"authors":["Minsuk Kahng","Nikhil Thorat","Duen Horng Chau","Fernanda Viégas","Martin Wattenberg"],"abstract":"Recent success in deep learning has generated immense interest among\npractitioners and students, inspiring many to learn about this new technology.\nWhile visual and interactive approaches have been successfully developed to\nhelp people more easily learn deep learning, most existing tools focus on\nsimpler models. In this work, we present GAN Lab, the first interactive\nvisualization tool designed for non-experts to learn and experiment with\nGenerative Adversarial Networks (GANs), a popular class of complex deep\nlearning models. With GAN Lab, users can interactively train generative models\nand visualize the dynamic training process's intermediate results. GAN Lab\ntightly integrates an model overview graph that summarizes GAN's structure, and\na layered distributions view that helps users interpret the interplay between\nsubmodels. GAN Lab introduces new interactive experimentation features for\nlearning complex deep learning models, such as step-by-step training at\nmultiple levels of abstraction for understanding intricate training dynamics.\nImplemented using TensorFlow.js, GAN Lab is accessible to anyone via modern web\nbrowsers, without the need for installation or specialized hardware, overcoming\na major practical challenge in deploying interactive tools for deep learning.","url_abs":"http://arxiv.org/abs/1809.01587v1","url_pdf":"http://arxiv.org/pdf/1809.01587v1.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":"gan-lab-understanding-complex-deep-generative","repo_url":"https://github.com/poloclub/ganlab","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}