{"id":19543163,"url":"https://github.com/yeonghyeon/memae-tf2","last_synced_at":"2025-11-08T06:04:50.095Z","repository":{"id":159175977,"uuid":"241898745","full_name":"YeongHyeon/MemAE-TF2","owner":"YeongHyeon","description":"TensorFlow implementation of \"Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection\"","archived":false,"fork":false,"pushed_at":"2023-06-11T07:00:37.000Z","size":754,"stargazers_count":25,"open_issues_count":0,"forks_count":5,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-26T17:47:12.791Z","etag":null,"topics":["anomaly-detection","augmentation","convolutional-neural-network","convolutional-neural-networks","deep-learning","memorizing","memory-augmentation","mnist-dataset","tensorflow","tensorflow2"],"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,"zenodo":null}},"created_at":"2020-02-20T14:01:59.000Z","updated_at":"2024-07-18T12:17:36.000Z","dependencies_parsed_at":null,"dependency_job_id":"d0ea5d31-5268-40b6-9208-9b5ca1ecf174","html_url":"https://github.com/YeongHyeon/MemAE-TF2","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/YeongHyeon/MemAE-TF2","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YeongHyeon%2FMemAE-TF2","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YeongHyeon%2FMemAE-TF2/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YeongHyeon%2FMemAE-TF2/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YeongHyeon%2FMemAE-TF2/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/YeongHyeon","download_url":"https://codeload.github.com/YeongHyeon/MemAE-TF2/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YeongHyeon%2FMemAE-TF2/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":267600438,"owners_count":24113782,"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":"2025-07-28T02:00:09.689Z","response_time":68,"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":["anomaly-detection","augmentation","convolutional-neural-network","convolutional-neural-networks","deep-learning","memorizing","memory-augmentation","mnist-dataset","tensorflow","tensorflow2"],"created_at":"2024-11-11T03:17:45.364Z","updated_at":"2025-11-08T06:04:50.068Z","avatar_url":"https://github.com/YeongHyeon.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"[TensorFlow 2] Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection\n=====\n\nTensorFlow implementation of Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection. [\u003ca href=\"https://github.com/donggong1/memae-anomaly-detection\"\u003ePyTorch Version\u003c/a\u003e] [\u003ca href=\"https://github.com/YeongHyeon/MemAE\"\u003eTensorFlow 1 Version\u003c/a\u003e]\n\n## Architecture\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"./figures/memae.png\" width=\"500\"\u003e  \n  \u003cp\u003eArchitecture of MemAE.\u003c/p\u003e\n\u003c/div\u003e\n\n## Graph in TensorBoard\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"./figures/graph.png\" width=\"500\"\u003e  \n  \u003cp\u003eGraph of MemAE.\u003c/p\u003e\n\u003c/div\u003e\n\n## Problem Definition\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"./figures/definition.png\" width=\"600\"\u003e  \n  \u003cp\u003e'Class-1' is defined as normal and the others are defined as abnormal.\u003c/p\u003e\n\u003c/div\u003e\n\n## Results\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"./figures/restoring.png\" width=\"800\"\u003e  \n  \u003cp\u003eRestoration result by MemAE.\u003c/p\u003e\n\u003c/div\u003e\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"./figures/test-box.png\" width=\"350\"\u003e\u003cimg src=\"./figures/histogram-test.png\" width=\"390\"\u003e\n  \u003cp\u003eBox plot and histogram of restoration loss in test procedure.\u003c/p\u003e\n\u003c/div\u003e\n\n## Environment\n* Python 3.7.4  \n* Tensorflow 2.1.0  \n* Numpy 1.18.1  \n* Matplotlib 3.1.3  \n* Scikit Learn (sklearn) 0.22.1  \n\n## Reference\n[1] Dong Gong et al. (2019). \u003ca href=\"https://arxiv.org/abs/1904.02639\"\u003eMemorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection\u003c/a\u003e. arXiv preprint arXiv:1904.02639.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyeonghyeon%2Fmemae-tf2","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyeonghyeon%2Fmemae-tf2","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyeonghyeon%2Fmemae-tf2/lists"}