{"id":21476793,"url":"https://github.com/girinchutia/object-detection-inference-interface","last_synced_at":"2026-01-31T05:01:31.526Z","repository":{"id":252519770,"uuid":"840678063","full_name":"GirinChutia/Object-Detection-Inference-Interface","owner":"GirinChutia","description":"Object Detection Inference Interface (ODII) : A common interface for object detection model inference","archived":false,"fork":false,"pushed_at":"2024-08-10T11:37:25.000Z","size":2196,"stargazers_count":1,"open_issues_count":2,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-09T03:04:34.080Z","etag":null,"topics":["artificial-intelligence","artificial-intelligence-framework","computer-vision","inference","inference-engine","object-detection","odii","python","python3","vision","yolo","yolov3","yolov6","yolov7","yolox"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/GirinChutia.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":"2024-08-10T10:53:00.000Z","updated_at":"2024-08-12T17:50:19.000Z","dependencies_parsed_at":"2024-08-10T12:54:20.000Z","dependency_job_id":null,"html_url":"https://github.com/GirinChutia/Object-Detection-Inference-Interface","commit_stats":null,"previous_names":["girinchutia/object-detection-inference-interface"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/GirinChutia/Object-Detection-Inference-Interface","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GirinChutia%2FObject-Detection-Inference-Interface","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GirinChutia%2FObject-Detection-Inference-Interface/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GirinChutia%2FObject-Detection-Inference-Interface/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GirinChutia%2FObject-Detection-Inference-Interface/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/GirinChutia","download_url":"https://codeload.github.com/GirinChutia/Object-Detection-Inference-Interface/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GirinChutia%2FObject-Detection-Inference-Interface/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28929862,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-31T04:05:25.756Z","status":"ssl_error","status_checked_at":"2026-01-31T04:02:35.005Z","response_time":128,"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":["artificial-intelligence","artificial-intelligence-framework","computer-vision","inference","inference-engine","object-detection","odii","python","python3","vision","yolo","yolov3","yolov6","yolov7","yolox"],"created_at":"2024-11-23T11:10:20.843Z","updated_at":"2026-01-31T05:01:31.511Z","avatar_url":"https://github.com/GirinChutia.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Object Detection Inference Interface (ODII)\n\nODII is a Python package designed to provide a unified and streamlined interface for running inference on multiple object detection models under one hood. \nODII facilitates seamless interaction with a range of popular models, including YOLOX, YOLOv3, YOLOv4, YOLOv6, and YOLOv7, without the need to manage multiple codebases or installation processes.\n\n## ✨ Features\n\n- 🚀 **Unified Interface**: Interact with multiple object detection models using a single, easy-to-use interface.\n- 🧹 **Reduced Boilerplate**: Simplifies the setup process by handling the installation of multiple models with varying instructions.\n- 📚 **Lower Learning Curve**: Minimizes the complexity of understanding and writing inference code, making it easier to work with different models.\n- 🔄 **Extensibility**: Easily extend the interface to support additional object detection models.\n\n## 📦 Supported Models\n\n- YOLOX  : https://github.com/Megvii-BaseDetection/YOLOX\n- YOLOv3 : https://github.com/eriklindernoren/PyTorch-YOLOv3\n- YOLOv4 : https://github.com/Tianxiaomo/pytorch-YOLOv4\n- YOLOv6 : https://github.com/meituan/YOLOv6\n- YOLOv7 : https://github.com/WongKinYiu/yolov7\n\n## 📦 Reference for COCO Pretrained Weights\n\n- [YOLOX](src/odii/yolox/readme.md)\n- [YOLOv3](src/odii/yolov3/readme.md)\n- [YOLOv4](src/odii/yolov4/readme.md)\n- [YOLOv6](src/odii/yolov6/readme.md)\n- [YOLOv7](src/odii/yolov7/readme.md)\n\n## 🛠️ Requirements\n\n- Python \u003e= 3.8\n- pip \u003e= 24.2\n\n## 📥 Installation\n\n1. **Install PyTorch**: Follow the instructions on the [PyTorch website](https://pytorch.org/get-started/locally/) to install the appropriate version of PyTorch for your system.\n\n   For example, using pip:\n\n   ```bash\n   pip install torch==1.13.0+cu117 torchvision==0.14.0+cu117 torchaudio==0.13.0 --extra-index-url https://download.pytorch.org/whl/cu117\n   ```\n\n2. **Clone the Repository and Install Dependencies**:\n\n   ```bash\n   git clone https://github.com/GirinChutia/Object-Detection-Inference-Interface.git\n   cd Object-Detection-Inference-Interface\n   python -m pip install -e .\n   ```\n\n## 🛠️ Usage\n\nHere is an example of how to use ODII to run inference on an image:\n\n```python\nfrom odii import INFERENCE, plot_results, load_classes, load_yaml\n\n# Load the classnames\nclassnames = load_classes('coco.names') # ['person','bicycle','car', ... ]\n\n# Set the model paths \u0026 configs \n# (COCO Pretrained weights can be downloaded from links provided in \"Reference for COCO Pretrained Weights\" section)\n\nmodel_config = {'yolov7': {'weights': 'weights/yolov7/yolov7.pt',\n                           'config': None},\n                'yolov4': {'weights': 'weights/yolov4/yolov4.weights',\n                           'config': 'weights/yolov4/yolov4.cfg'},}\n# Set Device\ndevice = 'cuda'\n\n# Input image path\nimage_path = 'tests/images/test_image.jpg'\n\n# --- Infer yolov7 model ---\n\nmodel_name = 'yolov7' \n\nINF = INFERENCE(model_name=model_name,\n                device=device,\n                model_paths={'weights': model_config[model_name]['weights'],\n                              'config': model_config[model_name]['config']})\n\nyolov7_result = INF.infer_image(image_path=image_path,\n                         confidence_threshold=0.4,\n                         nms_threshold=0.4)\n\n\n# --- Infer yolov4 model ---\n\nmodel_name = 'yolov4' \n\nINF = INFERENCE(model_name=model_name,\n                device=device,\n                model_paths={'weights': model_config[model_name]['weights'],\n                              'config': model_config[model_name]['config']})\n\nyoloxm_result = INF.infer_image(image_path=image_path,\n                         confidence_threshold=0.4,\n                         nms_threshold=0.4)\n```\nMore details for inference can be found in this notebook : [inference_demo.ipynb](inference_demo.ipynb)\n\n## 📊 Results Format\nThe inference results are returned as a dictionary with the following format:\n\n```python\n{\n    'boxes': [\n        [74, 11, 900, 613],\n        [77, 149, 245, 361],\n        [560, 359, 737, 565],\n        [139, 38, 414, 610]\n    ],\n    'scores': [\n        0.8257260322570801,\n        0.8446129560470581,\n        0.8616959452629089,\n        0.9366706013679504\n    ],\n    'classes': [2, 16, 28, 0]\n}\n```\n\n## 🙏 Acknowledgements\n\n1. https://github.com/Megvii-BaseDetection/YOLOX\n2. https://github.com/Tianxiaomo/pytorch-YOLOv4\n3. https://github.com/meituan/YOLOv6\n4. https://github.com/WongKinYiu/yolov7\n5. https://github.com/eriklindernoren/PyTorch-YOLOv3\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgirinchutia%2Fobject-detection-inference-interface","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgirinchutia%2Fobject-detection-inference-interface","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgirinchutia%2Fobject-detection-inference-interface/lists"}