{"id":43124709,"url":"https://github.com/veritone/yolo-sod","last_synced_at":"2026-01-31T20:08:26.335Z","repository":{"id":278405295,"uuid":"892171130","full_name":"veritone/yolo-sod","owner":"veritone","description":"Standalone Object Detector","archived":false,"fork":false,"pushed_at":"2025-02-19T15:16:31.000Z","size":130,"stargazers_count":0,"open_issues_count":1,"forks_count":0,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-02-19T16:27:55.378Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/veritone.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":"2024-11-21T16:21:52.000Z","updated_at":"2025-02-19T15:16:51.000Z","dependencies_parsed_at":"2025-02-19T16:38:09.914Z","dependency_job_id":null,"html_url":"https://github.com/veritone/yolo-sod","commit_stats":null,"previous_names":["veritone/yolo-sod"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/veritone/yolo-sod","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/veritone%2Fyolo-sod","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/veritone%2Fyolo-sod/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/veritone%2Fyolo-sod/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/veritone%2Fyolo-sod/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/veritone","download_url":"https://codeload.github.com/veritone/yolo-sod/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/veritone%2Fyolo-sod/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28952603,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-31T18:30:42.805Z","status":"ssl_error","status_checked_at":"2026-01-31T18:30:19.593Z","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":[],"created_at":"2026-01-31T20:08:26.259Z","updated_at":"2026-01-31T20:08:26.327Z","avatar_url":"https://github.com/veritone.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# yolo_sod\n\nA wrapper around Ultralytics' YOLO library, used for object detection. Results\nare output in a custom JSON format.\n\n# Installation\n\nInstallation requires `poetry`.\n\nTo install `poetry`, use `pipx`:\n\n``` shell\nsudo apt install pipx\npipx install poetry\n```\n\nTo install `yolo-sod`, from this directory run:\n\n``` shell\npoetry install \n```\n\nThis will install all the requirements in their own virtual environment. To\nenter the environment, from this directory run `poetry shell`.\n\n# Exporting a model\n\nTo export a model run\n\n``` shell\nyolo-sod-export\n```\n\ncommand from withing the `poetry` environment. Without any arguments this will\nbuild an INT8 precision TensorRT engine for the large YOLOv11 model. This will\ndownload the necessary files and use the VOC2007 dataset from `/import/datasets`\nfor calibration.\n\nModel files will be saved in the current working directory.\n\nVarious configuration options can also be set. These are listed with:\n\n``` shell\nyolo-sod-export --help\n```\n\nNote that by default a 2 GiB workspace is used for TensorRT. This program takes\na large amount of GPU memory during the calibration and building process, so\nsetting a larger value may lead to memory allocation errors. For the large\nYOLOv11 model a workspace of 2GiB requires just under 8GiB of GPU memory to do\nthe calibration.\n\n# Model inference\n\nTo perform inference on a video run\n\n``` shell\nyolo-sod --input \u003cpath_to_video_file\u003e --output \u003cpath_to_json_file\u003e --model-od \u003cpath_to_OD_model\u003e\n```\n\nfrom within the `poetry` shell. This will decode the video using Nvidia's NvDec\nGPU decoder and perform object detection using the model. The detections will be\nwritten to JSON output of the form:\n\n``` json\n{\n  \"label\": {\n    \"timestamp1\": [\n      [[x0, y0, x1, y1], \"category\", confidence],\n      [[x0, y0, x1, y1], \"category\", confidence],\n      ...\n    ],\n    \"timestamp2\": [\n      [[x0, y0, x1, y1], \"category\", confidence],\n      [[x0, y0, x1, y1], \"category\", confidence],\n      ...\n    ],\n    ...\n  }\n}\n```\n\nSupported video codecs:\n\n- `av1`\n- `h264`\n- `hevc`\n- `mjpeg`\n- `mpeg1video`\n- `mpeg2video`\n- `mpeg4video`\n- `vc1`\n- `vp8`\n- `vp9`\n\nAdditional inference options can be found by running\n\n``` shell\nyolo-sod --help\n```\n\n# Building Packages\n\nTo build packages (source and wheel) run\n\n``` shell\npoetry build\n```\n\nfrom within this directory. The packages will be produced in the `./dist`\ndirectory.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fveritone%2Fyolo-sod","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fveritone%2Fyolo-sod","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fveritone%2Fyolo-sod/lists"}