{"id":16536338,"url":"https://github.com/timbmg/vae-cvae-mnist","last_synced_at":"2025-04-04T08:07:16.313Z","repository":{"id":37602677,"uuid":"122969710","full_name":"timbmg/VAE-CVAE-MNIST","owner":"timbmg","description":"Variational Autoencoder and Conditional Variational Autoencoder on MNIST in PyTorch","archived":false,"fork":false,"pushed_at":"2024-07-25T10:48:03.000Z","size":1160,"stargazers_count":579,"open_issues_count":2,"forks_count":104,"subscribers_count":8,"default_branch":"master","last_synced_at":"2024-10-12T18:31:05.365Z","etag":null,"topics":["cvae","deep-learning","latent-variable-models","mnist","pytorch","vae","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/timbmg.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":"2018-02-26T12:54:18.000Z","updated_at":"2024-10-09T03:10:50.000Z","dependencies_parsed_at":"2023-11-21T23:25:10.942Z","dependency_job_id":"da0bb928-692b-419c-9c82-bb0dced35584","html_url":"https://github.com/timbmg/VAE-CVAE-MNIST","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/timbmg%2FVAE-CVAE-MNIST","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/timbmg%2FVAE-CVAE-MNIST/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/timbmg%2FVAE-CVAE-MNIST/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/timbmg%2FVAE-CVAE-MNIST/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/timbmg","download_url":"https://codeload.github.com/timbmg/VAE-CVAE-MNIST/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247142032,"owners_count":20890651,"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":["cvae","deep-learning","latent-variable-models","mnist","pytorch","vae","variational-autoencoder"],"created_at":"2024-10-11T18:30:37.024Z","updated_at":"2025-04-04T08:07:16.282Z","avatar_url":"https://github.com/timbmg.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Variational Autoencoder \u0026 Conditional Variational Autoenoder on MNIST\n\nVAE paper: [Auto-Encoding Variational Bayes](https://arxiv.org/abs/1312.6114)\n\nCVAE paper: [Semi-supervised Learning with Deep Generative Models](https://proceedings.neurips.cc/paper/2014/hash/d523773c6b194f37b938d340d5d02232-Abstract.html)\n\n---\nIn order to run _conditional_ variational autoencoder, add `--conditional` to the the command. Check out the other commandline options in the code for hyperparameter settings (like learning rate, batch size, encoder/decoder layer depth and size).\n\n---\n\n## Results\n\nAll plots obtained after 10 epochs of training. Hyperparameters accordning to default settings in the code; not tuned.\n\n### z ~ q(z|x) and q(z|x,c)\nThe modeled latent distribution after 10 epochs and 100 samples per digit.\n\nVAE | CVAE\n--- | --- \n\u003cimg src=\"https://github.com/timbmg/VAE-CVAE-MNIST/blob/master/figs/1519649452.702026/E9-Dist.png\" width=\"400\"\u003e | \u003cimg src=\"https://github.com/timbmg/VAE-CVAE-MNIST/blob/master/figs/1519649461.195146/E9-Dist.png\" width=\"400\"\u003e\n\n### p(x|z) and p(x|z,c)\nRandomly sampled z, and their output. For CVAE, each c has been given as input once.\n\nVAE | CVAE\n--- | --- \n\u003cimg src=\"https://github.com/timbmg/VAE-CVAE-MNIST/blob/master/figs/1519649452.702026/E9I937.png\" width=\"400\"\u003e | \u003cimg src=\"https://github.com/timbmg/VAE-CVAE-MNIST/blob/master/figs/1519649461.195146/E9I937.png\" width=\"400\"\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftimbmg%2Fvae-cvae-mnist","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftimbmg%2Fvae-cvae-mnist","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftimbmg%2Fvae-cvae-mnist/lists"}