{"id":15896192,"url":"https://github.com/fkodom/byol","last_synced_at":"2025-03-20T15:32:32.420Z","repository":{"id":119170265,"uuid":"288882086","full_name":"fkodom/byol","owner":"fkodom","description":"PyTorch implementation of BYOL: a fantastically simple method for self-supervised image representation learning with SOTA performance.","archived":false,"fork":false,"pushed_at":"2021-03-24T15:57:40.000Z","size":32,"stargazers_count":9,"open_issues_count":1,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-10-23T03:16:35.687Z","etag":null,"topics":["machine-learning","machine-learning-algorithms","mit-license","python3","pytorch","pytorch-implementation"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"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/fkodom.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","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":"2020-08-20T02:07:21.000Z","updated_at":"2023-08-11T08:53:32.000Z","dependencies_parsed_at":null,"dependency_job_id":"3f87197d-e30b-438a-b3e9-5f61ff7ccfdf","html_url":"https://github.com/fkodom/byol","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/fkodom%2Fbyol","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fkodom%2Fbyol/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fkodom%2Fbyol/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fkodom%2Fbyol/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/fkodom","download_url":"https://codeload.github.com/fkodom/byol/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":221776117,"owners_count":16878490,"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":["machine-learning","machine-learning-algorithms","mit-license","python3","pytorch","pytorch-implementation"],"created_at":"2024-10-06T09:06:45.775Z","updated_at":"2024-10-28T04:02:25.427Z","avatar_url":"https://github.com/fkodom.png","language":"Python","readme":"# BYOL: Bootstrap Your Own Latent\n\nPyTorch implementation of [BYOL](https://arxiv.org/abs/2006.07733): a fantastically simple method for self-supervised image representation learning with SOTA performance.  Strongly influenced and inspired by [this Github repo](https://github.com/lucidrains/byol-pytorch), but with a few notable differences:\n1. Enables **multi-GPU** training in PyTorch Lightning.\n2. (Optionally) Automatically trains a linear classifier, and logs its accuracy after each epoch.\n3. All functions and classes are fully type annotated for better usability/hackability with Python\u003e=3.6.\n\n\n## TO DO\n* Enable mixed-precision training in PyTorch Lightning.  `kornia.augmentation.RandomResizedCrop` currently doesn't support this.  I'll need to ensure that our implementation is sufficiently performant, so it doesn't inadvertently slow down training.\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffkodom%2Fbyol","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffkodom%2Fbyol","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffkodom%2Fbyol/lists"}