{"id":13444060,"url":"https://github.com/Xharlie/Grid-GCN","last_synced_at":"2025-03-20T17:33:03.314Z","repository":{"id":70647193,"uuid":"244564979","full_name":"Xharlie/Grid-GCN","owner":"Xharlie","description":"Grid-GCN for Fast and Scalable Point Cloud Learning","archived":false,"fork":false,"pushed_at":"2020-03-19T07:13:52.000Z","size":6695,"stargazers_count":184,"open_issues_count":11,"forks_count":25,"subscribers_count":11,"default_branch":"master","last_synced_at":"2024-10-28T07:42:40.812Z","etag":null,"topics":["3d-vision","3dvision","classification","computer-vision","cvpr2020","graphconv","graphconvoltution","grid-gcn","point-cloud","pointnet","s3dis","scannet","segmentation","self-driving-car"],"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/Xharlie.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}},"created_at":"2020-03-03T07:02:40.000Z","updated_at":"2024-10-16T07:31:33.000Z","dependencies_parsed_at":"2023-03-11T08:54:12.094Z","dependency_job_id":null,"html_url":"https://github.com/Xharlie/Grid-GCN","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/Xharlie%2FGrid-GCN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Xharlie%2FGrid-GCN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Xharlie%2FGrid-GCN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Xharlie%2FGrid-GCN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Xharlie","download_url":"https://codeload.github.com/Xharlie/Grid-GCN/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244660953,"owners_count":20489427,"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-vision","3dvision","classification","computer-vision","cvpr2020","graphconv","graphconvoltution","grid-gcn","point-cloud","pointnet","s3dis","scannet","segmentation","self-driving-car"],"created_at":"2024-07-31T03:02:17.924Z","updated_at":"2025-03-20T17:33:02.599Z","avatar_url":"https://github.com/Xharlie.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# Grid-GCN for Fast and Scalable Point Cloud Learning (CVPR2020)\nPlease cite us:\n``` \n@article{1912.02984,\n  Author = {Qiangeng Xu and Xudong Sun and Cho-Ying Wu and Panqu Wang and Ulrich Neumann},\n  Title = {Grid-GCN for Fast and Scalable Point Cloud Learning},\n  Year = {2019},\n  Eprint = {arXiv:1912.02984},\n  Howpublished = {Proceedings of the IEEE Conference on Computer Vision and Pattern\n    Recognition (CVPR 2020)}\n}\n``` \n\n## Requirement: GGCN implemented by MXNET 1.5.0\n\nmake sure you have gcc version suggested by MXNET 1.5.0\n\n## Install Our CUDA modules to MXNET Libary:\n```\ncd gridifyop\nvim Makefile  # then change mx_home to your mxnet-apache directory, and adjust nvcc command according to your gpu model and cuda version. here we use compute power 61 and 75 for 1080 ti and 2080 ti. save the change\nmake\ncd ..\n```\n\n## Data Preparation\n\n* ### Classification\n\n  * #### ModelNet40\n  We refer to pointnet  https://github.com/charlesq34/pointnet/blob/master/provider.py\n  ```\n  cd data/\n  wget https://shapenet.cs.stanford.edu/media/modelnet40_ply_hdf5_2048.zip\n  unzip modelnet40_ply_hdf5_2048.zip\n  unzip it and put it inside data/\n  ```\n  * #### ModelNet10\n  please refer to pointnet++'s github\n  ```\n  download  modelnet40_normal_resampled from https://github.com/charlesq34/pointnet2\n  take the modelnet10_train.txt, modelnet10_test.txt and extract from modelnet40_ply_hdf5_2048 to create a modelnet10_ply_hdf5_2048\n  or use modelnet40_normal_resampled directly, but configuration file configs_10.yaml new: True -\u003e False\n  ```\n  \n* ### Segmentation/ScanNet\n  Please refer to pointnet++ for downloading ScanNet use link: \n  ```\n  # in data/\n  wget https://shapenet.cs.stanford.edu/media/scannet_data_pointnet2.zip\n  unzip scannet_data_pointnet2.zip\n  mv data scannet\n\n\n## Training\n* ### Classification\n\n  * #### ModelNet40\n  ```\n  cd classification\n  nohup python -u train/train_gpu_ggcn_mdl40.py \u0026\u003e mdl40.log \u0026 \n  \n  ```\n  * #### ModelNet10\n  please refer to pointnet++\n  ```\n  cd classification\n  nohup python -u train/train_gpu_ggcn_mdl10.py \u0026\u003e mdl10.log \u0026\n  \n  ```\n  \n* ### Segmentation \n  * #### ScanNet\n  Please refer to pointnet++ for downloading ScanNet use link: \n  ```\n  cd segmentation\n  \n  ### then you cd configs -\u003e go to configs.yaml to choose 8192 points model or 81920 points model by leaving one of them uncommented\n  \n  nohup python -u train_test/train_ggcn_scannet.py \u0026\u003e train.log  \u0026\n  ```\n## Testing\n* ### Segmentation\n  * #### ScanNet\n  ```\n  cd segmentation\n  \n  ### then you cd configs -\u003e go to configs.yaml to choose 8192 points model or 81920 points model by leaving one of them uncommented\n  ### you should also change load_model_prefix to the intented trained model file in your output directory.\n  \n  nohup python -u train_test/test_ggcn_scannet.py \u0026\u003e test.log  \u0026\n  ```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FXharlie%2FGrid-GCN","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FXharlie%2FGrid-GCN","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FXharlie%2FGrid-GCN/lists"}