{"id":13721430,"url":"https://github.com/d-li14/regnet.pytorch","last_synced_at":"2026-03-27T04:04:28.418Z","repository":{"id":42183437,"uuid":"270024227","full_name":"d-li14/regnet.pytorch","owner":"d-li14","description":"PyTorch-style and human-readable RegNet with a spectrum of pre-trained models","archived":false,"fork":false,"pushed_at":"2021-03-19T16:23:57.000Z","size":17,"stargazers_count":69,"open_issues_count":1,"forks_count":14,"subscribers_count":6,"default_branch":"master","last_synced_at":"2025-05-30T12:49:23.297Z","etag":null,"topics":["imagenet","neural-architecture-search","pretrained-models","pytorch","regnet","resnext"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/2003.13678","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/d-li14.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}},"created_at":"2020-06-06T15:35:20.000Z","updated_at":"2025-03-21T08:16:25.000Z","dependencies_parsed_at":"2022-09-01T14:03:22.095Z","dependency_job_id":null,"html_url":"https://github.com/d-li14/regnet.pytorch","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/d-li14/regnet.pytorch","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/d-li14%2Fregnet.pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/d-li14%2Fregnet.pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/d-li14%2Fregnet.pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/d-li14%2Fregnet.pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/d-li14","download_url":"https://codeload.github.com/d-li14/regnet.pytorch/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/d-li14%2Fregnet.pytorch/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261453340,"owners_count":23160499,"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":["imagenet","neural-architecture-search","pretrained-models","pytorch","regnet","resnext"],"created_at":"2024-08-03T01:01:16.952Z","updated_at":"2025-10-05T01:00:13.073Z","avatar_url":"https://github.com/d-li14.png","language":"Python","funding_links":[],"categories":["DLA"],"sub_categories":["RegNet"],"readme":"# RegNet Implementation with TorchVision Style\nPyTorch implementation of [Designing Network Design Spaces](https://arxiv.org/abs/2003.13678) by Ilija Radosavovic, Raj Prateek Kosaraju, Ross Girshick, Kaiming He, and Piotr Dollár.\n\nCompared to the [official codebase](https://github.com/facebookresearch/pycls), this repository follows the [torchvision's ResNeXt](https://github.com/pytorch/vision/blob/master/torchvision/models/resnet.py) style, which is expected to be more easily interpreted and utilized by pre-existing downstream applications.\n\nWe train the following models on 8x TITAN XP GPUs with 12G VRAM. During the first five epochs, we linearly ramp up the learning rate from 0.1.\n\n# Pre-trained Models\n\n| Model                                                        | Params (M) | GFLOPs | Batch size | Top-1 acc (%) (our impl.) | Top-1 acc (%) (official) |\n| ------------------------------------------------------------ | ---------- | ------ | ---------- | ------------------------- | ------------------------ |\n| [RegNetX-200M](https://hkustconnect-my.sharepoint.com/:u:/g/personal/dlibh_connect_ust_hk/EcDivRLCy7BHmVuoKVyqfZsB8t7OpFoCEdnLOD495UKWCw?e=r0h5fh) | 2.685      | 0.199  | 1024       | 68.210                    | 68.9                     |\n| [RegNetX-400M](https://hkustconnect-my.sharepoint.com/:u:/g/personal/dlibh_connect_ust_hk/EaL_0Di7OK5DsCLtvGcw418BqZGg5BD875kOIFMnALcMLQ?e=1mEB0v) | 5.158      | 0.398  | 1024       | 72.278                    | 72.7                     |\n| [RegNetX-600M](https://hkustconnect-my.sharepoint.com/:u:/g/personal/dlibh_connect_ust_hk/ETFwqAcWWctLh3dPaCm0R5YB4xJVvoGdCTuwYYQzJiq35g?e=8OeH7k) | 6.196      | 0.601  | 1024       | 73.862                    | 74.1                     |\n| [RegNetX-800M](https://hkustconnect-my.sharepoint.com/:u:/g/personal/dlibh_connect_ust_hk/Ecd7nKqHLnZCmlgitigejWIBYLhcpqkDCoBx_CEILtQcCg?e=8Xt961) | 7.260      | 0.800  | 1024       | 74.940                    | 75.2                     |\n| [RegNetX-1.6G](https://hkustconnect-my.sharepoint.com/:u:/g/personal/dlibh_connect_ust_hk/EXOeBD6xco5JmvLziY4zySEB1bR00A7DqCx9t4IbI_MAng?e=ZG5PxS) | 9.190      | 1.603  | 1024       | 76.706                    | 77.0                     |\n| [RegNetX-3.2G](https://hkustconnect-my.sharepoint.com/:u:/g/personal/dlibh_connect_ust_hk/EQ1o8qVNLuhBg21Kgf_bss8BHFrhm8PLI3xMrMtD7a192Q?e=RG2LoH) | 15.296     | 3.177  | 512        | 78.188                    | 78.3                     |\n| [RegNetX-4.0G](https://hkustconnect-my.sharepoint.com/:u:/g/personal/dlibh_connect_ust_hk/ET7rz66druZGqPe-IFC21MQBd_kcLoYwXIoR9YQbJpGOqA?e=wfYSsA) | 22.118     | 3.965  | 512        | 78.690                    | 78.6                     |\n| [RegNetX-6.4G](https://hkustconnect-my.sharepoint.com/:u:/g/personal/dlibh_connect_ust_hk/EQkGuWBHehlDnkr3cASqgS4Btul3Lb_iuO4IGHIeHrkWbA?e=ndLLQs) | 26.209     | 6.460  | 512        | 79.152                    | 79.2                     |\n| [RgeNetX-8.0G](https://hkustconnect-my.sharepoint.com/:u:/g/personal/dlibh_connect_ust_hk/EYTpeCq4OnNIr9ly3KmokywBodWSZHHBNPhiwirhk9Urag?e=PDsrFu) | 39.573     | 7.995  | 512        | 79.380                    | 79.3                     |\n| [RegNetX-12G](https://hkustconnect-my.sharepoint.com/:u:/g/personal/dlibh_connect_ust_hk/EWEqa2PJVdxOj-M95XlLFVIBns9cnbdV6V6ASl-lyHzwyw?e=XVhG10) | 46.106     | 12.087 | 256        | 79.998                    | 79.7                     |\n| [RegNetX-16G](https://hkustconnect-my.sharepoint.com/:u:/g/personal/dlibh_connect_ust_hk/ETjNce9S9bxGgU09rLXoXucBBNLbo3t8zdtyriK-Vc8Eww?e=CrNU6u) | 54.279     | 15.941 | 256        | 80.118                    | 80.0                     |\n| [RegNetX-32G](https://hkustconnect-my.sharepoint.com/:u:/g/personal/dlibh_connect_ust_hk/EReWI0v2kvVBpKAGWRy2Hb0BKaIk6wx-VbkFBqYoE-YQZw?e=dT0dos) | 107.812    | 31.736 | 256        | 80.516                    | 80.5                     |\n\n# Citation\n```bibtex\n@InProceedings{Radosavovic_2020_CVPR,\nauthor = {Radosavovic, Ilija and Kosaraju, Raj Prateek and Girshick, Ross and He, Kaiming and Doll{\\'a}r, Piotr},\ntitle = {Designing Network Design Spaces},\nbooktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},\nmonth = {June},\nyear = {2020}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fd-li14%2Fregnet.pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fd-li14%2Fregnet.pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fd-li14%2Fregnet.pytorch/lists"}