{"id":22632013,"url":"https://github.com/alleninstitute/u-dagan","last_synced_at":"2025-07-30T12:12:21.674Z","repository":{"id":145221329,"uuid":"279382447","full_name":"AllenInstitute/U-DAGAN","owner":"AllenInstitute","description":"Unsupervised data augmentation using GANs.","archived":false,"fork":false,"pushed_at":"2020-09-16T05:45:56.000Z","size":12204,"stargazers_count":7,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-11T20:11:25.937Z","etag":null,"topics":[],"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/AllenInstitute.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,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2020-07-13T18:32:42.000Z","updated_at":"2023-10-08T14:04:15.000Z","dependencies_parsed_at":null,"dependency_job_id":"04a2bd6b-9c2e-4e8e-9037-0f15db258cad","html_url":"https://github.com/AllenInstitute/U-DAGAN","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/AllenInstitute/U-DAGAN","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AllenInstitute%2FU-DAGAN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AllenInstitute%2FU-DAGAN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AllenInstitute%2FU-DAGAN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AllenInstitute%2FU-DAGAN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AllenInstitute","download_url":"https://codeload.github.com/AllenInstitute/U-DAGAN/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AllenInstitute%2FU-DAGAN/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":267866448,"owners_count":24157345,"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","status":"online","status_checked_at":"2025-07-30T02:00:09.044Z","response_time":70,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":[],"created_at":"2024-12-09T02:14:54.307Z","updated_at":"2025-07-30T12:12:21.666Z","avatar_url":"https://github.com/AllenInstitute.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Unsupervised Adversarial Augmenter/Generator Networks\nThis repository contains an implementation of an unspervised adverserial framework for both data augmentation and generarion.\n\n## Table of contents\n* [Generator](#generator)\n* [Augmenter](#augmenter)\n* [Usage](#usage)\n\n## Generator\ncombining a variational autoencoder (VAE) with a generative adversarial network (GAN), we introduce a VAE-GAN netowrk that leverages unsupervised representation learning and data sample reconstruction.\n\nThe network architecture for the developed VAE-GAN.\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"figures/vaegan.png\" width=\"500\"\u003e\n\t\n## Augmenter\nGiven the adversarial training proposed for GANs, here we introduce an augmentation network thatgenerates multiple nonidentical augmented samples with identical class labels, called U-DAGAN.\n\nThe schematic of the proposed architecture for unsupervised data augmentation and the augmenter's architecture.\n\u003cimg src=\"figures/udagan.png\" width=\"400\"\u003e\n\u003cimg src=\"figures/augmenter.png\" width=\"300\"\u003e\n\n### Example\n#### MNIST\n\u003cimg src=\"figures/mnist_augmented_sample.png\" width=\"800\"\u003e\n\n#### snRNA-seq (FACS)\n\u003cimg src=\"figures/sc_lowD_feature_space.png\" width=\"800\"\u003e\n\n\u003cimg src=\"figures/sc_gene_82.png\" width=\"800\"\u003e\n\n## Usage\nEach **generator** and **augmenter** folder contains code for training the network and generating fakes samples.\nTo train the model you can use `run.py` to train the network and `*augmenter.py`/`*augmenter.py` to generate fake samples.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falleninstitute%2Fu-dagan","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falleninstitute%2Fu-dagan","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falleninstitute%2Fu-dagan/lists"}