{"id":13490653,"url":"https://github.com/Flode-Labs/auto-labeler","last_synced_at":"2025-03-28T06:31:41.400Z","repository":{"id":207384646,"uuid":"719094666","full_name":"Flode-Labs/auto-labeler","owner":"Flode-Labs","description":"Label your images using GPT-4!","archived":false,"fork":false,"pushed_at":"2024-01-23T12:28:45.000Z","size":153,"stargazers_count":16,"open_issues_count":0,"forks_count":3,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-10-31T04:34:51.435Z","etag":null,"topics":["gpt-4","image-segmentation"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Flode-Labs.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2023-11-15T12:50:34.000Z","updated_at":"2024-10-24T18:04:53.000Z","dependencies_parsed_at":null,"dependency_job_id":"50cf69ba-baa3-4793-88d0-ecd0e339ed80","html_url":"https://github.com/Flode-Labs/auto-labeler","commit_stats":null,"previous_names":["flode-labs/auto-labeler"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Flode-Labs%2Fauto-labeler","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Flode-Labs%2Fauto-labeler/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Flode-Labs%2Fauto-labeler/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Flode-Labs%2Fauto-labeler/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Flode-Labs","download_url":"https://codeload.github.com/Flode-Labs/auto-labeler/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245984577,"owners_count":20704793,"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":["gpt-4","image-segmentation"],"created_at":"2024-07-31T19:00:49.859Z","updated_at":"2025-03-28T06:31:41.078Z","avatar_url":"https://github.com/Flode-Labs.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"\n![Auto Labeler](./Auto%20Labeler.png)\n\n# Auto Labeler\n\nAuto Labeler is an automated image annotation tool that leverages the power of OpenAI's GPT-4 Vision API to detect objects in images and provide bounding box annotations.\n\n## Features\n\n- Object Detection: Automatically identifies objects in images.\n- Bounding Box Annotations: Generates bounding boxes around detected objects.\n- Multiple Formats: Supports saving annotations in both TensorFlow Object Detection and JSON formats.\n- Custom Labels: Allows for specifying custom object labels for detection.\n\n## Getting Started\n\n### Prerequisites\n\n- Python 3.6 or higher\n\n### Installation\n\nClone the repository to your local machine:\n\n```bash\ngit clone https://github.com/Flode-Labs/auto-labeler.git\n```\n\n\n### Usage\n\n1. Install required packages:\n\n```\npip install -r requirements.txt\n```\n\n2. Set your OpenAI API key:\n\n```python\napi_key = \"YOUR_API_KEY\"\n```\n\n3. Specify the path of the folder with the images that you want to label:\n\n```python\ninput_folder = '/path/to/input/folder'\n```\n\n4. Specify the path of the folder where you want to save the labels:\n\n```python\noutput_folder = '/path/to/output/folder'\n```\n\n5. Specify the format in which you want to save the labels:\n\n```python\noutput_format = 'json' # or 'tf'\n```\n\n6. Define the list of labels you want to detect:\n\n```python\nlabels = ['cat', 'dog', 'bird']\n```\n\n7. Run the main script:\n\n```bash\npython main.py\n```\n\n\n\n\n### Functions\n\n- `encode_image(image_path)`: Encodes the image to base64 format.\n- `detect_objects(image_path, labels)`: Detects objects in the image as specified by labels.\n- `save_tf_annotations(...)`: Saves annotations in TensorFlow Object Detection XML format.\n- `save_json_annotations(...)`: Saves annotations in JSON format.\n- `process_images_in_folder(...)`: Processes multiple images in a specified folder.\n\n\n## Acknowledgments\n\n- OpenAI for providing the GPT-4 Vision API.\n- The Python community for maintaining and improving the libraries used in this project.\n\n---\n\nEnsure you replace `YOUR_API_KEY` with your actual OpenAI API key.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FFlode-Labs%2Fauto-labeler","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FFlode-Labs%2Fauto-labeler","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FFlode-Labs%2Fauto-labeler/lists"}