{"id":18611756,"url":"https://github.com/deeplabcut/dlc-inferencespeed-benchmark","last_synced_at":"2025-04-10T23:31:03.856Z","repository":{"id":55136570,"uuid":"278249039","full_name":"DeepLabCut/DLC-inferencespeed-benchmark","owner":"DeepLabCut","description":"A database of inference speed benchmark results on various platforms and architectures","archived":false,"fork":false,"pushed_at":"2022-09-01T15:45:30.000Z","size":7270,"stargazers_count":4,"open_issues_count":2,"forks_count":4,"subscribers_count":5,"default_branch":"master","last_synced_at":"2025-03-25T06:09:50.805Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://deeplabcut.github.io/DLC-inferencespeed-benchmark/","language":"Ruby","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/DeepLabCut.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}},"created_at":"2020-07-09T03:05:14.000Z","updated_at":"2022-03-03T12:17:51.000Z","dependencies_parsed_at":"2022-08-14T13:01:03.948Z","dependency_job_id":null,"html_url":"https://github.com/DeepLabCut/DLC-inferencespeed-benchmark","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/DeepLabCut%2FDLC-inferencespeed-benchmark","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DeepLabCut%2FDLC-inferencespeed-benchmark/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DeepLabCut%2FDLC-inferencespeed-benchmark/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DeepLabCut%2FDLC-inferencespeed-benchmark/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DeepLabCut","download_url":"https://codeload.github.com/DeepLabCut/DLC-inferencespeed-benchmark/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248315949,"owners_count":21083351,"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":"2024-11-07T03:14:44.604Z","updated_at":"2025-04-10T23:30:59.180Z","avatar_url":"https://github.com/DeepLabCut.png","language":"Ruby","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DLC Inference Speed Benchmark \u003cimg src=\"https://images.squarespace-cdn.com/content/v1/57f6d51c9f74566f55ecf271/1606082050387-M8M1CFI5DFUZCBAAUI0W/ke17ZwdGBToddI8pDm48kLuMKy7Ws6mFofiFehYynfdZw-zPPgdn4jUwVcJE1ZvWQUxwkmyExglNqGp0IvTJZUJFbgE-7XRK3dMEBRBhUpzp2tFVMcEgqZM8QO7VXXQogrsLnYKC4n4YnYuHC1HMRWygQlqMNAoTF9HaycikLeg/DLClive.png?format=750w\" width=\"350\" title=\"DLC-live\" alt=\"DLC LIVE!\" align=\"right\" vspace = \"50\"\u003e\n\nThis repository stores the benchmark results for [DeepLabCut-live](https://github.com/DeepLabCut/DeepLabCut-live) for each standard dataset, grouped by operating system, processor, and DLC model. Each configuration is tested on a fixed set of videos.\n\n## How to contribute!\n\n1. Install the [DeepLabCut-live! SDK](https://github.com/DeepLabCut/DeepLabCut-live)\n2. git clone the DeepLabCut-live! repo: `git clone https://github.com/DeepLabCut/DLC-inferencespeed-benchmark.git` and run [`./reinstall.sh`](https://github.com/DeepLabCut/DeepLabCut-live/blob/master/reinstall.sh) to be sure it's properly installed.\n2. Run our benchmarking script on your system (with our data/model). Within the DeepLabCut-Live directory you will find the following structure:\n```\nDeepLabCut-Live\n   -Benchmarking\n   --\u003e run_dlclive_benchmark.py\n```\n\nThen you can run (with python3, pythonw on MacOS):\n\n```python\npython run_dlclive_benchmark.py\n```\n\nThis will take some time, depending on your internet connection and hardware. Note that downloading, might take a few minutes, as the multiple models \u0026 videos comprise about 2,2 GB. Then 4 models will be run on two videos for various video sizes. To get you a sense,  this takes about 90 minutes on a Titan RTX. IF you want to run the benchmark on a CPU or slow hardware, you can also change the number of frames, to 1000 in https://github.com/DeepLabCut/DeepLabCut-live/blob/master/benchmarking/run_dlclive_benchmark.py#L24.\n\n3. Please make a pull request here (i.e., add the resulting file to your forked repo under the `_data` folder--i.e., no need to hand edit the file, we will automatically convert your files into the correct yaml file format), and create a new pull request!) or email us: admin@deeplabcut.org if you have any trouble!\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeeplabcut%2Fdlc-inferencespeed-benchmark","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdeeplabcut%2Fdlc-inferencespeed-benchmark","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeeplabcut%2Fdlc-inferencespeed-benchmark/lists"}