{"id":13497239,"url":"https://github.com/nv-tlabs/GSCNN","last_synced_at":"2025-03-28T21:32:27.768Z","repository":{"id":41329833,"uuid":"196448316","full_name":"nv-tlabs/GSCNN","owner":"nv-tlabs","description":"Gated-Shape CNN for Semantic Segmentation (ICCV 2019)","archived":false,"fork":false,"pushed_at":"2023-10-23T15:39:04.000Z","size":169384,"stargazers_count":920,"open_issues_count":56,"forks_count":201,"subscribers_count":35,"default_branch":"master","last_synced_at":"2025-03-26T06:06:08.083Z","etag":null,"topics":["computer-vision","deep-learning","iccv2019","nv-tlabs","pytorch","semantic-boundaries","semantic-segmentation"],"latest_commit_sha":null,"homepage":"https://nv-tlabs.github.io/GSCNN/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/nv-tlabs.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":"2019-07-11T18:43:07.000Z","updated_at":"2025-03-10T03:22:17.000Z","dependencies_parsed_at":"2024-01-18T22:58:50.166Z","dependency_job_id":null,"html_url":"https://github.com/nv-tlabs/GSCNN","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/nv-tlabs%2FGSCNN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nv-tlabs%2FGSCNN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nv-tlabs%2FGSCNN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nv-tlabs%2FGSCNN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nv-tlabs","download_url":"https://codeload.github.com/nv-tlabs/GSCNN/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246105571,"owners_count":20724332,"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":["computer-vision","deep-learning","iccv2019","nv-tlabs","pytorch","semantic-boundaries","semantic-segmentation"],"created_at":"2024-07-31T20:00:27.225Z","updated_at":"2025-03-28T21:32:27.749Z","avatar_url":"https://github.com/nv-tlabs.png","language":"Python","funding_links":[],"categories":["SemanticSeg","对象检测_分割"],"sub_categories":["资源传输下载"],"readme":"# GSCNN\nThis is the official code for:\n\n#### Gated-SCNN: Gated Shape CNNs for Semantic Segmentation\n\n[Towaki Takikawa](https://tovacinni.github.io), [David Acuna](http://www.cs.toronto.edu/~davidj/), [Varun Jampani](https://varunjampani.github.io), [Sanja Fidler](http://www.cs.toronto.edu/~fidler/)\n\nICCV 2019\n**[[Paper](https://arxiv.org/abs/1907.05740)]  [[Project Page](https://nv-tlabs.github.io/GSCNN/)]**\n\n![GSCNN DEMO](docs/resources/gscnn.gif)\n\nBased on based on https://github.com/NVIDIA/semantic-segmentation.\n\n## License\n```\nCopyright (C) 2019 NVIDIA Corporation. Towaki Takikawa, David Acuna, Varun Jampani, Sanja Fidler\nAll rights reserved.\nLicensed under the CC BY-NC-SA 4.0 license (https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode).\n\nPermission to use, copy, modify, and distribute this software and its documentation\nfor any non-commercial purpose is hereby granted without fee, provided that the above\ncopyright notice appear in all copies and that both that copyright notice and this\npermission notice appear in supporting documentation, and that the name of the author\nnot be used in advertising or publicity pertaining to distribution of the software\nwithout specific, written prior permission.\n\nTHE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, INCLUDING ALL\nIMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR ANY PARTICULAR PURPOSE.\nIN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL\nDAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,\nWHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING\nOUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.\n~                                                                             \n```\n\n## Usage\n\n##### Clone this repo\n```bash\ngit clone https://github.com/nv-tlabs/GSCNN\ncd GSCNN\n ```\n\n#### Python requirements \n\nCurrently, the code supports Python 3\n* numpy \n* PyTorch (\u003e=1.1.0)\n* torchvision\n* scipy \n* scikit-image\n* tensorboardX\n* tqdm\n* torch-encoding\n* opencv\n* PyYAML\n\n#### Download pretrained models\n\nDownload the pretrained model from the [Google Drive Folder](https://drive.google.com/file/d/1wlhAXg-PfoUM-rFy2cksk43Ng3PpsK2c/view), and save it in 'checkpoints/'\n\n#### Download inferred images\n\nDownload (if needed) the inferred images from the [Google Drive Folder](https://drive.google.com/file/d/105WYnpSagdlf5-ZlSKWkRVeq-MyKLYOV/view)\n\n#### Evaluation (Cityscapes)\n```bash\npython train.py --evaluate --snapshot checkpoints/best_cityscapes_checkpoint.pth\n```\n\n#### Training\n\nA note on training- we train on 8 NVIDIA GPUs, and as such, training will be an issue with WiderResNet38 if you try to train on a single GPU.\n\nIf you use this code, please cite:\n\n```\n@article{takikawa2019gated,\n  title={Gated-SCNN: Gated Shape CNNs for Semantic Segmentation},\n  author={Takikawa, Towaki and Acuna, David and Jampani, Varun and Fidler, Sanja},\n  journal={ICCV},\n  year={2019}\n}\n```\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnv-tlabs%2FGSCNN","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnv-tlabs%2FGSCNN","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnv-tlabs%2FGSCNN/lists"}