{"id":13516952,"url":"https://github.com/poloclub/ganlab","last_synced_at":"2025-05-13T18:38:47.991Z","repository":{"id":37734727,"uuid":"127077950","full_name":"poloclub/ganlab","owner":"poloclub","description":"GAN Lab: An Interactive, Visual Experimentation Tool for Generative Adversarial Networks","archived":false,"fork":false,"pushed_at":"2022-12-08T18:05:00.000Z","size":5479,"stargazers_count":1381,"open_issues_count":27,"forks_count":380,"subscribers_count":55,"default_branch":"master","last_synced_at":"2024-08-02T05:16:18.465Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://poloclub.github.io/ganlab/","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/poloclub.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2018-03-28T03:23:07.000Z","updated_at":"2024-07-27T02:49:00.000Z","dependencies_parsed_at":"2023-01-25T15:31:15.940Z","dependency_job_id":null,"html_url":"https://github.com/poloclub/ganlab","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/poloclub%2Fganlab","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/poloclub%2Fganlab/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/poloclub%2Fganlab/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/poloclub%2Fganlab/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/poloclub","download_url":"https://codeload.github.com/poloclub/ganlab/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254004985,"owners_count":21998161,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-08-01T05:01:27.686Z","updated_at":"2025-05-13T18:38:47.965Z","avatar_url":"https://github.com/poloclub.png","language":"JavaScript","funding_links":[],"categories":["JavaScript","Computer Vision"],"sub_categories":["Image / Video Generation"],"readme":"# GAN Lab: An Interactive, Visual Experimentation Tool for Generative Adversarial Networks\n\nBy \n[Minsuk Kahng](http://minsuk.com),\n[Nikhil Thorat](https://twitter.com/nsthorat),\n[Polo Chau](https://www.cc.gatech.edu/~dchau/),\n[Fernanda Viégas](http://fernandaviegas.com/), and \n[Martin Wattenberg](http://www.bewitched.com/)\n\n## Overview\n\nGAN Lab is a novel interactive visualization tool for anyone to learn and experiment with Generative Adversarial Networks (GANs), a popular class of complex deep learning models. With GAN Lab, you can interactively train GAN models for 2D data distributions and visualize their inner-workings, similar to [TensorFlow Playground](http://playground.tensorflow.org/).\n\nGAN Lab uses [TensorFlow.js](https://js.tensorflow.org/), an in-browser GPU-accelerated deep learning library. Everything, from model training to visualization, is implemented with JavaScript. Users only need a web browser like Chrome to run GAN Lab. Our implementation approach significantly broadens people's access to interactive tools for deep learning. \n\n![Screenshot of GAN Lab](ganlab-teaser.png)\n\n\n## Working Demo\n\nClick the following link:\n\n[https://poloclub.github.io/ganlab/](https://poloclub.github.io/ganlab/)\n\nIt runs on most modern web browsers. We suggest you use Google Chrome.\n\n\n## Development\n\nThis section describes how you can develop GAN Lab.\n\n### Install Dependencies\n\nRun the following commands: \n\n```bash\n$ git clone https://github.com/poloclub/ganlab.git\n$ cd ganlab\n$ yarn prep\n```\n\nIt's unlikely, but you may need to install some basic JavaScript-related dependencies (e.g., yarn).\n\n\n### Running Your Demo\n\nRun the following command:\n\n```bash\n$ ./scripts/watch-demo\n\n\u003e\u003e Waiting for initial compile...\n\u003e\u003e 3462522 bytes written to demo/bundle.js (2.17 seconds) at 00:00:00\n\u003e\u003e Starting up http-server, serving ./\n\u003e\u003e Available on:\n\u003e\u003e   http://127.0.0.1:8080\n\u003e\u003e Hit CTRL-C to stop the server\n```\n\nThen visit `http://localhost:8080/demo/`. \n\nThe `watch-demo` script monitors for changes of typescript code (e.g., `demo/ganlab.ts`)\nand compiles the code for you.\n\n\n## Credit\n\nGAN Lab was created by \n[Minsuk Kahng](http://minsuk.com),\n[Nikhil Thorat](https://twitter.com/nsthorat),\n[Polo Chau](https://www.cc.gatech.edu/~dchau/),\n[Fernanda Viégas](http://www.fernandaviegas.com/), and \n[Martin Wattenberg](http://www.bewitched.com/),\nwhich was the result of a research collaboration between Georgia Tech and Google Brain/[PAIR](https://ai.google/research/teams/brain/pair).\nWe also thank Shan Carter and Daniel Smilkov, \n[Google Big Picture team](https://research.google.com/bigpicture/) and \n[Google People + AI Research (PAIR)](https://ai.google/research/teams/brain/pair), and \n[Georgia Tech Visualization Lab](http://vis.gatech.edu/)\nfor their feedback.\n \nFor more information, check out \n[our research paper](http://minsuk.com/research/papers/kahng-ganlab-vast2018.pdf):     \n \n[Minsuk Kahng](http://minsuk.com),\n[Nikhil Thorat](https://twitter.com/nsthorat),\n[Polo Chau](https://www.cc.gatech.edu/~dchau/),\n[Fernanda Viégas](http://www.fernandaviegas.com/), and \n[Martin Wattenberg](http://www.bewitched.com/).\n\"GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation.\"\n*IEEE Transactions on Visualization and Computer Graphics, 25(1) ([VAST 2018](http://ieeevis.org/year/2018/welcome))*, Jan. 2019.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpoloclub%2Fganlab","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpoloclub%2Fganlab","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpoloclub%2Fganlab/lists"}