{"id":22897208,"url":"https://github.com/le-big-mac/vcl_diffusion","last_synced_at":"2025-10-06T11:19:18.778Z","repository":{"id":231544653,"uuid":"780690296","full_name":"le-big-mac/VCL_Diffusion","owner":"le-big-mac","description":"Variational continual learning of a conditional diffusion model to generate MNIST. Based on 'Conditional Diffusion MNIST'.","archived":false,"fork":false,"pushed_at":"2024-05-22T14:20:04.000Z","size":48777,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-07-23T10:52:24.130Z","etag":null,"topics":["bayesian-deep-learning","continual-learning","deep-learning","diffusion-models","neural-network"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":false,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":"TeaPearce/Conditional_Diffusion_MNIST","license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/le-big-mac.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}},"created_at":"2024-04-02T01:18:19.000Z","updated_at":"2024-05-22T14:20:08.000Z","dependencies_parsed_at":"2024-05-22T15:40:11.423Z","dependency_job_id":null,"html_url":"https://github.com/le-big-mac/VCL_Diffusion","commit_stats":null,"previous_names":["le-big-mac/conditional_diffusion_mnist","le-big-mac/vcl_diffusion"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/le-big-mac/VCL_Diffusion","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/le-big-mac%2FVCL_Diffusion","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/le-big-mac%2FVCL_Diffusion/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/le-big-mac%2FVCL_Diffusion/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/le-big-mac%2FVCL_Diffusion/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/le-big-mac","download_url":"https://codeload.github.com/le-big-mac/VCL_Diffusion/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/le-big-mac%2FVCL_Diffusion/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278599586,"owners_count":26013510,"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":"2025-10-06T02:00:05.630Z","response_time":65,"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":["bayesian-deep-learning","continual-learning","deep-learning","diffusion-models","neural-network"],"created_at":"2024-12-14T00:15:59.873Z","updated_at":"2025-10-06T11:19:18.756Z","avatar_url":"https://github.com/le-big-mac.png","language":"Python","readme":"# Variational continual learning for diffusion models.\n\nA codespace for training diffusion models with [variational continual learning](https://arxiv.org/abs/1710.10628), to see if it can mitigate catastrophic forgetting.\n\n\u003cdiv align=\"center\"\u003e\n  \u003ctable\u003e\n    \u003ctr\u003e\n      \u003ctd align=\"center\"\u003e\n        \u003cimg src=\"images/standard.png\" width=\"200\" /\u003e\n        \u003cbr\u003e\n        \u003cem\u003eStandard training.\u003c/em\u003e\n      \u003c/td\u003e\n      \u003ctd align=\"center\"\u003e\n        \u003cimg src=\"images/vcl.png\" width=\"200\" /\u003e\n        \u003cbr\u003e\n        \u003cem\u003eVCL training.\u003c/em\u003e\n      \u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n      \u003ctd colspan=\"2\" align=\"center\"\u003e\n        \u003cem\u003eImages generated during continual learning of MNIST digits, with no data replay. Each row i shows generations from when the model had been trained on\n            the first i tasks (digits), each column j shows generations for digit j.\u003c/em\u003e\n      \u003c/td\u003e\n    \u003c/tr\u003e\n  \u003c/table\u003e\n\u003c/div\u003e\n\nNote that the variational inference for VCL is very expensive, so this code will take several hours to run on a powerful GPU.\n\nThis diffusion model in this project is based on original work by Tim Pearce, released under the MIT License in 2022. The original code can be found at [Conditional Diffusion MNIST](https://github.com/TeaPearce/Conditional_Diffusion_MNIST). The modifications made by me in 2024 are also released under the MIT License.\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fle-big-mac%2Fvcl_diffusion","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fle-big-mac%2Fvcl_diffusion","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fle-big-mac%2Fvcl_diffusion/lists"}