{"id":14959086,"url":"https://github.com/yeonghyeon/wgan-tf","last_synced_at":"2026-01-21T14:03:28.414Z","repository":{"id":159176023,"uuid":"309347193","full_name":"YeongHyeon/WGAN-TF","owner":"YeongHyeon","description":"TensorFlow implementation of Wasserstein GAN (WGAN) with MNIST dataset.","archived":false,"fork":false,"pushed_at":"2020-11-09T09:22:15.000Z","size":4564,"stargazers_count":4,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-07T16:52:01.105Z","etag":null,"topics":["gan","gans","generative-adversarial-network","generative-model","mnist","mnist-dataset","tensorflow","tensorflow-examples","wasserstein","wasserstein-gan","wgan"],"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":"2020-11-02T11:18:04.000Z","updated_at":"2022-01-09T11:12:46.000Z","dependencies_parsed_at":null,"dependency_job_id":"a0992078-5347-4d9b-8abb-ac00093819f7","html_url":"https://github.com/YeongHyeon/WGAN-TF","commit_stats":{"total_commits":14,"total_committers":1,"mean_commits":14.0,"dds":0.0,"last_synced_commit":"5e77b978ee216f75ca99025363f49cf17852b06c"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YeongHyeon%2FWGAN-TF","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YeongHyeon%2FWGAN-TF/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YeongHyeon%2FWGAN-TF/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YeongHyeon%2FWGAN-TF/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/YeongHyeon","download_url":"https://codeload.github.com/YeongHyeon/WGAN-TF/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247694893,"owners_count":20980731,"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":["gan","gans","generative-adversarial-network","generative-model","mnist","mnist-dataset","tensorflow","tensorflow-examples","wasserstein","wasserstein-gan","wgan"],"created_at":"2024-09-24T13:18:49.373Z","updated_at":"2026-01-21T14:03:28.363Z","avatar_url":"https://github.com/YeongHyeon.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"[TensorFlow] Wasserstein GAN (WGAN)\n=====\nTensorFlow implementation of Wasserstein GAN (WGAN) with MNIST dataset.  \n\n### Training algorithm\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"./figures/algorithm.png\" width=\"500\"\u003e  \n  \u003cp\u003eThe algorithm for training WGAN [1].\u003c/p\u003e\n\u003c/div\u003e\n\n### WGAN architecture\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"./figures/wgan.png\" width=\"500\"\u003e  \n  \u003cp\u003eThe architecture of WGAN [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 WGAN.\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/WGAN_loss_d.svg\" width=\"300\"\u003e\n    \u003cimg src=\"./figures/WGAN_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\u003cdiv align=\"center\"\u003e\n\n|z:2|z:2 (latent space walking)|\n|:---:|:---:|\n|\u003cimg src=\"./figures/z02.png\" width=\"300\"\u003e|\u003cimg src=\"./figures/z02_lw.png\" width=\"300\"\u003e|\n\n|z:64|z:128|\n|:---:|:---:|\n|\u003cimg src=\"./figures/z64.png\" width=\"300\"\u003e|\u003cimg src=\"./figures/z128.png\" width=\"300\"\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] Martin Arjovsky et al. (2017). \u003ca href=\"https://arxiv.org/abs/1701.07875\"\u003eWasserstein GAN\u003c/a\u003e. arXiv preprint arXiv:1701.07875.  \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyeonghyeon%2Fwgan-tf","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyeonghyeon%2Fwgan-tf","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyeonghyeon%2Fwgan-tf/lists"}