{"id":13717200,"url":"https://github.com/wohlert/semi-supervised-pytorch","last_synced_at":"2025-05-07T07:30:30.338Z","repository":{"id":45143179,"uuid":"105130683","full_name":"wohlert/semi-supervised-pytorch","owner":"wohlert","description":"Implementations of various VAE-based semi-supervised and generative models in PyTorch","archived":false,"fork":false,"pushed_at":"2020-03-02T14:23:59.000Z","size":13061,"stargazers_count":707,"open_issues_count":6,"forks_count":123,"subscribers_count":13,"default_branch":"master","last_synced_at":"2024-11-14T05:33:57.023Z","etag":null,"topics":["generative-models","pytorch","semi-supervised-learning"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":false,"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/wohlert.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2017-09-28T09:41:18.000Z","updated_at":"2024-11-12T17:48:47.000Z","dependencies_parsed_at":"2022-07-13T16:45:05.396Z","dependency_job_id":null,"html_url":"https://github.com/wohlert/semi-supervised-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/wohlert%2Fsemi-supervised-pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wohlert%2Fsemi-supervised-pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wohlert%2Fsemi-supervised-pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wohlert%2Fsemi-supervised-pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wohlert","download_url":"https://codeload.github.com/wohlert/semi-supervised-pytorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252833380,"owners_count":21811174,"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":["generative-models","pytorch","semi-supervised-learning"],"created_at":"2024-08-03T00:01:19.213Z","updated_at":"2025-05-07T07:30:29.970Z","avatar_url":"https://github.com/wohlert.png","language":"Python","funding_links":[],"categories":["Pytorch \u0026 related libraries｜Pytorch \u0026 相关库","Pytorch \u0026 related libraries"],"sub_categories":["Other libraries｜其他库:","Other libraries:"],"readme":"# Semi-supervised PyTorch\n\nA PyTorch-based package containing useful models for modern deep semi-supervised learning and deep generative models. Want to jump right into it? Look into the [notebooks](examples/notebooks).\n\n### Latest additions\n\n*2018.04.17* - The Gumbel softmax notebook has been added to show how\nyou can use discrete latent variables in VAEs.\n*2018.02.28* - The β-VAE notebook was added to show how VAEs can learn disentangled representations.\n\n## What is semi-supervised learning?\n\nSemi-supervised learning tries to bridge the gap between supervised and unsupervised learning by learning from both\nlabelled and unlabelled data.\n\nSemi-supervised learning can typically be applied to areas where data is easy to get a hold of, but labelling is expensive.\nNormally, one would either use an unsupervised method, or just the few labelled examples - both of which would be\nlikely to yield bad results.\n\nThe current state-of-the-art method in semi-supervised learning achieves an accuracy of over 99% on the MNIST dataset using just **10 labelled examples per class**.\n\n## Conditional generation\n\nMost semi-supervised models simultaneously train an inference network and a generator network. This means that it is\nnot only possible to query this models for classification, but also to generate new data from trained model.\nBy seperating label information, one can generate a new sample with the given digit as shown in the image below from\nKingma 2014.\n\n![Conditional generation of samples](examples/images/conditional.png)\n\n## Implemented models and methods:\n\n* [Variational Autoencoder (Kingma 2013)](https://arxiv.org/abs/1312.6114)\n* [Importance Weighted Autoencoders (Burda 2015)](https://arxiv.org/abs/1509.00519)\n* [Variational Inference with Normalizing Flows (Rezende \u0026 Mohamed 2015)](https://arxiv.org/abs/1505.05770)\n* [Semi-supervised Learning with Deep Generative Models (Kingma 2014)](https://arxiv.org/abs/1406.5298)\n* [Auxiliary Deep Generative Models (Maaløe 2016)](https://arxiv.org/abs/1602.05473)\n* [Ladder Variational Autoencoders (Sønderby 2016)](https://arxiv.org/abs/1602.02282)\n* [β-VAE (Higgins 2017)](https://openreview.net/forum?id=Sy2fzU9gl)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwohlert%2Fsemi-supervised-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwohlert%2Fsemi-supervised-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwohlert%2Fsemi-supervised-pytorch/lists"}