{"id":20841708,"url":"https://github.com/jahongir7174/mobileone","last_synced_at":"2026-04-18T01:37:52.785Z","repository":{"id":226351893,"uuid":"625764436","full_name":"jahongir7174/MobileOne","owner":"jahongir7174","description":"MobileOne: An Improved One millisecond Mobile Backbone","archived":false,"fork":false,"pushed_at":"2024-03-07T05:40:45.000Z","size":92,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-10-07T19:46:31.544Z","etag":null,"topics":["classification","imagenet","mobileone","pretrained","python","pytorch"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/2206.04040","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/jahongir7174.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,"zenodo":null}},"created_at":"2023-04-10T03:41:10.000Z","updated_at":"2025-04-04T07:58:40.000Z","dependencies_parsed_at":null,"dependency_job_id":"01de5ff1-d0d6-46ec-a34a-3d3728156c28","html_url":"https://github.com/jahongir7174/MobileOne","commit_stats":null,"previous_names":["jahongir7174/mobileone"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/jahongir7174/MobileOne","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jahongir7174%2FMobileOne","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jahongir7174%2FMobileOne/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jahongir7174%2FMobileOne/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jahongir7174%2FMobileOne/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jahongir7174","download_url":"https://codeload.github.com/jahongir7174/MobileOne/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jahongir7174%2FMobileOne/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31953515,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-18T00:39:45.007Z","status":"ssl_error","status_checked_at":"2026-04-18T00:39:20.671Z","response_time":62,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["classification","imagenet","mobileone","pretrained","python","pytorch"],"created_at":"2024-11-18T01:21:25.311Z","updated_at":"2026-04-18T01:37:52.768Z","avatar_url":"https://github.com/jahongir7174.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"[MobileOne: An Improved One millisecond Mobile Backbone](https://arxiv.org/abs/2206.04040)\n\n### Installation\n\n```\nconda create -n PyTorch python=3.8\nconda activate PyTorch\nconda install pytorch torchvision torchaudio cudatoolkit=10.2 -c pytorch-lts\npip install opencv-python==4.5.5.64\npip install tqdm\n```\n\n### Note\n\n* The default training configuration is for `mobile_one-s0`\n* The test results including accuracy, params and FLOP are obtained by using fused model\n\n### Parameters and FLOPS\n\n```\nNumber of parameters: 2078504\nTime per operator type:\n        15.0684 ms.    91.0851%. Conv\n        1.20933 ms.     7.3101%. Relu\n       0.242441 ms.     1.4655%. FC\n      0.0117301 ms.  0.0709057%. AveragePool\n     0.00421935 ms.   0.025505%. Reshape\n     0.00261659 ms.  0.0158167%. Gather\n     0.00200163 ms.  0.0120994%. ExpandDims\n     0.00170158 ms.  0.0102857%. Concat\n      0.0007769 ms. 0.00469618%. Shape\n        16.5432 ms in Total\nFLOP per operator type:\n       0.548173 GFLOP.    99.6276%. Conv\n       0.002049 GFLOP.   0.372395%. FC\n              0 GFLOP.          0%. Concat\n              0 GFLOP.          0%. Relu\n       0.550222 GFLOP in Total\nFeature Memory Read per operator type:\n        19.7686 MB.    50.6551%. Conv\n        15.1532 MB.    38.8285%. Relu\n         4.1041 MB.    10.5164%. FC\n        1.2e-05 MB. 3.07489e-05%. Concat\n        39.0258 MB in Total\nFeature Memory Written per operator type:\n        15.1532 MB.    49.9934%. Conv\n        15.1532 MB.    49.9934%. Relu\n          0.004 MB.  0.0131968%. FC\n          8e-06 MB. 2.63937e-05%. Concat\n        30.3103 MB in Total\nParameter Memory per operator type:\n         4.1801 MB.    50.4837%. Conv\n            4.1 MB.    49.5163%. FC\n              0 MB.          0%. Concat\n              0 MB.          0%. Relu\n         8.2801 MB in Total\n```\n\n### Train\n\n* Configure your `IMAGENET` dataset path in `main.py` for training\n* Run `bash main.sh $ --train` for training, `$` is number of GPUs\n\n### Test\n\n* Configure your `IMAGENET` path in `main.py` for testing\n* Run `python main.py --test` for testing\n\n### Results\n\n|    Version     | Epochs | Top-1 Acc | Top-5 Acc | Params (M) | FLOP (G) |                                                                          Download |\n|:--------------:|:------:|----------:|----------:|-----------:|---------:|----------------------------------------------------------------------------------:|\n| mobile_one-s0  |  300   |         - |         - |       2.08 |    0.550 |                                                                                 - |\n| mobile_one-s0* |  300   |      71.4 |      89.9 |       2.08 |    0.550 | [model](https://github.com/jahongir7174/MobileOne/releases/download/v0.0.1/s0.pt) |\n| mobile_one-s1* |  300   |      75.8 |      92.8 |       4.76 |    1.650 | [model](https://github.com/jahongir7174/MobileOne/releases/download/v0.0.1/s1.pt) |\n| mobile_one-s2* |  300   |      77.4 |      93.2 |       7.80 |    2.596 | [model](https://github.com/jahongir7174/MobileOne/releases/download/v0.0.1/s2.pt) |\n| mobile_one-s3* |  300   |      77.9 |      93.9 |      10.07 |    3.791 | [model](https://github.com/jahongir7174/MobileOne/releases/download/v0.0.1/s3.pt) |\n| mobile_one-s4* |  300   |      79.3 |      94.4 |      14.83 |    5.960 | [model](https://github.com/jahongir7174/MobileOne/releases/download/v0.0.1/s4.pt) |\n\n* `*` means that weights are ported from original repo, see reference\n\n#### Reference\n\n* https://github.com/apple/ml-mobileone\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjahongir7174%2Fmobileone","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjahongir7174%2Fmobileone","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjahongir7174%2Fmobileone/lists"}