{"id":25423960,"url":"https://github.com/georgepearse/visionchain","last_synced_at":"2025-06-27T11:39:45.526Z","repository":{"id":174515166,"uuid":"652339437","full_name":"GeorgePearse/VisionChain","owner":"GeorgePearse","description":"Framework to support stitching together multiple models to create effective Computer Vision systems, as accurate or fast as you need them to be.","archived":false,"fork":false,"pushed_at":"2025-06-18T20:26:40.000Z","size":52333,"stargazers_count":5,"open_issues_count":2,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-19T04:06:12.339Z","etag":null,"topics":["active-learning","computer-vision","heuristics","object-detection"],"latest_commit_sha":null,"homepage":"https://georgepearse.github.io/VisionChain/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/GeorgePearse.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":"2023-06-11T20:44:22.000Z","updated_at":"2025-06-18T20:26:43.000Z","dependencies_parsed_at":"2025-06-18T10:29:35.971Z","dependency_job_id":null,"html_url":"https://github.com/GeorgePearse/VisionChain","commit_stats":null,"previous_names":["georgepearse/visionchain"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/GeorgePearse/VisionChain","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GeorgePearse%2FVisionChain","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GeorgePearse%2FVisionChain/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GeorgePearse%2FVisionChain/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GeorgePearse%2FVisionChain/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/GeorgePearse","download_url":"https://codeload.github.com/GeorgePearse/VisionChain/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GeorgePearse%2FVisionChain/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":260906866,"owners_count":23080596,"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":["active-learning","computer-vision","heuristics","object-detection"],"created_at":"2025-02-16T22:47:22.059Z","updated_at":"2025-06-27T11:39:45.306Z","avatar_url":"https://github.com/GeorgePearse.png","language":"Python","readme":"# VisionChain\nFramework to support common preprocessing and postprocessing steps, along with computer vision heuristics built with opencv, and voting systems ontop of those heuristic-model combos. \n\nCould add a hyperparameter optimizer for things like setting the confidence at which to intervene.\n\nConstraining artificial stupidity and giving AI some hand rails.\n\nTo Do: \n- [ ] Create some templates, e.g. cascade model\n- [ ] Support VQA models on crops or similar\n- [ ] Support NN Classifiers based on the embeddings of multiple models.\n- [ ] Support Segmentation models\n- [ ] Support more from https://github.com/IDEA-Research/Grounded-Segment-Anything/tree/main\n- [ ] Integrate TaskMatrix a bit https://github.com/microsoft/TaskMatrix\n\n\n```python\nmodel = vc.ModelChain(\n    [\n        vc.ConditionalDetector(\n            model=yolov8,\n        ),\n        vc.ConditionalDetector(\n            model=grounded_sam, \n            frame_level_condition = lambda predictions: any([score \u003c 0.5 for score in predictions.scores]),\n            prediction_level_condition = lambda pred: 'cat' in pred.label,\n        ),\n        vc.ConditionalClassifier(\n            model=nn_classifier,\n            prediction_level_condition = lambda pred: 'dog' in pred.label,\n        ),\n    ],\n    log_level = 'verbose',\n)\n```\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgeorgepearse%2Fvisionchain","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgeorgepearse%2Fvisionchain","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgeorgepearse%2Fvisionchain/lists"}