{"id":50733525,"url":"https://github.com/monajemi-arman/object-detection-utils","last_synced_at":"2026-06-10T11:01:48.501Z","repository":{"id":255991714,"uuid":"854049954","full_name":"monajemi-arman/object-detection-utils","owner":"monajemi-arman","description":"Utility scripts used in object detection model training and testing","archived":false,"fork":false,"pushed_at":"2025-08-21T13:34:56.000Z","size":156,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-08-21T15:46:24.361Z","etag":null,"topics":["coco","data-visualization","dataset-visualizer","deep-learning","object-detection","visualizer","yolo"],"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/monajemi-arman.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":"2024-09-08T09:17:14.000Z","updated_at":"2025-08-21T13:34:59.000Z","dependencies_parsed_at":"2025-05-19T19:37:07.802Z","dependency_job_id":null,"html_url":"https://github.com/monajemi-arman/object-detection-utils","commit_stats":null,"previous_names":["monajemi-arman/object-detection-utils"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/monajemi-arman/object-detection-utils","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/monajemi-arman%2Fobject-detection-utils","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/monajemi-arman%2Fobject-detection-utils/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/monajemi-arman%2Fobject-detection-utils/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/monajemi-arman%2Fobject-detection-utils/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/monajemi-arman","download_url":"https://codeload.github.com/monajemi-arman/object-detection-utils/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/monajemi-arman%2Fobject-detection-utils/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34149132,"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":"2026-06-10T02:00:07.152Z","response_time":89,"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":["coco","data-visualization","dataset-visualizer","deep-learning","object-detection","visualizer","yolo"],"created_at":"2026-06-10T11:01:47.735Z","updated_at":"2026-06-10T11:01:48.486Z","avatar_url":"https://github.com/monajemi-arman.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Object Detection Utils\n* Utility scripts used in object detection model training and testing\n* Utility functions and classes are easy to import in your projects\n\n# Requirements\nBefore using any of the tools, install requirements:\n```bash\npip install -r requirements.txt\n```\n\n# List of Tools\n## Visualizer\nVisualize standardized object detection datasets\n## Features\n* Support COCO and YOLO style dataset\n* Live search for files\n\n### COCO Style dataset\n```bash\npython visualizer.py -m coco -d train/images -l train.json \n```\n\n## YOLO Style dataset\n```bash\npython visualizer.py -m yolo -d train/images -l train/labels \n```\nChoose image             |  Visualize\n:-------------------------:|:-------------------------:\n![visualizer_1](demo/visualizer_1.png) | ![visualizer_2](demo/visualizer_2.png)\n\n\n## YOLO to COCO Converter\nA simple script to convert YOLO annotations to COCO format.\n### Usage\n```bash\npython yolo_to_coco.py \u003cyolo_annotations\u003e \u003cimage_dir\u003e \u003coutput_file\u003e\n```\n*    \u003cyolo_annotations\u003e: Directory with YOLO .txt files.\n*    \u003cimage_dir\u003e: Directory with corresponding images.\n*    \u003coutput_file\u003e: Output COCO JSON file.\n\n## COCO to YOLO Converter\nA simple script to convert YOLO annotations to COCO format.\n### Usage\n```bash\npython coco_to_yolo.py -c \u003ccoco_annotation_json\u003e -i \u003cimage_dir\u003e -o \u003coutput_labels_path\u003e\n```\n*    \u003ccoco_annotation_json\u003e: Path to COCO annotations JSON file.\n*    \u003cimage_dir\u003e: Directory with corresponding images.\n*    \u003coutput_labels_path\u003e: Path to output yolo labels directory path.\n\n\n## Histogram\nDraw histogram of colored or grey images\n* Support medical DICOM image format\n* Support PNG / JPEG\n* Auto-detect colored / grey images\n* Hover on chart to get exact pixel intensity values\n### Usage\n```bash\npython histogram.py \u003cimage_path\u003e\n```\n\n## COCO Metrics\nCalculate metrics using an output JSON containing your model predictions in COCO format. The metrics calculated include mAP (Mean Average Precison).  \nYour output JSON has annotations in this format:\n```json\n\"annotations\": [\n  {\n    \"id\": 0,\n    \"image_id\": 0,\n    \"category_id\": 0,\n    \"bbox\": [...],   // bounding box coordinates according to COCO format\n    \"score\": 0.9994403719902039\n  },\n  ...\n]\n```\n### Usage\n```bash\npython coco_metrics.py predictions.json  # Your predictions JSON\n```\n\n## COCO split train / validation / test set\nYou may happen to forget to split your database into train / validation /test set, in that case you may use this script to split a single `labels.json` into `train.json`, `val.json`, and `test.json`. (no need to split images folder, JSON would suffice)\n\n```bash\npython coco_split_train_val_test.py labels.json  # Your labels JSON\n```\n\n## COCO Multi to Single Class\nSometimes you need to convert your multi-class object detection COCO JSON into a single-class COCO JSON. All categories of objects squashed into one.\n### Usage\n```bash\npython coco_multi_to_single_class.py labels.json  # Your COCO-style JSON\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmonajemi-arman%2Fobject-detection-utils","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmonajemi-arman%2Fobject-detection-utils","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmonajemi-arman%2Fobject-detection-utils/lists"}