{"id":13499119,"url":"https://github.com/shicai/SENet-Caffe","last_synced_at":"2025-03-29T04:30:30.730Z","repository":{"id":145001298,"uuid":"101946719","full_name":"shicai/SENet-Caffe","owner":"shicai","description":"A Caffe Re-Implementation of SENet","archived":false,"fork":false,"pushed_at":"2018-11-26T03:30:07.000Z","size":7,"stargazers_count":169,"open_issues_count":9,"forks_count":99,"subscribers_count":10,"default_branch":"master","last_synced_at":"2025-03-13T18:17:52.963Z","etag":null,"topics":["caffe","imagenet","resnet","senet"],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/shicai.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}},"created_at":"2017-08-31T01:45:56.000Z","updated_at":"2024-08-20T02:07:09.000Z","dependencies_parsed_at":"2023-05-06T22:38:11.283Z","dependency_job_id":null,"html_url":"https://github.com/shicai/SENet-Caffe","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/shicai%2FSENet-Caffe","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shicai%2FSENet-Caffe/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shicai%2FSENet-Caffe/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shicai%2FSENet-Caffe/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/shicai","download_url":"https://codeload.github.com/shicai/SENet-Caffe/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246140565,"owners_count":20729797,"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":["caffe","imagenet","resnet","senet"],"created_at":"2024-07-31T22:00:29.279Z","updated_at":"2025-03-29T04:30:30.414Z","avatar_url":"https://github.com/shicai.png","language":null,"funding_links":[],"categories":["Papers\u0026Codes","DLA"],"sub_categories":["SENet"],"readme":"# SENet-Caffe\n\n### Introduction\n\nThis is a Caffe implementation of Squeeze-and-Excitation Networks (SENet). For details, please read the original slides:\n- [Squeeze-and-Excitation Networks](http://image-net.org/challenges/talks_2017/SENet.pdf)\n\nFor offical implementations, please check this repo [SENet](https://github.com/hujie-frank/SENet).\n\n### Pretrained Models on ImageNet\n\nHere we provide a pretrained SE-ResNet-50 model on ImageNet, which achieves slightly better accuracy rates than the original one reported in the official repo. You can use the official [bvlc caffe](https://github.com/BVLC/caffe) to run this model without any modifications.\n\nThe top-1/5 accuracy rates by using single center crop (crop size: 224x224, image size: 256xN):\n\nNetwork|Top-1|Top-5|Download|Architecture\n:---:|:---:|:---:|:---:|:---:\nSE-ResNet-50| 78.01| 94.21| [caffemodel (107 MB)](https://drive.google.com/open?id=0B7ubpZO7HnlCWkwtSG5CdXBKcmc)| [netscope](http://ethereon.github.io/netscope/#/gist/36a20d27cba38695b4a44632d7af608c), [netron](http://lutzroeder.github.io/netron?gist=36a20d27cba38695b4a44632d7af608c)\n\nFor your convenience, we also provide a link to this model on [Baidu Disk](https://pan.baidu.com/s/1eSzT6KU).\n\n\n### Notes\n\n- BGR mean values **[103.94,116.78,123.68]** are subtracted\n- **scale: 0.017** is used as std values for image preprocessing\n- Images labels are the same as [fb.resnet.torch](https://github.com/facebook/fb.resnet.torch). We also provide `synset.txt`, which can be found [here](https://gist.github.com/shicai/fa9f98edc23521382955d4731636d1af).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshicai%2FSENet-Caffe","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fshicai%2FSENet-Caffe","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshicai%2FSENet-Caffe/lists"}