{"id":18585836,"url":"https://github.com/d-li14/octconv.pytorch","last_synced_at":"2025-04-09T21:23:32.764Z","repository":{"id":108971497,"uuid":"183762735","full_name":"d-li14/octconv.pytorch","owner":"d-li14","description":"PyTorch implementation of Octave Convolution with pre-trained Oct-ResNet and Oct-MobileNet models","archived":false,"fork":false,"pushed_at":"2020-07-08T00:45:02.000Z","size":138,"stargazers_count":293,"open_issues_count":2,"forks_count":42,"subscribers_count":9,"default_branch":"master","last_synced_at":"2025-04-02T19:09:04.158Z","etag":null,"topics":["deep-neural-networks","iccv2019","imagenet","mobilenet","multi-scale","octconv","pytorch-implementation","resnet"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/1904.05049","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-04-27T11:10:53.000Z","updated_at":"2025-02-23T02:29:20.000Z","dependencies_parsed_at":"2023-04-08T22:51:23.987Z","dependency_job_id":null,"html_url":"https://github.com/d-li14/octconv.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%2Foctconv.pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/d-li14%2Foctconv.pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/d-li14%2Foctconv.pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/d-li14%2Foctconv.pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/d-li14","download_url":"https://codeload.github.com/d-li14/octconv.pytorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248113133,"owners_count":21049788,"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":["deep-neural-networks","iccv2019","imagenet","mobilenet","multi-scale","octconv","pytorch-implementation","resnet"],"created_at":"2024-11-07T00:35:38.616Z","updated_at":"2025-04-09T21:23:32.744Z","avatar_url":"https://github.com/d-li14.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# octconv.pytorch\n[PyTorch](pytorch.org) implementation of Octave Convolution in [Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution](https://arxiv.org/abs/1904.05049)\n\n## ResNet-50/101 on ImageNet\n| Architecture             | LR decay strategy   | Parameters | GFLOPs | Top-1 / Top-5 Accuracy (%) |\n| ------------------------ | ------------------- | ---------- | ------ | ----------------------- |\n| [ResNet-50](https://drive.google.com/open?id=1n7H6WNrvtf0eyWeWotbWD1kb95iVWaze)                | step (90 epochs)    | 25.557M    | 4.089  | 76.010 / 92.834         |\n| [ResNet-50](https://drive.google.com/open?id=1_aconGn2oZB1Bvgq65g2tsqSI7CSPAEt)                | cosine (120 epochs) | 25.557M    | 4.089  | 77.150 / 93.468         |\n| [Oct-ResNet-50 (alpha=0.5)](https://drive.google.com/open?id=1F9esqmbIJmfTOsAZ6_6JEUnI83LVgF_S) | cosine (120 epochs) | 25.557M    | 2.367  | 77.640 / 93.662         |\n| [ResNet-101](https://drive.google.com/file/d/128pkjPIN8hvjmbsSmUb62cikmiPjlgb1/view?usp=sharing) | cosine (120 epochs) | 44.549M | 7.801 | 78.898 / 94.304 |\n| [Oct-ResNet-101 (alpha=0.5)](https://drive.google.com/file/d/1E3To8EZDlVX8EfIU4q4r6SHDUHStKOqG/view?usp=sharing) | cosine (120 epochs) | 44.549M | 3.991 | 78.794 / 94.330 |\n| [ResNet-152](https://drive.google.com/file/d/1RZwAaVs1sUjUBlXTRR-zq0-S2d38Zb8Y/view?usp=sharing) | cosine (120 epochs) | 60.193M | 11.514 | 79.234 / 94.556 |\n| [Oct-ResNet-152 (alpha=0.5)](https://drive.google.com/file/d/1lmNaN8W-ky91je2hbPfUv4va6Uj4_qw1/view?usp=sharing) | cosine (120 epochs) | 60.193M | 5.615 | 79.258 / 94.480 |\n\n\n\u003cp align=\"center\"\u003e\u003cimg src=\"fig/ablation.png\" width=\"600\" /\u003e\u003c/p\u003e\n\n\n\n## MobileNet V1 on ImageNet\n| Architecture             | LR decay strategy   | Parameters | FLOPs | Top-1 / Top-5 Accuracy (%) |\n| ------------------------ | ------------------- | ---------- | ------ | ----------------------- |\n| [MobileNetV1](https://drive.google.com/file/d/14FBekvITT77z2LX_2utFGMteK3gxN1vn/view?usp=sharing) | cosine (150 epochs) | 4.232M | 568.7M | 72.238 / 90.536 |\n| [Oct-MobileNetV1](https://drive.google.com/file/d/1hpXYlHuTLeg04BOTFInrDYsaM4P-b0vK/view?usp=sharing) | cosine (150 epochs) | 4.232M | 318.2M | 71.254 / 89.728 |\n\n## Acknowledgement\n[Official MXNet implmentation](https://github.com/facebookresearch/OctConv) by [@cypw](https://github.com/cypw)\n\n## Citation\n```bibtex\n@InProceedings{Chen_2019_ICCV,\nauthor = {Chen, Yunpeng and Fan, Haoqi and Xu, Bing and Yan, Zhicheng and Kalantidis, Yannis and Rohrbach, Marcus and Yan, Shuicheng and Feng, Jiashi},\ntitle = {Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks With Octave Convolution},\nbooktitle = {The IEEE International Conference on Computer Vision (ICCV)},\nmonth = {October},\nyear = {2019}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fd-li14%2Foctconv.pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fd-li14%2Foctconv.pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fd-li14%2Foctconv.pytorch/lists"}