{"id":21984507,"url":"https://github.com/garyli1019/pointnet-keras","last_synced_at":"2025-04-30T07:25:06.579Z","repository":{"id":218335392,"uuid":"115844684","full_name":"garyli1019/pointnet-keras","owner":"garyli1019","description":"Keras implementation for Pointnet","archived":false,"fork":false,"pushed_at":"2019-10-28T03:41:10.000Z","size":1731,"stargazers_count":123,"open_issues_count":7,"forks_count":42,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-03-30T13:51:16.696Z","etag":null,"topics":["classification","deep-learning","keras","point-cloud","pointnet","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/garyli1019.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":"2017-12-31T05:24:42.000Z","updated_at":"2025-02-21T20:22:48.000Z","dependencies_parsed_at":"2024-01-21T10:22:40.773Z","dependency_job_id":"891ff3c3-d83c-4537-a138-cb8a738a4eae","html_url":"https://github.com/garyli1019/pointnet-keras","commit_stats":null,"previous_names":["garyli1019/pointnet-keras"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/garyli1019%2Fpointnet-keras","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/garyli1019%2Fpointnet-keras/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/garyli1019%2Fpointnet-keras/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/garyli1019%2Fpointnet-keras/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/garyli1019","download_url":"https://codeload.github.com/garyli1019/pointnet-keras/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251659500,"owners_count":21623060,"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":["classification","deep-learning","keras","point-cloud","pointnet","segmentation"],"created_at":"2024-11-29T18:09:48.897Z","updated_at":"2025-04-30T07:25:06.557Z","avatar_url":"https://github.com/garyli1019.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# pointnet-keras\nOriginal tensorflow implementation: https://github.com/charlesq34/pointnet\n\nPackage requirement: Python3.6, keras, tensorflow, numpy, matplotlib, h5py\n\n## Results\n\nSegmentation Sample\n\n![seg_sample](images/seg_sample.png)\n\n## How to Run code:\n\n### Classification:\n- Download the aligned dataset from [Link](https://shapenet.cs.stanford.edu/media/modelnet40_ply_hdf5_2048.zip)\n- Put all traning `.h5` files under `Prepdata` folder, all testing `.h5` files under `Prepdata_test` folder\n- Run train_cls.py. Accuracy rate will be 82.5%, which is slightly lower than the original implementation. \n\n### Segmentation:\n- Download and unzip the shapenet dataset from [Link](https://shapenet.cs.stanford.edu/ericyi/shapenetcore_partanno_v0.zip).\n- Run Seg_dataprep.py then train_seg.py.\n\n## Point Architecture\n\n- Input Transformation Net: Input: Nx3 point cloud sample, Output: 3x3 transformation net\n![input_transformation_net](images/input_transformation_net.png)\n\n- Feature Transformation Net:\n![feature_transformation_net](images/feature_transformation_net.png)\n\n- Global Feature: Input: Nx3 point cloud sample multiply input T_net. Output: 1*1024 global feature\n\n- Classification Net: Input: Nx3 point cloud sample multiply input T_net. Output: 1x40 softmax prediction\n![classification_net](images/classification_net.png)\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgaryli1019%2Fpointnet-keras","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgaryli1019%2Fpointnet-keras","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgaryli1019%2Fpointnet-keras/lists"}