{"id":34628250,"url":"https://github.com/nwangfw/nerf_ddp","last_synced_at":"2026-04-22T01:02:11.962Z","repository":{"id":182338232,"uuid":"549873394","full_name":"nwangfw/nerf_ddp","owner":"nwangfw","description":null,"archived":false,"fork":false,"pushed_at":"2022-10-19T19:40:43.000Z","size":698,"stargazers_count":6,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-12-26T05:38:53.435Z","etag":null,"topics":["distributed-data-parallel","distributed-training","nerf","neural-radiance-fields","pytorch"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/nwangfw.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":"2022-10-11T21:50:01.000Z","updated_at":"2024-04-24T19:14:50.000Z","dependencies_parsed_at":null,"dependency_job_id":"ecb777b9-2958-40ed-8d56-58ac60b255ce","html_url":"https://github.com/nwangfw/nerf_ddp","commit_stats":null,"previous_names":["nwangfw/nerf_ddp"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/nwangfw/nerf_ddp","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nwangfw%2Fnerf_ddp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nwangfw%2Fnerf_ddp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nwangfw%2Fnerf_ddp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nwangfw%2Fnerf_ddp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nwangfw","download_url":"https://codeload.github.com/nwangfw/nerf_ddp/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nwangfw%2Fnerf_ddp/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32116514,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-22T00:31:26.853Z","status":"ssl_error","status_checked_at":"2026-04-22T00:30:22.894Z","response_time":128,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["distributed-data-parallel","distributed-training","nerf","neural-radiance-fields","pytorch"],"created_at":"2025-12-24T16:29:18.172Z","updated_at":"2026-04-22T01:02:11.928Z","avatar_url":"https://github.com/nwangfw.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# nerf_ddp\n\n\nThis repo tries to reduce NeRF training time by applying Pytorch Distributed Data Parallel training (DDP). Much of the code is inspired by the original implementation by GitHub user [bmild](https://github.com/bmild/nerf) as well as PyTorch implementations from GitHub users [yenchenlin](https://github.com/bmild/nerf), [krrish94](https://github.com/krrish94/nerf-pytorch/) and the Medium Article (https://towardsdatascience.com/its-nerf-from-nothing-build-a-vanilla-nerf-with-pytorch-7846e4c45666). The code has been modified for correctness, clarity, and consistency.\n\n\nThere are two implementations (e.g., tiny-nerf and full nerf). It is good to start with tiny_nerf to understand the basic implementation of both NeRF and Pytorch DDP.\n\n\n(1) tiny_nerf_ddp.py is modified from https://colab.research.google.com/drive/1rO8xo0TemN67d4mTpakrKrLp03b9bgCX and add Pytorch Data Parallel.\n\nThe author's repo is https://github.com/krrish94/nerf-pytorch\n\n\nlaunch command if you have one machine with 8 GPUs\n```\npython tiny_nerf_pytorch_ddp.py -n 1 -g 8 -i 0\n```\n\n\n\n(1) nerf_ddp.py is modified from (https://towardsdatascience.com/its-nerf-from-nothing-build-a-vanilla-nerf-with-pytorch-7846e4c45666)ch\n\n\nlaunch command if you have one machine with 8 GPUs\n```\npython nerf_pytorch_ddp.py -n 1 -g 8 -i 0\n```\n\n\nlaunch command if you have two machines with 8 GPUs each\n```\npython nerf_ddp.py -n 2 -g 8,8 -i 0\npython nerf_ddp.py -n 2 -g 8,8 -i 1\n```\n\nThe results show the with DDP, the NeRF training time can be reduced by 5 times.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnwangfw%2Fnerf_ddp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnwangfw%2Fnerf_ddp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnwangfw%2Fnerf_ddp/lists"}