{"id":18585837,"url":"https://github.com/d-li14/efficientnetv2.pytorch","last_synced_at":"2025-04-05T16:10:27.000Z","repository":{"id":43075504,"uuid":"354021767","full_name":"d-li14/efficientnetv2.pytorch","owner":"d-li14","description":"PyTorch implementation of EfficientNetV2 family","archived":false,"fork":false,"pushed_at":"2022-02-20T08:57:32.000Z","size":21,"stargazers_count":467,"open_issues_count":7,"forks_count":95,"subscribers_count":10,"default_branch":"main","last_synced_at":"2025-03-29T15:11:24.168Z","etag":null,"topics":["efficientnet","efficientnetv2","icml2021","imagenet","pytorch-implementation"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/2104.00298","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":"2021-04-02T13:05:58.000Z","updated_at":"2025-03-29T13:08:09.000Z","dependencies_parsed_at":"2022-08-03T02:45:53.356Z","dependency_job_id":null,"html_url":"https://github.com/d-li14/efficientnetv2.pytorch","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/d-li14%2Fefficientnetv2.pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/d-li14%2Fefficientnetv2.pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/d-li14%2Fefficientnetv2.pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/d-li14%2Fefficientnetv2.pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/d-li14","download_url":"https://codeload.github.com/d-li14/efficientnetv2.pytorch/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247361695,"owners_count":20926643,"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":["efficientnet","efficientnetv2","icml2021","imagenet","pytorch-implementation"],"created_at":"2024-11-07T00:35:38.636Z","updated_at":"2025-04-05T16:10:26.966Z","avatar_url":"https://github.com/d-li14.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"**[NEW!]** Check out our latest work [involution](https://github.com/d-li14/involution) accepted to CVPR'21 that introduces a new neural operator, other than convolution and self-attention.\n\n---\n\n# PyTorch implementation of EfficientNet V2\n\nReproduction of EfficientNet V2 architecture as described in [EfficientNetV2: Smaller Models and Faster Training](https://arxiv.org/abs/2104.00298) by Mingxing Tan, Quoc V. Le with the [PyTorch](pytorch.org) framework.\n\n## Models\n\n| Architecture      | # Parameters | FLOPs | Top-1 Acc. (%) |\n| ----------------- | ------------ | ------ | -------------------------- |\n| EfficientNetV2-S    | 22.10M | 8.42G @ 384 |  |\n| EfficientNetV2-M    | 55.30M | 24.74G @ 480 |  |\n| EfficientNetV2-L    | 119.36M | 56.13G @ 480 |  |\n| EfficientNetV2-XL    | 208.96M | 93.41G @ 512 |  |\n\nStay tuned for ImageNet pre-trained weights.\n\n## Acknowledgement\n\nThe implementation is heavily borrowed from [HBONet](https://github.com/d-li14/HBONet) or [MobileNetV2](https://github.com/d-li14/mobilenetv2.pytorch), please kindly consider citing the following\n\n```\n@InProceedings{Li_2019_ICCV,\nauthor = {Li, Duo and Zhou, Aojun and Yao, Anbang},\ntitle = {HBONet: Harmonious Bottleneck on Two Orthogonal Dimensions},\nbooktitle = {The IEEE International Conference on Computer Vision (ICCV)},\nmonth = {Oct},\nyear = {2019}\n}\n```\n```\n@InProceedings{Sandler_2018_CVPR,\nauthor = {Sandler, Mark and Howard, Andrew and Zhu, Menglong and Zhmoginov, Andrey and Chen, Liang-Chieh},\ntitle = {MobileNetV2: Inverted Residuals and Linear Bottlenecks},\nbooktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},\nmonth = {June},\nyear = {2018}\n}\n```\n\nThe official [TensorFlow implementation](https://github.com/google/automl/tree/master/efficientnetv2) by [@mingxingtan](https://github.com/mingxingtan).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fd-li14%2Fefficientnetv2.pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fd-li14%2Fefficientnetv2.pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fd-li14%2Fefficientnetv2.pytorch/lists"}