{"id":13499062,"url":"https://github.com/shicai/DenseNet-Caffe","last_synced_at":"2025-03-29T03:32:15.635Z","repository":{"id":145001177,"uuid":"81929000","full_name":"shicai/DenseNet-Caffe","owner":"shicai","description":"DenseNet Caffe Models, converted from https://github.com/liuzhuang13/DenseNet","archived":false,"fork":false,"pushed_at":"2019-08-29T17:45:11.000Z","size":13,"stargazers_count":357,"open_issues_count":17,"forks_count":272,"subscribers_count":19,"default_branch":"master","last_synced_at":"2025-03-13T18:17:52.304Z","etag":null,"topics":["caffe","deep-learning","densenet","imagenet","torch"],"latest_commit_sha":null,"homepage":null,"language":null,"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/shicai.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}},"created_at":"2017-02-14T09:34:01.000Z","updated_at":"2024-08-11T07:17:07.000Z","dependencies_parsed_at":"2023-06-07T13:45:30.012Z","dependency_job_id":null,"html_url":"https://github.com/shicai/DenseNet-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%2FDenseNet-Caffe","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shicai%2FDenseNet-Caffe/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shicai%2FDenseNet-Caffe/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shicai%2FDenseNet-Caffe/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/shicai","download_url":"https://codeload.github.com/shicai/DenseNet-Caffe/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246135766,"owners_count":20729056,"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","deep-learning","densenet","imagenet","torch"],"created_at":"2024-07-31T22:00:27.817Z","updated_at":"2025-03-29T03:32:15.378Z","avatar_url":"https://github.com/shicai.png","language":null,"funding_links":[],"categories":["Papers\u0026Codes"],"sub_categories":["DenseNet"],"readme":"# DenseNet-Caffe\n\n### Introduction\nWe manually converted the original torch models into caffe format from https://github.com/liuzhuang13/DenseNet.\n\nFor details of these networks, please read the original paper:\n- [Densely Connected Convolutional Networks](https://arxiv.org/abs/1608.06993)\n\n\n### Pretrained DenseNet Models on ImageNet\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:---:|:---:|:---:|:---:|:---:\nDenseNet 121 (k=32)| 74.91| 92.19| [caffemodel (30.8  MB)](https://drive.google.com/open?id=0B7ubpZO7HnlCcHlfNmJkU2VPelE)| [netscope](http://ethereon.github.io/netscope/#/gist/4928834eca7f06261ba0558e0ff63a6a), [netron](http://lutzroeder.github.io/netron?gist=4928834eca7f06261ba0558e0ff63a6a)\nDenseNet 169 (k=32)| 76.09| 93.14| [caffemodel (54.6  MB)](https://drive.google.com/open?id=0B7ubpZO7HnlCRWVVdUJjVVAyQXc)| [netscope](http://ethereon.github.io/netscope/#/gist/71335b6e8634327c9b9216619572b3dd), [netron](http://lutzroeder.github.io/netron?gist=71335b6e8634327c9b9216619572b3dd)\nDenseNet 201 (k=32)| 77.31| 93.64| [caffemodel (77.3  MB)](https://drive.google.com/open?id=0B7ubpZO7HnlCV3pud2oyR3lNMWs)| [netscope](http://ethereon.github.io/netscope/#/gist/ee808e19615844b8dbc7b13e92abd233), [netron](http://lutzroeder.github.io/netron?gist=ee808e19615844b8dbc7b13e92abd233)\nDenseNet 161 (k=48)| 77.64| 93.79| [caffemodel (110 MB)](https://drive.google.com/open?id=0B7ubpZO7HnlCa0phRGJIRERoTXM)| [netscope](http://ethereon.github.io/netscope/#/gist/8fae97d9c66b40b8da443f7f23e9b29b), [netron](http://lutzroeder.github.io/netron?gist=8fae97d9c66b40b8da443f7f23e9b29b)\n\n**Update** (July 27, 2017): for your convenience, we also provide a link to these models on [Baidu Disk](https://pan.baidu.com/s/1gfjD8cF).\n\n### Notes\nDue to compatibility reasons, several modifications have been made:\n- BGR mean values **[103.94,116.78,123.68]** are subtracted\n- **scale: 0.017** is used, instead of the original std values for image preprocessing\n- **ceil_mode: false** is used in the first pooling layers ('pool1') \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshicai%2FDenseNet-Caffe","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fshicai%2FDenseNet-Caffe","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshicai%2FDenseNet-Caffe/lists"}