{"id":15892802,"url":"https://github.com/warner-benjamin/fastgarden","last_synced_at":"2025-04-02T17:26:46.477Z","repository":{"id":116187893,"uuid":"253916853","full_name":"warner-benjamin/FastGarden","owner":"warner-benjamin","description":null,"archived":false,"fork":false,"pushed_at":"2020-05-13T23:50:17.000Z","size":2877,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-02-08T08:14:13.906Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/warner-benjamin.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":"2020-04-07T21:32:53.000Z","updated_at":"2020-05-13T23:50:20.000Z","dependencies_parsed_at":null,"dependency_job_id":"70ac9d80-b6a6-4d07-8f75-d0d9955890eb","html_url":"https://github.com/warner-benjamin/FastGarden","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/warner-benjamin%2FFastGarden","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/warner-benjamin%2FFastGarden/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/warner-benjamin%2FFastGarden/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/warner-benjamin%2FFastGarden/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/warner-benjamin","download_url":"https://codeload.github.com/warner-benjamin/FastGarden/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246858729,"owners_count":20845338,"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":[],"created_at":"2024-10-06T08:04:19.793Z","updated_at":"2025-04-02T17:26:46.455Z","avatar_url":"https://github.com/warner-benjamin.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# FastGarden\n\nMy FastGarden submissions, fast.ai forum competition: https://forums.fast.ai/t/fastgarden-a-new-imagenette-like-competition-just-for-fun\n\n# Submissions\n\nCurrent best submission: \n\n* **82.40% +-0.15%**\n  * Experiment 2.3 in FastGarden MK-ResNeXt-50 F \u0026 G.ipynb\n  * Using MK-SE-ResNeXt-50F, which adds [MDConvs](https://arxiv.org/abs/1907.09595/) and [Network Deconvolutions](https://openreview.net/forum?id=rkeu30EtvS) to fast.ai’s XSE-ResNeXt. See the notebook for more details.\n  * Ranger optimizer, Label Smoothing Cross Entropy loss, fit_flat_cos with learning rate of 8e-3.\n\nRejected result because unable to reproduce: \n\n* **83.22% +-0.14%**\n  * Experiment 5.1 in FastGarden MK-ResNeXt-50D \u0026 E with Deconv Stem.ipynb\n  * Using MK-SE-ResNeXt-50E with deconv stem, which adds [MDConvs](https://arxiv.org/abs/1907.09595/) and [Network Deconvolutions](https://openreview.net/forum?id=rkeu30EtvS) to fast.ai’s XSE-ResNeXt. See the notebook for more details.\n  * Ranger optimizer, Label Smoothing Cross Entropy loss, fit_flat_cos with learning rate of 8e-3.\n\nPrior best submissions: \n\n* **80.41% +-0.73%**\n  * Experiment 7.3 in FastGarden MK-ResNeXt-50.ipynb\n  * Using MK-SE-ResNeXt-50E, which adds [MDConvs](https://arxiv.org/abs/1907.09595/) to fast.ai’s XSE-ResNeXt. See the notebook for more details.\n  * Ranger optimizer, Label Smoothing Cross Entropy loss, fit_flat_cos with learning rate of 8e-3.\n\n* **76.55% +- 0.25%**\n  * Second submission in FastGarden XSE-ResNeXt-50.ipynb\n  * XSE-ResNeXt50 with a (24,32,64) stem and GeM pool\n  * Ranger optimizer, Label Smoothing Cross Entropy loss, fit_flat_cos with learning rate of 8e-3.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwarner-benjamin%2Ffastgarden","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwarner-benjamin%2Ffastgarden","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwarner-benjamin%2Ffastgarden/lists"}