{"id":13418130,"url":"https://github.com/alexgkendall/caffe-segnet","last_synced_at":"2026-01-28T07:28:26.743Z","repository":{"id":36067692,"uuid":"40366929","full_name":"alexgkendall/caffe-segnet","owner":"alexgkendall","description":"Implementation of SegNet: A Deep Convolutional Encoder-Decoder Architecture for Semantic Pixel-Wise Labelling","archived":false,"fork":false,"pushed_at":"2018-03-15T08:10:01.000Z","size":29800,"stargazers_count":1080,"open_issues_count":81,"forks_count":456,"subscribers_count":76,"default_branch":"segnet-cleaned","last_synced_at":"2024-07-31T22:41:18.592Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"http://mi.eng.cam.ac.uk/projects/segnet/","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":"digoal/blog","license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/alexgkendall.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":"2015-08-07T15:21:09.000Z","updated_at":"2024-07-29T20:06:02.000Z","dependencies_parsed_at":"2022-09-01T00:22:41.019Z","dependency_job_id":null,"html_url":"https://github.com/alexgkendall/caffe-segnet","commit_stats":null,"previous_names":[],"tags_count":10,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alexgkendall%2Fcaffe-segnet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alexgkendall%2Fcaffe-segnet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alexgkendall%2Fcaffe-segnet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alexgkendall%2Fcaffe-segnet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/alexgkendall","download_url":"https://codeload.github.com/alexgkendall/caffe-segnet/tar.gz/refs/heads/segnet-cleaned","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243675177,"owners_count":20329221,"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":[],"created_at":"2024-07-30T22:00:58.793Z","updated_at":"2026-01-28T07:28:26.696Z","avatar_url":"https://github.com/alexgkendall.png","language":"C++","funding_links":[],"categories":["TODO scan for Android support in followings","C++","\u003ca name=\"Vision\"\u003e\u003c/a\u003e2. Vision"],"sub_categories":[],"readme":"# Caffe SegNet\n**This is a modified version of [Caffe](https://github.com/BVLC/caffe) which supports the [SegNet architecture](http://mi.eng.cam.ac.uk/projects/segnet/)**\n\nAs described in **SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation** Vijay Badrinarayanan, Alex Kendall and Roberto Cipolla, PAMI 2017 [http://arxiv.org/abs/1511.00561]\n\n# Updated Version:\n**This version supports cudnn v2 acceleration. @TimoSaemann has a branch supporting a more recent version of Caffe (Dec 2016) with cudnn v5.1:\nhttps://github.com/TimoSaemann/caffe-segnet-cudnn5**\n\n## Getting Started with Example Model and Webcam Demo\n\nIf you would just like to try out a pretrained example model, then you can find the model used in the [SegNet webdemo](http://mi.eng.cam.ac.uk/projects/segnet/) and a script to run a live webcam demo here:\nhttps://github.com/alexgkendall/SegNet-Tutorial\n\nFor a more detailed introduction to this software please see the tutorial here:\nhttp://mi.eng.cam.ac.uk/projects/segnet/tutorial.html\n\n### Dataset\n\nPrepare a text file of space-separated paths to images (jpegs or pngs) and corresponding label images alternatively e.g. ```/path/to/im1.png /another/path/to/lab1.png /path/to/im2.png /path/lab2.png ...```\n\nLabel images must be single channel, with each value from 0 being a separate class. The example net uses an image size of 360 by 480.\n\n### Net specification\n\nExample net specification and solver prototext files are given in examples/segnet.\nTo train a model, alter the data path in the ```data``` layers in ```net.prototxt``` to be your dataset.txt file (as described above).\n\nIn the last convolution layer, change ```num_output``` to be the number of classes in your dataset.\n\n### Training\n\nIn solver.prototxt set a path for ```snapshot_prefix```. Then in a terminal run\n```./build/tools/caffe train -solver ./examples/segnet/solver.prototxt```\n\n## Publications\n\nIf you use this software in your research, please cite our publications:\n\nhttp://arxiv.org/abs/1511.02680\nAlex Kendall, Vijay Badrinarayanan and Roberto Cipolla \"Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding.\" arXiv preprint arXiv:1511.02680, 2015.\n\nhttp://arxiv.org/abs/1511.00561\nVijay Badrinarayanan, Alex Kendall and Roberto Cipolla \"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation.\" PAMI, 2017. \n\n\n## License\n\nThis extension to the Caffe library is released under a creative commons license which allows for personal and research use only. For a commercial license please contact the authors. You can view a license summary here:\nhttp://creativecommons.org/licenses/by-nc/4.0/\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falexgkendall%2Fcaffe-segnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falexgkendall%2Fcaffe-segnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falexgkendall%2Fcaffe-segnet/lists"}