{"id":13444238,"url":"https://github.com/RBirkeland/MVCNN-PyTorch","last_synced_at":"2025-03-20T18:31:36.361Z","repository":{"id":85812421,"uuid":"133497313","full_name":"RBirkeland/MVCNN-PyTorch","owner":"RBirkeland","description":null,"archived":false,"fork":false,"pushed_at":"2019-02-19T14:26:49.000Z","size":30,"stargazers_count":99,"open_issues_count":5,"forks_count":32,"subscribers_count":4,"default_branch":"master","last_synced_at":"2024-08-01T03:46:13.826Z","etag":null,"topics":["3d","deep-learning","neural-network","pytorch","resnet"],"latest_commit_sha":null,"homepage":null,"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/RBirkeland.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":"2018-05-15T10:05:18.000Z","updated_at":"2024-06-19T02:01:52.000Z","dependencies_parsed_at":null,"dependency_job_id":"fc1e0e22-e0d5-4746-ab4a-5a60d2183a2e","html_url":"https://github.com/RBirkeland/MVCNN-PyTorch","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/RBirkeland%2FMVCNN-PyTorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RBirkeland%2FMVCNN-PyTorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RBirkeland%2FMVCNN-PyTorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RBirkeland%2FMVCNN-PyTorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/RBirkeland","download_url":"https://codeload.github.com/RBirkeland/MVCNN-PyTorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":221792892,"owners_count":16881289,"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","deep-learning","neural-network","pytorch","resnet"],"created_at":"2024-07-31T03:02:22.655Z","updated_at":"2024-10-28T06:30:24.708Z","avatar_url":"https://github.com/RBirkeland.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# MVCNN-PyTorch\n## Multi-View CNN built on ResNet/AlexNet to classify 3D objects\nA PyTorch implementation of MVCNN using ResNet, inspired by the paper by [Hang Su](http://vis-www.cs.umass.edu/mvcnn/docs/su15mvcnn.pdf).\nMVCNN uses multiple 2D images of 3D objects to classify them. You can use the provided dataset or create your own.\n\nAlso check out my [RotationNet](https://github.com/RBirkeland/RotationNet) implementation whitch outperforms MVCNN (Under construction).\n\n![MVCNN](https://preview.ibb.co/eKcJHy/687474703a2f2f7669732d7777772e63732e756d6173732e6564752f6d76636e6e2f696d616765732f6d76636e6e2e706e67.png)\n\n### Dependencies\n* torch\n* torchvision\n* numpy\n* tensorflow (for logging)\n\n### Dataset\nModelNet40 12-view PNG dataset can be downloaded from [Google Drive](https://drive.google.com/file/d/0B4v2jR3WsindMUE3N2xiLVpyLW8/view).\n\nYou can also create your own 2D dataset from 3D objects (.obj, .stl, and .off), using [BlenderPhong](https://github.com/WeiTang114/BlenderPhong)\n\n### Setup\n```bash\nmkdir checkpoint\nmkdir logs\n```\n\n### Train\nTo start training, simply point to the path of the downloaded dataset. All the other settings are optional.\n\n```\npython controller.py \u003cpath to dataset\u003e  [--depth N] [--model MODEL] [--epochs N] [-b N]\n                                        [--lr LR] [--momentum M] [--lr-decay-freq W]\n                                        [--lr-decay W] [--print-freq N] [-r PATH] [--pretrained]\n```\n\nTo resume from a checkpoint, use the -r tag together with the path to the checkpoint file.\n\n### Tensorboard\nTo view training logs\n```\ntensorboard --logdir='logs' --port=6006\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FRBirkeland%2FMVCNN-PyTorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FRBirkeland%2FMVCNN-PyTorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FRBirkeland%2FMVCNN-PyTorch/lists"}