{"id":19459810,"url":"https://github.com/jsflo/generative-adversarial-nets","last_synced_at":"2026-05-15T17:02:19.638Z","repository":{"id":187794763,"uuid":"105404998","full_name":"JsFlo/Generative-Adversarial-Nets","owner":"JsFlo","description":"Different GAN (Generative Adversarial Network) architectures in TensorFlow","archived":false,"fork":false,"pushed_at":"2018-06-28T01:15:49.000Z","size":13790,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-02-25T12:23:48.352Z","etag":null,"topics":["digimon","generative-adversarial-network","pokemon","tensorflow"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/JsFlo.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2017-09-30T22:30:58.000Z","updated_at":"2023-03-12T09:43:01.000Z","dependencies_parsed_at":"2023-08-12T06:52:18.919Z","dependency_job_id":null,"html_url":"https://github.com/JsFlo/Generative-Adversarial-Nets","commit_stats":null,"previous_names":["jsflo/generative-adversarial-nets"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/JsFlo/Generative-Adversarial-Nets","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JsFlo%2FGenerative-Adversarial-Nets","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JsFlo%2FGenerative-Adversarial-Nets/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JsFlo%2FGenerative-Adversarial-Nets/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JsFlo%2FGenerative-Adversarial-Nets/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/JsFlo","download_url":"https://codeload.github.com/JsFlo/Generative-Adversarial-Nets/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JsFlo%2FGenerative-Adversarial-Nets/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33072970,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-15T11:35:32.926Z","status":"ssl_error","status_checked_at":"2026-05-15T11:35:31.362Z","response_time":103,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["digimon","generative-adversarial-network","pokemon","tensorflow"],"created_at":"2024-11-10T17:34:10.648Z","updated_at":"2026-05-15T17:02:19.622Z","avatar_url":"https://github.com/JsFlo.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Generative-Adversarial-Nets\nDifferent GAN ([Generative Adversarial Network](http://papers.nips.cc/paper/5423-generative-adversarial-nets.pdf)) architectures in TensorFlow\n\n## w gan (*./w_gan/*)\n\n### Trained on Digimon images:\n![](images/digi_gan_1.jpg)\n\n![](images/digi_gan_2.jpg)\n\n### Trained on the original 150 Pokemon:\n![](images/poke_example.jpg)\n\n### Wasserstein GAN\nhttps://arxiv.org/abs/1701.07875\n\n### Generator\ntf.layers.conv2d_transpose\ntf.contrib.layers.batch_norm\n### Discriminator\ntf.layers.conv2d\ntf.contrib.layers.batch_norm\n\ndef leaky_relu(input, name, leak=0.2):\n    return tf.maximum(input, leak * input, name=name)\n\nw- gan\n\n\n\n\n\n\n\n\n\n\n\n## GAN (*/vaniall_gan/*)\nA Generative Adversarial Net implemented with **TensorFlow** using the\n**MNIST** data set.\n\n#### Generator:\n* Input: **100**\n* Output: **784**\n* Purpose: Will learn to **output images** that **look** like a **real**\nimage from **random input**.\n\n\n\n#### Discriminator:\n* Input: **784**\n* Output: **1**\n* Purpose: Will learn to tell a **real** (\"looks like it could be a real image in MNIST dataset\") **image**(784) from a fake one.\n\n\n#### Notes and Outputs\nA problem with the way that I built this is that I used the **same architecture**\nfor **both** the **generator** and **discriminator**. Although I thought this save me, the developer, a lot of time it actually\ncaused a lot of problems with trying to pigeonhole that architecture to work with a smaller input **(Discriminator: 28x28 vs 10x10 : Generator)**.\n\n##### Architecture\n\n* conv1 -\u003e relu -\u003e pool -\u003e\n* conv2 -\u003e relu -\u003e pool -\u003e\n* conv3 -\u003e relu -\u003e pool -\u003e\n* fullyConnected1 -\u003e relu -\u003e\n* fullyConnected2 -\u003e relu -\u003e\n* fullyConnected3 -\u003e\n\n100 random numbers -\u003e Generator -\u003e ImageOutput -\u003e Discriminator -\u003e (Real|Fake)\n\n\n![generated gan output](images/gan_generated.gif)\n\n![](images/init.png)\n![](images/two.png)\n![](images/two1.png)\n![](images/three.png)\n![](images/weird.png)\n![](images/weird2.png)\n![](images/weird3.png)\n\n## ColorGan","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjsflo%2Fgenerative-adversarial-nets","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjsflo%2Fgenerative-adversarial-nets","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjsflo%2Fgenerative-adversarial-nets/lists"}