{"id":26694462,"url":"https://github.com/deeplearnphysics/dynamic-gcnn","last_synced_at":"2025-04-13T00:35:09.440Z","repository":{"id":116515120,"uuid":"151665988","full_name":"DeepLearnPhysics/dynamic-gcnn","owner":"DeepLearnPhysics","description":"Dynamic Graph Convolutional Neural Network for 3D point cloud semantic segmentation","archived":false,"fork":false,"pushed_at":"2018-11-07T22:21:51.000Z","size":117,"stargazers_count":64,"open_issues_count":1,"forks_count":11,"subscribers_count":5,"default_branch":"develop","last_synced_at":"2025-04-13T00:34:49.364Z","etag":null,"topics":["convolutional-neural-networks","custom-data","dgcnn","gcnn","graph-convolutional-networks","python","tensorflow"],"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/DeepLearnPhysics.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","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":"2018-10-05T03:27:52.000Z","updated_at":"2025-02-09T11:36:35.000Z","dependencies_parsed_at":"2024-01-18T15:57:16.975Z","dependency_job_id":"ea1e90d2-6147-4999-936c-ff48efa72d42","html_url":"https://github.com/DeepLearnPhysics/dynamic-gcnn","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/DeepLearnPhysics%2Fdynamic-gcnn","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DeepLearnPhysics%2Fdynamic-gcnn/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DeepLearnPhysics%2Fdynamic-gcnn/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DeepLearnPhysics%2Fdynamic-gcnn/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DeepLearnPhysics","download_url":"https://codeload.github.com/DeepLearnPhysics/dynamic-gcnn/tar.gz/refs/heads/develop","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248650461,"owners_count":21139670,"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":["convolutional-neural-networks","custom-data","dgcnn","gcnn","graph-convolutional-networks","python","tensorflow"],"created_at":"2025-03-26T18:29:36.334Z","updated_at":"2025-04-13T00:35:09.423Z","avatar_url":"https://github.com/DeepLearnPhysics.png","language":"Python","readme":"# dgcnn\n\nThis is an implementation of 3D point cloud semantic segmentation for [Dynamic Graph Convolutional Neural Network](https://arxiv.org/abs/1801.07829). The number of edge convolution layers, fully connected layers, and number of filters per each layer are all configurable. The implementation includes a few variations such as residual unit (edge convolution with identity mapping), with or without fully connected layers, etc.. Experimental results on DeepLearnPhysics open data set will be made available.\n\n### Requirements\n* `tensorflow \u003e= v1.3`\n* `numpy \u003e= 1.13` \n* Optional requirements for IO include `h5py`, `larcv`\n\n### Help\nAn executable script can be found at `bin/dgcnn.py`. The script takes `train` or `inference` arguments. Try `--help` to list available arguments:\n```\nbin/dgcnn.py train --help\n```\n### How to run\nBelow is an example of how to train the network using `mydata.hdf5` data file with `hdf5` format, 4 GPUs with batch size 24 and mini-batch size of 6, store snapshot every 500 iterations, print out info (loss,accuracy,etc) every 10 iterations, and store tensorboard summary every 50 iterations.\n```\nbin/dgcnn.py train --gpus 0,1,2,3 -bs 24 -mbs 6 -chks 500 -rs 10 -ss 50 -if mydata.hdf5 -io h5\n```\nSee `--help` to find more flags and a descipriton for arguments.\n\n\n\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeeplearnphysics%2Fdynamic-gcnn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdeeplearnphysics%2Fdynamic-gcnn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeeplearnphysics%2Fdynamic-gcnn/lists"}