{"id":19340419,"url":"https://github.com/eragonruan/refinenet-image-segmentation","last_synced_at":"2025-04-23T02:31:26.652Z","repository":{"id":89249128,"uuid":"103763213","full_name":"eragonruan/refinenet-image-segmentation","owner":"eragonruan","description":"a tensorflow implement of refinenet ,RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation","archived":false,"fork":false,"pushed_at":"2017-11-02T11:25:01.000Z","size":1490,"stargazers_count":131,"open_issues_count":18,"forks_count":35,"subscribers_count":12,"default_branch":"dev","last_synced_at":"2025-04-02T06:51:15.479Z","etag":null,"topics":["refinenet","semantic-segmentation","tensorflow"],"latest_commit_sha":null,"homepage":null,"language":"Python","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/eragonruan.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,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2017-09-16T15:36:33.000Z","updated_at":"2025-03-23T22:48:47.000Z","dependencies_parsed_at":"2023-03-17T16:00:57.165Z","dependency_job_id":null,"html_url":"https://github.com/eragonruan/refinenet-image-segmentation","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/eragonruan%2Frefinenet-image-segmentation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eragonruan%2Frefinenet-image-segmentation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eragonruan%2Frefinenet-image-segmentation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eragonruan%2Frefinenet-image-segmentation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/eragonruan","download_url":"https://codeload.github.com/eragonruan/refinenet-image-segmentation/tar.gz/refs/heads/dev","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250357629,"owners_count":21417317,"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":["refinenet","semantic-segmentation","tensorflow"],"created_at":"2024-11-10T03:26:24.758Z","updated_at":"2025-04-23T02:31:26.644Z","avatar_url":"https://github.com/eragonruan.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# refinenet\na tensorflow implement of refinenet. RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation\n\n\n## Introduction\nthis is a tensorflow implement of refinenet discribed in [arxiv:1611.06612](https://arxiv.org/abs/1611.06612).I have not finished it yet, this is just a demo, but the model is already able to work.\n\n## prepare\n- download the pretrain model of resnet_v1_101.ckpt, you can download it from [here](https://github.com/tensorflow/models/tree/master/slim)\n- download the [pascal voc dataset](http://host.robots.ox.ac.uk/pascal/VOC/voc2012/)\n- some dependence like cv2, numpy and etc. recommend to install Anaconda\n\n## training\n- first, run convert_pascal_voc_to_tfrecords.py to convert training data into .tfrecords, Or you can use the tfrecord I converted In [BaiduYun](http://pan.baidu.com/s/1kVefEIj).Currently, I only use the pascal voc 2012 for training.\n- second, run python RefineNet/multi_gpu_train.py, also, you can change some hyper parameters in this file, like the batch size.\n\n## eval\n- if you have already got a model, or just download the model I trained on pascal voc.[model](http://pan.baidu.com/s/1kVefEIj).\n- put images in demo/ and run python RefineNet/demo.py \n\n## roadmap\n- [x] python2/3 compatibility\n- [ ] Complete realization of refinenet model\n- [ ] test on pascal voc, give the IoU result\n- [ ] training on other datasets\n\n## some result\n\u003cimg src=\"/demo/2007_000713.jpg\" width=256 height=256 /\u003e\u003cimg src=\"/demo/2007_000733.jpg\" width=256 height=256 /\u003e\u003cimg src=\"/demo/2007_000738.jpg\" width=256 height=256 /\u003e\n\u003cimg src=\"/result/2007_000713.jpg\" width=256 height=256 /\u003e\u003cimg src=\"/result/2007_000733.jpg\" width=256 height=256 /\u003e\u003cimg src=\"/result/2007_000738.jpg\" width=256 height=256 /\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feragonruan%2Frefinenet-image-segmentation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Feragonruan%2Frefinenet-image-segmentation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feragonruan%2Frefinenet-image-segmentation/lists"}