{"id":50677231,"url":"https://github.com/theshubhamp/sample-florence2-object-detection","last_synced_at":"2026-06-08T16:05:55.727Z","repository":{"id":310108206,"uuid":"1038735527","full_name":"theshubhamp/sample-florence2-object-detection","owner":"theshubhamp","description":"Sample: Object Detection over a Video Stream using Microsoft's Florence-2 Model ","archived":false,"fork":false,"pushed_at":"2025-08-15T19:08:00.000Z","size":42,"stargazers_count":0,"open_issues_count":1,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-08-15T20:39:54.687Z","etag":null,"topics":["florence-2","florence2","object-detection","opencv"],"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/theshubhamp.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,"zenodo":null}},"created_at":"2025-08-15T18:19:02.000Z","updated_at":"2025-08-15T19:08:04.000Z","dependencies_parsed_at":"2025-08-15T20:40:01.483Z","dependency_job_id":null,"html_url":"https://github.com/theshubhamp/sample-florence2-object-detection","commit_stats":null,"previous_names":["theshubhamp/sample-florence2-object-detection"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/theshubhamp/sample-florence2-object-detection","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/theshubhamp%2Fsample-florence2-object-detection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/theshubhamp%2Fsample-florence2-object-detection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/theshubhamp%2Fsample-florence2-object-detection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/theshubhamp%2Fsample-florence2-object-detection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/theshubhamp","download_url":"https://codeload.github.com/theshubhamp/sample-florence2-object-detection/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/theshubhamp%2Fsample-florence2-object-detection/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34069528,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-08T02:00:07.615Z","response_time":111,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["florence-2","florence2","object-detection","opencv"],"created_at":"2026-06-08T16:05:54.907Z","updated_at":"2026-06-08T16:05:55.721Z","avatar_url":"https://github.com/theshubhamp.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Sample: Object Detection over a Video Stream using Microsoft's Florence-2 Model \nFlorence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks. Florence-2 can interpret simple text prompts to perform tasks like captioning, object detection, and segmentation. It leverages our FLD-5B dataset, containing 5.4 billion annotations across 126 million images, to master multi-task learning. The model's sequence-to-sequence architecture enables it to excel in both zero-shot and fine-tuned settings, proving to be a competitive vision foundation model.\n\nThis repository hosts a sample for Florence-2's Object Detection capabilities that:\n- Uses OpenCV to read a Video Frames\n- Runs each frame through Florence-2 to get bounding boxes\n- Overlay bounding boxes on top of the original image  \n\nHere's a sample of how it looks live:\n![Demo Image with Bounding Boxes](https://github.com/user-attachments/assets/ac3991e1-ff79-427f-97c7-a18c7d8acce6)\n\n# Run on a Video File\n```shell\nuv run main.py ~/path/to/file.TS\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftheshubhamp%2Fsample-florence2-object-detection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftheshubhamp%2Fsample-florence2-object-detection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftheshubhamp%2Fsample-florence2-object-detection/lists"}