{"id":13546319,"url":"https://github.com/musyoku/adversarial-autoencoder","last_synced_at":"2025-04-02T18:30:35.585Z","repository":{"id":202248995,"uuid":"52342663","full_name":"musyoku/adversarial-autoencoder","owner":"musyoku","description":"Chainer implementation of adversarial autoencoder (AAE)","archived":false,"fork":false,"pushed_at":"2018-03-07T12:32:25.000Z","size":2006,"stargazers_count":258,"open_issues_count":10,"forks_count":76,"subscribers_count":18,"default_branch":"master","last_synced_at":"2024-11-03T14:35:35.289Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","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/musyoku.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":"2016-02-23T08:16:41.000Z","updated_at":"2024-09-01T08:15:31.000Z","dependencies_parsed_at":null,"dependency_job_id":"afdb61c0-1d5a-46ed-bd92-2f06ad4563ec","html_url":"https://github.com/musyoku/adversarial-autoencoder","commit_stats":null,"previous_names":["musyoku/adversarial-autoencoder"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/musyoku%2Fadversarial-autoencoder","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/musyoku%2Fadversarial-autoencoder/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/musyoku%2Fadversarial-autoencoder/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/musyoku%2Fadversarial-autoencoder/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/musyoku","download_url":"https://codeload.github.com/musyoku/adversarial-autoencoder/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246869599,"owners_count":20847157,"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":"2024-08-01T12:00:35.491Z","updated_at":"2025-04-02T18:30:35.281Z","avatar_url":"https://github.com/musyoku.png","language":"Python","funding_links":[],"categories":["Preferred Networks Research"],"sub_categories":["Generative models"],"readme":"## Adversarial AutoEncoder\r\n\r\n- Code for the [paper](https://arxiv.org/abs/1511.05644)\r\n\r\n### Requirements\r\n\r\n- Chainer 2+\r\n- Python 2 or 3\r\n\r\n## Incorporating Label Information in the Adversarial Regularization\r\n\r\nrun `semi-supervised/regularize_z/train.py`\r\n\r\nWe trained with a prior (a mixture of 10 2-D Gaussians or Swissroll distribution) on 10K labeled MNIST examples and 40K unlabeled MNIST examples.\r\n\r\n![gaussian](http://musyoku.github.io/images/post/2016-02-22/gaussian.png)\r\n\r\n![swissroll](http://musyoku.github.io/images/post/2016-02-22/swissroll.png)\r\n\r\n## Supervised Adversarial Autoencoders\r\n\r\nrun `supervised/learn_style/train.py`\r\n\r\n![analogy](https://github.com/musyoku/musyoku.github.io/blob/master/images/post/2016-02-22/analogy_supervised.png?raw=true)\r\n\r\n## Semi-Supervised Adversarial Autoencoders\r\n\r\nrun `semi-supervised/classification/train.py`\r\n\r\n| data | # |\r\n|:--:|:--:|\r\n| labeled | 100 |\r\n| unlabeled | 49900 |\r\n| validation | 10000 |\r\n\r\n#### Validation accuracy at each epoch\r\n\r\n![classification](https://github.com/musyoku/musyoku.github.io/blob/master/images/post/2016-02-22/classification.png?raw=true)\r\n\r\n#### Analogies\r\n\r\n![analogy_semi](https://github.com/musyoku/musyoku.github.io/blob/master/images/post/2016-02-22/analogy_semi.png?raw=true)\r\n\r\n## Unsupervised clustering\r\n\r\nrun `unsupervised/clustering/train.py`\r\n\r\n#### 16 clusters\r\n\r\n![clusters_16](https://github.com/musyoku/musyoku.github.io/blob/master/images/post/2016-02-22/clusters_16.png?raw=true)\r\n\r\n#### 32 clusters\r\n\r\n![clusters_32](https://github.com/musyoku/musyoku.github.io/blob/master/images/post/2016-02-22/clusters_32.png?raw=true)\r\n\r\n## Dimensionality reduction\r\n\r\nrun `unsupervised/dim_reduction/train.py`\r\n\r\n![reduction_unsupervised](https://github.com/musyoku/musyoku.github.io/blob/master/images/post/2016-02-22/reduction_unsupervised.png?raw=true)\r\n\r\nrun `semi-supervised/dim_reduction/train.py`\r\n\r\n![reduction_100](https://github.com/musyoku/musyoku.github.io/blob/master/images/post/2016-02-22/reduction_100.png?raw=true)\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmusyoku%2Fadversarial-autoencoder","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmusyoku%2Fadversarial-autoencoder","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmusyoku%2Fadversarial-autoencoder/lists"}