{"id":13443604,"url":"https://github.com/myavartanoo/PolyNet_PyTorch","last_synced_at":"2025-03-20T16:32:12.300Z","repository":{"id":157973961,"uuid":"414129203","full_name":"myavartanoo/PolyNet_PyTorch","owner":"myavartanoo","description":"Official implementation of the paper \"PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation\" (3DV 2021)","archived":false,"fork":false,"pushed_at":"2022-08-26T04:03:50.000Z","size":390,"stargazers_count":21,"open_issues_count":1,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-10-28T06:58:35.162Z","etag":null,"topics":["deep-learning","graphcnn","graphconv","pytorch"],"latest_commit_sha":null,"homepage":"","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/myavartanoo.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,"roadmap":null,"authors":null}},"created_at":"2021-10-06T08:24:37.000Z","updated_at":"2024-10-14T17:03:24.000Z","dependencies_parsed_at":"2024-01-18T14:45:44.440Z","dependency_job_id":"9d83f667-97aa-45d7-8eb9-fd4bb5842177","html_url":"https://github.com/myavartanoo/PolyNet_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/myavartanoo%2FPolyNet_PyTorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/myavartanoo%2FPolyNet_PyTorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/myavartanoo%2FPolyNet_PyTorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/myavartanoo%2FPolyNet_PyTorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/myavartanoo","download_url":"https://codeload.github.com/myavartanoo/PolyNet_PyTorch/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244649982,"owners_count":20487536,"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":["deep-learning","graphcnn","graphconv","pytorch"],"created_at":"2024-07-31T03:02:04.881Z","updated_at":"2025-03-20T16:32:11.888Z","avatar_url":"https://github.com/myavartanoo.png","language":"Python","readme":"# PolyNet_Pytorch\nThis repository contains the official code to reproduce the results from the paper: \n\n**PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation (3DV 2021)**\n\n\\[[project page](https://myavartanoo.github.io/polynet/)\\] \\[[arXiv](https://arxiv.org/abs/2110.07882)\\] \\[[ResearchGate](https://www.researchgate.net/publication/355218072_PolyNet_Polynomial_Neural_Network_for_3D_Shape_Recognition_with_PolyShape_Representation)\\]  \\[[presentation](https://www.youtube.com/watch?v=Pk8gvfGV5N8\u0026list=PLhCEMvtuQ92VkQCsiMKSn5ORcYM3BA1eM)\\] \n\n\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"source/PolyNet.png\" width=\"100%\"/\u003e  \n\u003c/p\u003e\n\n\n### Dependencies\n* Python 3.8.5\n* PyTorch 1.7.1\n* numpy\n* Pillow\n* torch_scatter\n\n### Dataset\nDownload the preprocessed ModelNet dataset with PTQ and √3-subdivision from the follwing link and unzip them in the data directroy. The data type is ```.npz```.\n\n\\[[PTQ](https://drive.google.com/drive/folders/15VFhxRTpSfetJqNqssuNWNJhpHOBOUsE?usp=sharing)\\] \\[[√3-subdivision](https://drive.google.com/drive/folders/1WnwZ0NkSme9s_VceZRjVTpS1QYCJ4yYt?usp=sharing)\\] \n\n\n### Train\nIn ```config.json``` you can set dataset type (ModelNet10 or ModelNet40) and the PolyPool type (PTQ, Sqrt3).\n\nTo train PolyNet with the desired dataset and PolyPool, simply run, \n\n```\nCUDA_VISIBLE_DEVICES=0 python train.py --config config.json -t \"direction to save the model\"\n```\n\n\n\n## Citation\nIf you find our paper, code, or provided data useful, please consider citing:\n\n```\n@INPROCEEDINGS{9665897,\n  author={Yavartanoo, Mohsen and Hung, Shih-Hsuan and Neshatavar, Reyhaneh and Zhang, Yue and Lee, Kyoung Mu},\n  booktitle={2021 International Conference on 3D Vision (3DV)}, \n  title={PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation}, \n  year={2021},\n  pages={1014-1023},\n  doi={10.1109/3DV53792.2021.00109}}\n```\n\n","funding_links":[],"categories":["Python"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmyavartanoo%2FPolyNet_PyTorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmyavartanoo%2FPolyNet_PyTorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmyavartanoo%2FPolyNet_PyTorch/lists"}