{"id":13637750,"url":"https://github.com/jfzhuang/IFR","last_synced_at":"2025-04-19T17:31:57.445Z","repository":{"id":38322487,"uuid":"430611545","full_name":"jfzhuang/IFR","owner":"jfzhuang","description":"[CVPR'22] Semi-Supervised Video Semantic Segmentation with Inter-Frame Feature Reconstruction","archived":false,"fork":false,"pushed_at":"2022-10-17T10:29:53.000Z","size":20650,"stargazers_count":27,"open_issues_count":3,"forks_count":4,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-08-03T01:11:49.036Z","etag":null,"topics":["cvpr2022","semantic-segmentation","semi-supervised-learning","semi-supervised-segmentation"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jfzhuang.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":"2021-11-22T07:53:14.000Z","updated_at":"2024-06-02T08:27:56.000Z","dependencies_parsed_at":"2023-01-19T15:46:15.452Z","dependency_job_id":null,"html_url":"https://github.com/jfzhuang/IFR","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/jfzhuang%2FIFR","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jfzhuang%2FIFR/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jfzhuang%2FIFR/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jfzhuang%2FIFR/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jfzhuang","download_url":"https://codeload.github.com/jfzhuang/IFR/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223804939,"owners_count":17205824,"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":["cvpr2022","semantic-segmentation","semi-supervised-learning","semi-supervised-segmentation"],"created_at":"2024-08-02T01:00:29.067Z","updated_at":"2024-11-09T08:30:19.776Z","avatar_url":"https://github.com/jfzhuang.png","language":"Python","funding_links":[],"categories":["2022"],"sub_categories":[],"readme":"# IFR\nThis repository is the official implementation of \"Semi-Supervised Video Semantic Segmentation with Inter-Frame Feature Reconstruction\" (accepted by CVPR 2022). It is designed for semi-supervised video semantic segmentation task.\n\n## Install \u0026 Requirements\nThe code has been tested on pytorch=1.8.2 and python3.8. Please refer to `requirements.txt` for detailed information.\n\n**To Install python packages**\n```\npip install -r requirements.txt\n```\n\n## Download Pretrained Weights\n````bash\nmkdir ./IFR/pretrained\ncd ./IFR/pretrained\n# download resnet18 imagenet pretrained weight\nwget http://sceneparsing.csail.mit.edu/model/pretrained_resnet/resnet18-imagenet.pth\n# download resnet101 imagenet pretrained weight\nwget http://sceneparsing.csail.mit.edu/model/pretrained_resnet/resnet101-imagenet.pth\n````\n\n## Data preparation\nYou need to download the [Cityscapes](https://www.cityscapes-dataset.com/) datasets.\n\nYour directory tree should be look like this:\n````bash\n./IFR/data\n├── cityscapes\n│   ├── gtFine\n│   │   ├── train\n│   │   └── val\n│   └── leftImg8bit_sequence\n│       ├── train\n│       └── val\n````\n\n## Prepare Downsample Dataset\nGenerated downsample dataset would be saved in ./data\n````bash\ncd ./IFR\npython tools/data_downsample.py\n````\n\n## Stage One Training of Accel\nFor example, train image segmentation model on 2 GPUs. Checkpoints would be saved in ./IFR/work_dirs.\n````bash\n# train PSP18 baseline model\ncd ./IFR/exp/sup_30_res18/scripts\nbash train.sh\n# train PSP101 baseline model\ncd ./IFR/exp/sup_30_res101/scripts\nbash train.sh\n# train PSP18 IFR model\ncd ./IFR/exp/IFR_30_res18/scripts\nbash train.sh\n# train PSP101 IFR model\ncd ./IFR/exp/IFR_30_res101/scripts\nbash train.sh\n````\n\n## Stage Two Training of Accel\nFor example, train Accel18 on 2 GPUs. Checkpoints would be saved in ./Accel/work_dirs.\n````bash\nmkdir ./Accel/work_dirs\n# train Accel18 with baseline model\ncd ./Accel/exp/accel18_30_sup/script\nbash train.sh\n# train Accel18 with IFR model\ncd ./Accel/exp/accel18_30_IFR/script\nbash train.sh\n````\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjfzhuang%2FIFR","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjfzhuang%2FIFR","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjfzhuang%2FIFR/lists"}