{"id":15565391,"url":"https://github.com/dkurt/dl_tradeoff","last_synced_at":"2026-02-18T10:02:35.257Z","repository":{"id":129100149,"uuid":"207138511","full_name":"dkurt/dl_tradeoff","owner":"dkurt","description":"Deep learning accuracy / efficiency tradeoff diagrams","archived":false,"fork":false,"pushed_at":"2019-10-03T07:48:25.000Z","size":33,"stargazers_count":5,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"gh-pages","last_synced_at":"2025-10-10T01:36:15.383Z","etag":null,"topics":["accuracy","computer-vision","deep-learning","efficiency","performance"],"latest_commit_sha":null,"homepage":"https://dkurt.github.io/dl_tradeoff","language":"HTML","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/dkurt.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-09-08T16:11:14.000Z","updated_at":"2020-07-16T19:57:28.000Z","dependencies_parsed_at":"2023-04-13T10:18:45.775Z","dependency_job_id":null,"html_url":"https://github.com/dkurt/dl_tradeoff","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/dkurt/dl_tradeoff","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dkurt%2Fdl_tradeoff","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dkurt%2Fdl_tradeoff/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dkurt%2Fdl_tradeoff/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dkurt%2Fdl_tradeoff/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dkurt","download_url":"https://codeload.github.com/dkurt/dl_tradeoff/tar.gz/refs/heads/gh-pages","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dkurt%2Fdl_tradeoff/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29575343,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-18T08:38:15.585Z","status":"ssl_error","status_checked_at":"2026-02-18T08:38:14.917Z","response_time":162,"last_error":"SSL_read: 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":["accuracy","computer-vision","deep-learning","efficiency","performance"],"created_at":"2024-10-02T16:55:36.878Z","updated_at":"2026-02-18T10:02:35.241Z","avatar_url":"https://github.com/dkurt.png","language":"HTML","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Deep learning network accuracy / efficiency tradeoff diagrams\n\nThis repository contains data and evaluation scripts for plots from\nhttps://dkurt.github.io/dl_tradeoff which represent comparison of different\ncomputer vision deep learning networks by accuracy and efficiency.\n\nThis kind of diagrams can help to choose pre-trained networks for your problem\nor decide which topology / backbone is more suitable for training.\n\n\u003e **NOTE**: Explore datasets that were used for evaluation! Some of the models can be\ntrained for specific use cases and may perform better for some of the scenarios.\nTo put as much networks as possible to a single chart we had to evaluate them on\nthe same data to make metrics comparable. Image previews will be added later.\n\n## How can I add a new network?\n\nThere are two sources which are used for evaluation: [Open Mozel Zoo](https://github.com/opencv/open_model_zoo)\nwhich is more preferable and [custom models](./extra/models). Choose one of them for contribution.\n\n## Found a bug in metric measurement or have concerns about it?\n\nOpen [an issue](https://github.com/dkurt/dl_tradeoff/issues) or contribute\nchanges by [a pull request](https://github.com/dkurt/dl_tradeoff/pulls).\n\nBranches strategy:\n* [master](https://github.com/dkurt/dl_tradeoff/tree/master) - release versions. Is used for rendering.\n* [gh-pages](https://github.com/dkurt/dl_tradeoff/tree/gh-pages) - development branch (choose one for new pull requests).\n\n## Local experiments\n\nIf you want to try to reproduce the data, follow these steps:\n\n1. Clone Open Model Zoo\n  ```bash\n  git clone https://github.com/opencv/open_model_zoo\n  git remote add dkurt https://github.com/dkurt/open_model_zoo\n  git fetch dkurt py_open_model_zoo_v2\n  git checkout py_open_model_zoo_v2\n  export PYTHONPATH=/path/to/open_model_zoo/tools/downloader:$PYTHONPATH\n  ```\n\n2. Install OpenCV at least of version 4.1.2 or starts with OpenVINO R3\n\n3. Download task specific dataset:\n  * COCO for object detection: http://cocodataset.org/#download\n  * ImageNet for classification: http://www.image-net.org/challenges/LSVRC/2012/nonpub-downloads\n  * FDDB for face detection: http://vis-www.cs.umass.edu/fddb/\n\n4. (optional for object detection) Install COCO validation pipeline\n  ```bash\n  git clone https://github.com/cocodataset/cocoapi\n  cd cocoapi/PythonAPI\n  python3 setup.py build_ext --inplace\n  rm -rf build\n  export PYTHONPATH=/path/to/cocoapi/PythonAPI:$PYTHONPATH\n  ```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdkurt%2Fdl_tradeoff","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdkurt%2Fdl_tradeoff","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdkurt%2Fdl_tradeoff/lists"}