{"id":16359308,"url":"https://github.com/gaborvecsei/variational-autoencoder","last_synced_at":"2025-04-13T15:42:12.515Z","repository":{"id":84266170,"uuid":"176825040","full_name":"gaborvecsei/Variational-Autoencoder","owner":"gaborvecsei","description":"Variational-Autoencoder w/ Convolutional Layers","archived":false,"fork":false,"pushed_at":"2019-03-24T17:47:23.000Z","size":749,"stargazers_count":3,"open_issues_count":1,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-03-27T06:44:46.746Z","etag":null,"topics":["cnn","convolutional-networks","convolutional-neural-networks","deep-learning","image-reconstruction","keras","machine-learning","python","research","tensorflow","vae","variational-autoencoder"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/gaborvecsei.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}},"created_at":"2019-03-20T22:12:03.000Z","updated_at":"2020-07-09T07:51:43.000Z","dependencies_parsed_at":"2023-05-24T04:45:12.992Z","dependency_job_id":null,"html_url":"https://github.com/gaborvecsei/Variational-Autoencoder","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gaborvecsei%2FVariational-Autoencoder","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gaborvecsei%2FVariational-Autoencoder/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gaborvecsei%2FVariational-Autoencoder/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gaborvecsei%2FVariational-Autoencoder/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gaborvecsei","download_url":"https://codeload.github.com/gaborvecsei/Variational-Autoencoder/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248740057,"owners_count":21154248,"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":["cnn","convolutional-networks","convolutional-neural-networks","deep-learning","image-reconstruction","keras","machine-learning","python","research","tensorflow","vae","variational-autoencoder"],"created_at":"2024-10-11T02:08:03.312Z","updated_at":"2025-04-13T15:42:12.510Z","avatar_url":"https://github.com/gaborvecsei.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Variational Autoencoder - VAE\n\nIn this repository you will find a *Variational Autoencoder* implementation which uses\n*Convolutional* layers to encode the input images to a latent vector, and *Traansposed Convolutional* layers to\nreconstruct the encoded vectors into images.\n\n\u003cimg src=\"art/reconstruction_random.gif\" width=\"600\" alt=\"interactive random reconstruction\"\u003e\n\n## Latent Space Playground\n\nCheck out the [notebook](latent_playground.ipynb) which contains the code for the experiments\n\n### Feature Importance\n\nWe can measure that in the latent space which feature is the most important for the reconstruction.\nBy \"most important\" I mean the ones which contribute to the bigger changes on the decoded images.\n\n\u003cimg src=\"art/most_important_features.png\" width=\"600\" alt=\"most important features\"\u003e\n\n### Interactive Image Reconstruction\n\nIn this part of the [notebook](latent_playground.ipynb), you can play with the latent space to generate your own\nimages based on the latent vector values.\n\n\u003cimg src=\"art/reconstruction_manual.gif\" width=\"600\" alt=\"interactive reconstruction\"\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgaborvecsei%2Fvariational-autoencoder","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgaborvecsei%2Fvariational-autoencoder","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgaborvecsei%2Fvariational-autoencoder/lists"}