{"id":13444143,"url":"https://github.com/lightaime/deep_gcns","last_synced_at":"2025-05-03T03:56:27.641Z","repository":{"id":50438286,"uuid":"179769299","full_name":"lightaime/deep_gcns","owner":"lightaime","description":"Tensorflow Repo for \"DeepGCNs: Can GCNs Go as Deep as CNNs?\" ICCV2019 Oral https://www.deepgcns.org","archived":false,"fork":false,"pushed_at":"2020-01-23T13:17:32.000Z","size":229275,"stargazers_count":631,"open_issues_count":1,"forks_count":87,"subscribers_count":19,"default_branch":"master","last_synced_at":"2025-05-03T03:56:22.289Z","etag":null,"topics":["3d-point-clouds","deep-gcns","geometric-deep-learning","graph-neural-networks"],"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/lightaime.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":"2019-04-05T23:52:51.000Z","updated_at":"2025-04-15T13:34:12.000Z","dependencies_parsed_at":"2022-08-05T07:30:16.944Z","dependency_job_id":null,"html_url":"https://github.com/lightaime/deep_gcns","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/lightaime%2Fdeep_gcns","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lightaime%2Fdeep_gcns/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lightaime%2Fdeep_gcns/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lightaime%2Fdeep_gcns/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lightaime","download_url":"https://codeload.github.com/lightaime/deep_gcns/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252140975,"owners_count":21700773,"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":["3d-point-clouds","deep-gcns","geometric-deep-learning","graph-neural-networks"],"created_at":"2024-07-31T03:02:20.191Z","updated_at":"2025-05-03T03:56:27.620Z","avatar_url":"https://github.com/lightaime.png","language":"Python","readme":"# DeepGCNs: Can GCNs Go as Deep as CNNs?\nIn this work, we present new ways to successfully train very deep GCNs. We borrow concepts from CNNs, mainly residual/dense connections and dilated convolutions, and adapt them to GCN architectures. Through extensive experiments, we show the positive effect of these deep GCN frameworks.\n\n[[Project]](https://www.deepgcns.org/) [[Paper]](https://arxiv.org/abs/1904.03751) [[Slides]](https://docs.google.com/presentation/d/1L82wWymMnHyYJk3xUKvteEWD5fX0jVRbCbI65Cxxku0/edit?usp=sharing) [[Tensorflow Code]](https://github.com/lightaime/deep_gcns) [[Pytorch Code]](https://github.com/lightaime/deep_gcns_torch)\n\n\u003cdiv style=\"text-align:center\"\u003e\u003cimg src='./misc/intro.png' width=800\u003e\n\n## Overview\nWe do extensive experiments to show how different components (#Layers, #Filters, #Nearest Neighbors, Dilation, etc.) effect `DeepGCNs`. We also provide ablation studies on different type of Deep GCNs (MRGCN, EdgeConv, GraphSage and GIN).\n\n\u003cdiv style=\"text-align:center\"\u003e\u003cimg src='./misc/pipeline.png' width=800\u003e\n\nFurther information and details please contact [Guohao Li](https://ghli.org) and [Matthias Müller](https://matthias.pw/).\n\n## Requirements\n* [TensorFlow 1.12.0](https://www.tensorflow.org/)\n* [h5py](https://www.h5py.org/)\n* [vtk](https://vtk.org/) (only needed for visualization)\n* [jupyter notebook](https://jupyter.org/) (only needed for visualization)\n\n## Conda Environment\nIn order to setup a conda environment with all neccessary dependencies run,\n```\nconda env create -f environment.yml\n```\n\n## Getting Started\nYou will find detailed instructions how to use our code for semantic segmentation of 3D point clouds, in the folder [sem_seg](sem_seg/). Currently, we provide the following:\n* Conda environment\n* Setup of \u003ca href=\"http://buildingparser.stanford.edu/dataset.html\"\u003eS3DIS Dataset\u003c/a\u003e\n* Training code\n* Evaluation code\n* Several pretrained models\n* Visualization code\n\n## Citation\nPlease cite our paper if you find anything helpful,\n```\n@InProceedings{li2019deepgcns,\n    title={DeepGCNs: Can GCNs Go as Deep as CNNs?},\n    author={Guohao Li and Matthias Müller and Ali Thabet and Bernard Ghanem},\n    booktitle={The IEEE International Conference on Computer Vision (ICCV)},\n    year={2019}\n}\n```\n\n```\n@misc{li2019deepgcns_journal,\n    title={DeepGCNs: Making GCNs Go as Deep as CNNs},\n    author={Guohao Li and Matthias Müller and Guocheng Qian and Itzel C. Delgadillo and Abdulellah Abualshour and Ali Thabet and Bernard Ghanem},\n    year={2019},\n    eprint={1910.06849},\n    archivePrefix={arXiv},\n    primaryClass={cs.CV}\n}\n```\n\n## License\nMIT License\n\n## Acknowledgement\nThis code is heavily borrowed from [PointNet](https://github.com/charlesq34/pointnet) and [EdgeConv](https://github.com/WangYueFt/dgcnn). We would also like to thank [3d-semantic-segmentation](https://github.com/VisualComputingInstitute/3d-semantic-segmentation) for the visualization code.\n","funding_links":[],"categories":["Python","Improved GCN:"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flightaime%2Fdeep_gcns","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flightaime%2Fdeep_gcns","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flightaime%2Fdeep_gcns/lists"}