{"id":19543151,"url":"https://github.com/yeonghyeon/cvae-anomalydetection-pytorch","last_synced_at":"2025-04-26T17:31:50.799Z","repository":{"id":159175949,"uuid":"220211053","full_name":"YeongHyeon/CVAE-AnomalyDetection-PyTorch","owner":"YeongHyeon","description":"Example of Anomaly Detection using Convolutional Variational Auto-Encoder (CVAE)","archived":false,"fork":false,"pushed_at":"2024-04-09T17:38:24.000Z","size":2423,"stargazers_count":36,"open_issues_count":0,"forks_count":2,"subscribers_count":5,"default_branch":"master","last_synced_at":"2024-04-09T19:36:13.729Z","etag":null,"topics":["anomaly-detection","convolutional-neural-networks","generative-neural-network","mnist-dataset","pytorch","variational-autoencoder"],"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/YeongHyeon.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}},"created_at":"2019-11-07T10:32:01.000Z","updated_at":"2024-04-09T15:53:29.000Z","dependencies_parsed_at":null,"dependency_job_id":"bb545585-84d3-46b8-83b9-4d0654137baf","html_url":"https://github.com/YeongHyeon/CVAE-AnomalyDetection-PyTorch","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/YeongHyeon%2FCVAE-AnomalyDetection-PyTorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YeongHyeon%2FCVAE-AnomalyDetection-PyTorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YeongHyeon%2FCVAE-AnomalyDetection-PyTorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YeongHyeon%2FCVAE-AnomalyDetection-PyTorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/YeongHyeon","download_url":"https://codeload.github.com/YeongHyeon/CVAE-AnomalyDetection-PyTorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224040419,"owners_count":17245762,"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":["anomaly-detection","convolutional-neural-networks","generative-neural-network","mnist-dataset","pytorch","variational-autoencoder"],"created_at":"2024-11-11T03:17:37.634Z","updated_at":"2024-11-11T03:17:38.946Z","avatar_url":"https://github.com/YeongHyeon.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"[PyTorch] Anomaly Detection using Convolutional Variational Auto-Encoder (CVAE)\n=====\n\nExample of Anomaly Detection using Convolutional Variational Auto-Encoder (CVAE) [\u003ca href=\"https://github.com/YeongHyeon/CVAE-AnomalyDetection\"\u003eTensorFlow 1.x\u003c/a\u003e] [\u003ca href=\"https://github.com/YeongHyeon/CVAE-AnomalyDetection-TF2\"\u003eTensorFlow 2.x\u003c/a\u003e].\n\n## Architecture\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"./figures/vae.png\" width=\"400\"\u003e  \n  \u003cp\u003eSimplified VAE architecture.\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\n||MNIST|Fashion-MNIST|\n|:---|:---:|:---:|\n|Reconstruciton of training|\u003cimg src=\"./figures/mnist/restoring.png\" width=\"500\"\u003e|\u003cimg src=\"./figures/fmnist/restoring.png\" width=\"500\"\u003e|\n|Latent of training|\u003cimg src=\"./figures/mnist/latent_tr.png\" width=\"500\"\u003e|\u003cimg src=\"./figures/fmnist/latent_tr.png\" width=\"500\"\u003e|\n|Latent walk|\u003cimg src=\"./figures/mnist/latent_walk.png\" width=\"500\"\u003e|\u003cimg src=\"./figures/fmnist/latent_walk.png\" width=\"500\"\u003e|\n|Latent of test|\u003cimg src=\"./figures/mnist/latent_te_2.png\" width=\"500\"\u003e|\u003cimg src=\"./figures/fmnist/latent_te_2.png\" width=\"500\"\u003e|\n|Histogram of test|\u003cimg src=\"./figures/mnist/histogram-test.png\" width=\"500\"\u003e|\u003cimg src=\"./figures/fmnist/histogram-test.png\" width=\"500\"\u003e|\n|AUROC|0.997|0.980|\n\n## Environment\n* Python 3.7.4  \n* PyTorch 1.1.0   \n* Numpy 1.17.1  \n* Matplotlib 3.1.1  \n* Scikit Learn (sklearn) 0.21.3  \n\n## Reference\n[1] Kingma, D. P., \u0026 Welling, M. (2013). \u003ca href=\"https://arxiv.org/abs/1312.6114\"\u003eAuto-encoding variational bayes\u003c/a\u003e. arXiv preprint arXiv:1312.6114.  \n[2] \u003ca href=\"https://en.wikipedia.org/wiki/Kullback%E2%80%93Leibler_divergence\"\u003eKullback Leibler divergence\u003c/a\u003e. Wikipedia\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyeonghyeon%2Fcvae-anomalydetection-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyeonghyeon%2Fcvae-anomalydetection-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyeonghyeon%2Fcvae-anomalydetection-pytorch/lists"}