{"id":13936667,"url":"https://github.com/xunhuang1995/SGAN","last_synced_at":"2025-07-19T22:31:55.259Z","repository":{"id":89295703,"uuid":"76410710","full_name":"xunhuang1995/SGAN","owner":"xunhuang1995","description":"Stacked Generative Adversarial Networks","archived":false,"fork":false,"pushed_at":"2017-05-14T03:36:03.000Z","size":43437,"stargazers_count":244,"open_issues_count":0,"forks_count":51,"subscribers_count":13,"default_branch":"master","last_synced_at":"2024-11-16T06:18:52.626Z","etag":null,"topics":["computer-vision","generative-adversarial-network","generative-model","machine-learning"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/1612.04357","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/xunhuang1995.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":"2016-12-14T00:42:41.000Z","updated_at":"2024-01-04T16:09:46.000Z","dependencies_parsed_at":"2023-03-14T09:30:36.491Z","dependency_job_id":null,"html_url":"https://github.com/xunhuang1995/SGAN","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xunhuang1995%2FSGAN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xunhuang1995%2FSGAN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xunhuang1995%2FSGAN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xunhuang1995%2FSGAN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/xunhuang1995","download_url":"https://codeload.github.com/xunhuang1995/SGAN/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":226686729,"owners_count":17666928,"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":["computer-vision","generative-adversarial-network","generative-model","machine-learning"],"created_at":"2024-08-07T23:02:53.944Z","updated_at":"2025-07-19T22:31:55.247Z","avatar_url":"https://github.com/xunhuang1995.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# Stacked Generative Adversarial Networks\n\n\nThis repository contains code for the paper \"[Stacked Generative Adversarial Networks](https://arxiv.org/abs/1612.04357)\", CVPR 2017. Part of the code is modified from OpenAI's [implementation](https://github.com/openai/improved-gan) of Improved GAN.\n\n## Architecture\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"http://www.cs.cornell.edu/~xhuang/img/sgan.jpg\" width=\"650\"\u003e\n\u003c/p\u003e\n\n## Samples\n\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"http://www.cs.cornell.edu/~xhuang/img/mnist_samples.png\"  width=\"250\"\u003e\n\u003cimg src=\"http://www.cs.cornell.edu/~xhuang/img/svhn_samples.png\"  width=\"250\"\u003e\n\u003cimg src=\"http://www.cs.cornell.edu/~xhuang/img/cifar_samples.png\"  width=\"250\"\u003e\n\u003c/p\u003e\n\n## Performance Comprison on CIFAR-10\n| Method       |  Inception Score | \n| ------------- | ----------- |\n| Infusion training    |  4.62 ± 0.06     | \n| GMAN (best variant)  |  5.34 ± 0.05  | \n| LR-GAN  |  6.11 ± 0.06  | \n| EGAN-Ent-VI  |  7.07 ± 0.10  | \n| Denoising feature matching  |  7.72 ± 0.13 | \n| DCGAN  |  6.58 | \n| SteinGAN |  6.35 | \n| Improved GAN（best variant)  |  8.09 ± 0.07 | \n| AC-GAN |  8.25 ± 0.07 | \n| **SGAN (ours)**   |  **8.59 ± 0.12** | \n\n## Citations\n\nIf you use the code in this repository in your paper, please consider citing:\n\n```\n@inproceedings{huang2017sgan,\n  title={Stacked Generative Adversarial Networks},\n  author={Huang, Xun and Li, Yixuan and Poursaeed, Omid and Hopcroft, John and Belongie, Serge},\n  booktitle={CVPR},\n  year={2017}\n}\n```\n\n## Contact\n\nIf you have any questions about the code, feel free to email me (xh258@cornell.edu).\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxunhuang1995%2FSGAN","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fxunhuang1995%2FSGAN","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxunhuang1995%2FSGAN/lists"}