{"id":14959085,"url":"https://github.com/yeonghyeon/cgan-tf","last_synced_at":"2025-10-24T16:31:05.424Z","repository":{"id":159175941,"uuid":"311523674","full_name":"YeongHyeon/CGAN-TF","owner":"YeongHyeon","description":"TensorFlow implementation of Conditional Generative Adversarial Nets (CGAN) with MNIST dataset.","archived":false,"fork":false,"pushed_at":"2020-11-11T04:58:47.000Z","size":3999,"stargazers_count":7,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-31T03:12:31.602Z","etag":null,"topics":["cgan","cgans","conditional-gan","conditions","gan","gans","generative-adversarial-network","generative-model","mnist","mnist-dataset","tensorflow","tensorflow-examples"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/YeongHyeon.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-11-10T02:33:09.000Z","updated_at":"2024-11-29T07:44:19.000Z","dependencies_parsed_at":null,"dependency_job_id":"d6732b58-f523-47ae-bc67-555095100e6a","html_url":"https://github.com/YeongHyeon/CGAN-TF","commit_stats":{"total_commits":11,"total_committers":1,"mean_commits":11.0,"dds":0.0,"last_synced_commit":"b6f1c13478879c9e18bd42f0c2723518d8411b4a"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YeongHyeon%2FCGAN-TF","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YeongHyeon%2FCGAN-TF/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YeongHyeon%2FCGAN-TF/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YeongHyeon%2FCGAN-TF/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/YeongHyeon","download_url":"https://codeload.github.com/YeongHyeon/CGAN-TF/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":237999605,"owners_count":19399914,"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":["cgan","cgans","conditional-gan","conditions","gan","gans","generative-adversarial-network","generative-model","mnist","mnist-dataset","tensorflow","tensorflow-examples"],"created_at":"2024-09-24T13:18:49.302Z","updated_at":"2025-10-24T16:31:00.369Z","avatar_url":"https://github.com/YeongHyeon.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"[TensorFlow] Conditional Generative Adversarial Nets (CGAN)\n=====\n\nTensorFlow implementation of Conditional Generative Adversarial Nets (CGAN) with MNIST dataset.  \n\n## Architecture\n\n### Training algorithm\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"./figures/algorithm.png\" width=\"500\"\u003e  \n  \u003cp\u003eThe algorithm for training CGAN [1].\u003c/p\u003e\n\u003c/div\u003e\n\n### CGAN architecture\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"./figures/cgan.png\" width=\"500\"\u003e  \n  \u003cp\u003eThe architecture of CGAN [1].\u003c/p\u003e\n\u003c/div\u003e\n\n### Graph in TensorBoard\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"./figures/graph.png\" width=\"650\"\u003e  \n  \u003cp\u003eGraph of CGAN.\u003c/p\u003e\n\u003c/div\u003e\n\n## Results\n\n### Training Procedure\n\u003cdiv align=\"center\"\u003e\n  \u003cp\u003e\n    \u003cimg src=\"./figures/CGAN_loss_d.svg\" width=\"300\"\u003e\n    \u003cimg src=\"./figures/CGAN_loss_g.svg\" width=\"300\"\u003e\n  \u003c/p\u003e\n  \u003cp\u003eLoss graph in the training procedure. \u003c/br\u003e Each graph shows loss of the discriminator and loss of the generator respectively.\u003c/p\u003e\n\u003c/div\u003e\n\n### Test Procedure\n\n#### From random noise without conditions\n\u003cdiv align=\"center\"\u003e\n\n|z:2|z:64|z:128|\n|:---:|:---:|:---:|\n|\u003cimg src=\"./figures/z02_n.png\" width=\"200\"\u003e|\u003cimg src=\"./figures/z64_n.png\" width=\"200\"\u003e|\u003cimg src=\"./figures/z128_n.png\" width=\"200\"\u003e|\n\n\u003c/div\u003e\n\n#### From random noise with conditions\n\u003cdiv align=\"center\"\u003e\n\n|z:2|z:64|z:128|\n|:---:|:---:|:---:|\n|\u003cimg src=\"./figures/z02_c.png\" width=\"200\"\u003e|\u003cimg src=\"./figures/z64_c.png\" width=\"200\"\u003e|\u003cimg src=\"./figures/z128_c.png\" width=\"200\"\u003e|\n\n\u003c/div\u003e\n\n#### Latent space walking with conditions\n\u003cdiv align=\"center\"\u003e\n\n|Class-0 (z:2)|Class-1 (z:2)|Class-2 (z:2)|Class-3 (z:2)|Class-4 (z:2)|\n|:---:|:---:|:---:|:---:|:---:|\n|\u003cimg src=\"./figures/z02_0.png\" width=\"150\"\u003e|\u003cimg src=\"./figures/z02_1.png\" width=\"150\"\u003e|\u003cimg src=\"./figures/z02_2.png\" width=\"150\"\u003e|\u003cimg src=\"./figures/z02_3.png\" width=\"150\"\u003e|\u003cimg src=\"./figures/z02_4.png\" width=\"150\"\u003e|\n\n|Class-5 (z:2)|Class-6 (z:2)|Class-7 (z:2)|Class-8 (z:2)|Class-9 (z:2)|\n|:---:|:---:|:---:|:---:|:---:|\n|\u003cimg src=\"./figures/z02_5.png\" width=\"150\"\u003e|\u003cimg src=\"./figures/z02_6.png\" width=\"150\"\u003e|\u003cimg src=\"./figures/z02_7.png\" width=\"150\"\u003e|\u003cimg src=\"./figures/z02_8.png\" width=\"150\"\u003e|\u003cimg src=\"./figures/z02_9.png\" width=\"150\"\u003e|\n\n\u003c/div\u003e\n\n## Environment\n* Python 3.7.4  \n* Tensorflow 1.14.0  \n* Numpy 1.17.1  \n* Matplotlib 3.1.1  \n* Scikit Learn (sklearn) 0.21.3  \n\n\n## Reference\n[1] Mehdi Mirza and Simon Osindero. (2014). \u003ca href=\"https://arxiv.org/abs/1411.1784\"\u003eConditional Generative Adversarial Nets\u003c/a\u003e. arXiv preprint arXiv:1411.1784.   \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyeonghyeon%2Fcgan-tf","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyeonghyeon%2Fcgan-tf","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyeonghyeon%2Fcgan-tf/lists"}