{"id":23478177,"url":"https://github.com/mtli/dlgpubench","last_synced_at":"2025-04-14T21:31:34.762Z","repository":{"id":141260931,"uuid":"471575309","full_name":"mtli/DLGPUBench","owner":"mtli","description":"Code for Deep Learning GPU Benchmark: A Latency-Based Approach :watch:","archived":false,"fork":false,"pushed_at":"2025-03-21T05:17:08.000Z","size":85,"stargazers_count":14,"open_issues_count":1,"forks_count":2,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-28T09:36:29.763Z","etag":null,"topics":[],"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/mtli.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-03-19T02:48:10.000Z","updated_at":"2025-03-21T05:17:12.000Z","dependencies_parsed_at":null,"dependency_job_id":"539faccf-9be2-4cfd-ad4b-b20b7166ef69","html_url":"https://github.com/mtli/DLGPUBench","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/mtli%2FDLGPUBench","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mtli%2FDLGPUBench/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mtli%2FDLGPUBench/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mtli%2FDLGPUBench/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mtli","download_url":"https://codeload.github.com/mtli/DLGPUBench/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248963446,"owners_count":21190360,"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":[],"created_at":"2024-12-24T19:16:41.647Z","updated_at":"2025-04-14T21:31:34.722Z","avatar_url":"https://github.com/mtli.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Code for Deep Learning GPU Benchmark: A Latency-Based Approach\n\n\u003cp align=\"center\"\u003e\u003cimg alt=\"demo\" src=\"doc/img/gpubench_demo.png\"\u003e\u003c/p\u003e\n\n(Note that the above is a screenshot of the benchmark. Please visit the [project page](https://mtli.github.io/gpubench/) for the \u003ci\u003elatest version\u003c/i\u003e and an \u003ci\u003einteractive experience\u003c/i\u003e.)\n\n![#fc4903](https://via.placeholder.com/15/fc4903/000000?text=+) Helps to estimate the runtime of algorithms on a different GPU\n\n![#4abdab](https://via.placeholder.com/15/4abdab/000000?text=+) Measures GPU processing speed independent of GPU memory capacity\n\n![#F7B733](https://via.placeholder.com/15/F7B733/000000?text=+) Contains adjustable weightings through interactive UIs\n\nThis repo contains the timing scripts used in the GPU benchmark. This latency-based benchmark is designed to compare algorithms with runtime reported under different GPUs, and it also serves as a GPU purchasing guide. Please check out the [project page](https://mtli.github.io/gpubench/) for the complete benchmark with detailed descriptions. This page documents instructions on how to run the code and the changelog of the benchmark.\n\n\n## Setting Up\n\n```\ngit clone https://github.com/mtli/DLGPUBench.git\ncd DLGPUBench\nconda env create -f environment.yml\nconda activate bench\n```\n\nDownload and unpack ImageNet (ILSVRC2012) and MS COCO. For running the detection scripts, you also need to download the pretrained model from [this link](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth). Modify the dataset paths in each script you plan to run. \n\n## Changelog\n\n### Version 1.1\n- Update the timing setting for classification by excluding the time spent on GPU-host data transfer, and disabling multi-threading to make timing more stable and faster.\n- Update to work with llcv 0.0.9.\n- Change the default batch size for classification inference to 64\n- Add results for GTX 1080 and RTX A6000.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmtli%2Fdlgpubench","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmtli%2Fdlgpubench","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmtli%2Fdlgpubench/lists"}